% Citations refer to arXiv preprints, using initial submission dates, not later proceedings.
% Source URLs are not version-pinned.
% Chronology dates and venue labels are available separately in papers.json.
@misc{lit_2405_08644,
  title = { {Thinking Tokens for Language Modeling} },
  author = {David Herel and Tomas Mikolov},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2405.08644},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.08644}
}

@misc{lit_2310_02226,
  title = { {Think before you speak: Training language models with pause tokens} },
  author = {Sachin Goyal and Ziwei Ji and Ankit Singh Rawat and Aditya Krishna Menon and Sanjiv Kumar and Vaishnavh Nagarajan},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2310.02226},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.02226}
}

@misc{lit_2310_05707,
  title = { {Guiding Language Model Reasoning with Planning Tokens} },
  author = {Xinyi Wang and Lucas Caccia and Oleksiy Ostapenko and Xingdi Yuan and William Yang Wang and Alessandro Sordoni},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2310.05707},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.05707}
}

@misc{lit_2310_10845,
  title = { {CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference} },
  author = {Amirkeivan Mohtashami and Matteo Pagliardini and Martin Jaggi},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2310.10845},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.10845}
}

@misc{lit_2310_14491,
  title = { {Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models} },
  author = {Yifan Hou and Jiaoda Li and Yu Fei and Alessandro Stolfo and Wangchunshu Zhou and Guangtao Zeng and Antoine Bosselut and Mrinmaya Sachan},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2310.14491},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.14491}
}

@misc{lit_2311_01460,
  title = { {Implicit Chain of Thought Reasoning via Knowledge Distillation} },
  author = {Yuntian Deng and Kiran Prasad and Roland Fernandez and Paul Smolensky and Vishrav Chaudhary and Stuart Shieber},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2311.01460},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.01460}
}

@misc{lit_2402_07754,
  title = { {Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models} },
  author = {Jiacheng Ye and Shansan Gong and Liheng Chen and Lin Zheng and Jiahui Gao and Han Shi and Chuan Wu and Xin Jiang and Zhenguo Li and Wei Bi and Lingpeng Kong},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2402.07754},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.07754}
}

@misc{lit_2402_11917,
  title = { {A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task} },
  author = {Jannik Brinkmann and Abhay Sheshadri and Victor Levoso and Paul Swoboda and Christian Bartelt},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2402.11917},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.11917}
}

@misc{lit_2402_14328,
  title = { {Understanding and Patching Compositional Reasoning in LLMs} },
  author = {Zhaoyi Li and Gangwei Jiang and Hong Xie and Linqi Song and Defu Lian and Ying Wei},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2402.14328},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.14328}
}

@misc{lit_2402_16837,
  title = { {Do Large Language Models Latently Perform Multi-Hop Reasoning?} },
  author = {Sohee Yang and Elena Gribovskaya and Nora Kassner and Mor Geva and Sebastian Riedel},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2402.16837},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.16837}
}

@misc{lit_2403_09629,
  title = { {Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking} },
  author = {Eric Zelikman and Georges Harik and Yijia Shao and Varuna Jayasiri and Nick Haber and Noah D. Goodman},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2403.09629},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.09629}
}

@misc{lit_2404_15758,
  title = { {Let's think dot by dot: Hidden computation in transformer language models} },
  author = {Jacob Pfau and William Merrill and Samuel R. Bowman},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2404.15758},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.15758}
}

@misc{lit_2405_14838,
  title = { {From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step} },
  author = {Yuntian Deng and Yejin Choi and Stuart Shieber},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2405.14838},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.14838}
}

@misc{lit_2405_15071,
  title = { {Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization} },
  author = {Boshi Wang and Xiang Yue and Yu Su and Huan Sun},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2405.15071},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.15071}
}

@misc{lit_2406_13858,
  title = { {Distributional Reasoning in LLMs: Parallel Reasoning Processes in Multi-Hop Reasoning} },
  author = {Yuval Shalev and Amir Feder and Ariel Goldstein},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2406.13858},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.13858}
}

@misc{lit_2407_06023,
  title = { {Distilling System 2 into System 1} },
  author = {Ping Yu and Jing Xu and Jason Weston and Ilia Kulikov},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2407.06023},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.06023}
}

@misc{lit_2407_20311,
  title = { {Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process} },
  author = {Tian Ye and Zicheng Xu and Yuanzhi Li and Zeyuan Allen-Zhu},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2407.20311},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.20311}
}

@misc{lit_2409_08561,
  title = { {Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding} },
  author = {Tianqiao Liu and Zui Chen and Zitao Liu and Mi Tian and Weiqi Luo},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2409.08561},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.08561}
}

@misc{lit_2409_14026,
  title = { {Uncovering Latent Chain of Thought Vectors in Language Models} },
  author = {Jason Zhang and Scott Viteri},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2409.14026},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.14026}
}

@misc{lit_2410_09918,
  title = { {Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces} },
  author = {DiJia Su and Sainbayar Sukhbaatar and Michael Rabbat and Yuandong Tian and Qinqing Zheng},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2410.09918},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.09918}
}

@misc{lit_2410_13640,
  title = { {Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation} },
  author = {Yiming Wang and Pei Zhang and Baosong Yang and Derek F. Wong and Rui Wang},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2410.13640},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.13640}
}

@misc{lit_2411_15862,
  title = { {Do LLMs Really Think Step-by-step In Implicit Reasoning?} },
  author = {Yijiong Yu},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2411.15862},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.15862}
}

@misc{lit_2412_06769,
  title = { {Training Large Language Models to Reason in a Continuous Latent Space} },
  author = {Shibo Hao and Sainbayar Sukhbaatar and DiJia Su and Xian Li and Zhiting Hu and Jason Weston and Yuandong Tian},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2412.06769},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.06769}
}

@misc{lit_2412_08635,
  title = { {Multimodal Latent Language Modeling with Next-Token Diffusion} },
  author = {Yutao Sun and Hangbo Bao and Wenhui Wang and Zhiliang Peng and Li Dong and Shaohan Huang and Jianyong Wang and Furu Wei},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2412.08635},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.08635}
}

@misc{lit_2412_13171,
  title = { {Compressed Chain of Thought: Efficient Reasoning Through Dense Representations} },
  author = {Jeffrey Cheng and Benjamin Van Durme},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2412.13171},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.13171}
}

@misc{lit_2501_19201,
  title = { {Efficient Reasoning with Hidden Thinking} },
  author = {Xuan Shen and Yizhou Wang and Yufa Zhou and Xiangxi Shi and Pu Zhao and Yanzhi Wang and Jiuxiang Gu},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2501.19201},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.19201}
}

@misc{lit_2502_03275,
  title = { {Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning} },
  author = {DiJia Su and Hanlin Zhu and Yingchen Xu and Jiantao Jiao and Yuandong Tian and Qinqing Zheng},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.03275},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.03275}
}

@misc{lit_2502_05171,
  title = { {Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach} },
  author = {Jonas Geiping and Sean McLeish and Neel Jain and John Kirchenbauer and Siddharth Singh and Brian R. Bartoldson and Bhavya Kailkhura and Abhinav Bhatele and Tom Goldstein},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.05171},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.05171}
}

@misc{lit_2502_07827,
  title = { {Implicit Language Models are RNNs: Balancing Parallelization and Expressivity} },
  author = {Mark Schöne and Babak Rahmani and Heiner Kremer and Fabian Falck and Hitesh Ballani and Jannes Gladrow},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.07827},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.07827}
}

@misc{lit_2502_08524,
  title = { {LLM Pretraining with Continuous Concepts} },
  author = {Jihoon Tack and Jack Lanchantin and Jane Yu and Andrew Cohen and Ilia Kulikov and Janice Lan and Shibo Hao and Yuandong Tian and Jason Weston and Xian Li},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.08524},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.08524}
}

@misc{lit_2502_13842,
  title = { {Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking} },
  author = {Yilong Chen and Junyuan Shang and Zhenyu Zhang and Yanxi Xie and Jiawei Sheng and Tingwen Liu and Shuohuan Wang and Yu Sun and Hua Wu and Haifeng Wang},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.13842},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.13842}
}

@misc{lit_2502_15589,
  title = { {LightThinker: Thinking Step-by-Step Compression} },
  author = {Jintian Zhang and Yuqi Zhu and Mengshu Sun and Yujie Luo and Shuofei Qiao and Lun Du and Da Zheng and Huajun Chen and Ningyu Zhang},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.15589},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.15589}
}

@misc{lit_2502_17416,
  title = { {Reasoning with Latent Thoughts: On the Power of Looped Transformers} },
  author = {Nikunj Saunshi and Nishanth Dikkala and Zhiyuan Li and Sanjiv Kumar and Sashank J. Reddi},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.17416},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.17416}
}

@misc{lit_2502_21074,
  title = { {CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation} },
  author = {Zhenyi Shen and Hanqi Yan and Linhai Zhang and Zhanghao Hu and Yali Du and Yulan He},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.21074},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.21074}
}

@misc{lit_2503_07604,
  title = { {Implicit Reasoning in Transformers is Reasoning through Shortcuts} },
  author = {Tianhe Lin and Jian Xie and Siyu Yuan and Deqing Yang},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2503.07604},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.07604}
}

@misc{lit_2504_10615,
  title = { {Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models} },
  author = {Thilo Hagendorff and Sarah Fabi},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2504.10615},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.10615}
}

@misc{lit_2504_14992,
  title = { {Efficient Pretraining Length Scaling} },
  author = {Bohong Wu and Shen Yan and Sijun Zhang and Jianqiao Lu and Yutao Zeng and Ya Wang and Xun Zhou},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2504.14992},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.14992}
}

@misc{lit_2505_12629,
  title = { {Enhancing Latent Computation in Transformers with Latent Tokens} },
  author = {Yuchang Sun and Yanxi Chen and Yaliang Li and Bolin Ding},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.12629},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.12629}
}

@misc{lit_2505_13308,
  title = { {Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space} },
  author = {Hengli Li and Chenxi Li and Tong Wu and Xuekai Zhu and Yuxuan Wang and Zhaoxin Yu and Eric Hanchen Jiang and Song-Chun Zhu and Zixia Jia and Ying Nian Wu and Zilong Zheng},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.13308},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.13308}
}

@misc{lit_2505_13898,
  title = { {Do Language Models Use Their Depth Efficiently?} },
  author = {Róbert Csordás and Christopher D. Manning and Christopher Potts},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.13898},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.13898}
}

@misc{lit_2505_14530,
  title = { {Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs} },
  author = {Zhipeng Yang and Junzhuo Li and Siyu Xia and Xuming Hu},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.14530},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.14530}
}

@misc{lit_2505_14827,
  title = { {Text Generation Beyond Discrete Token Sampling} },
  author = {Yufan Zhuang and Liyuan Liu and Chandan Singh and Jingbo Shang and Jianfeng Gao},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.14827},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.14827}
}

@misc{lit_2505_16552,
  title = { {Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains} },
  author = {Wenhui Tan and Jiaze Li and Jianzhong Ju and Zhenbo Luo and Ruihua Song and Jian Luan},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.16552},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.16552}
}

@misc{lit_2505_16782,
  title = { {Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning} },
  author = {Xinghao Chen and Anhao Zhao and Heming Xia and Xuan Lu and Hanlin Wang and Yanjun Chen and Wei Zhang and Jian Wang and Wenjie Li and Xiaoyu Shen},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.16782},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.16782}
}

@misc{lit_2505_17923,
  title = { {Language Models Can Learn Implicit Multi-Hop Reasoning, but Only If They Have Lots of Training Data} },
  author = {Yuekun Yao and Yupei Du and Dawei Zhu and Michael Hahn and Alexander Koller},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.17923},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.17923}
}

@misc{lit_2505_18454,
  title = { {Hybrid Latent Reasoning via Reinforcement Learning} },
  author = {Zhenrui Yue and Bowen Jin and Huimin Zeng and Honglei Zhuang and Zhen Qin and Jinsung Yoon and Lanyu Shang and Jiawei Han and Dong Wang},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.18454},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.18454}
}

@misc{lit_2505_18962,
  title = { {System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts} },
  author = {Xiaoqiang Wang and Suyuchen Wang and Yun Zhu and Bang Liu},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.18962},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.18962}
}

@misc{lit_2505_19245,
  title = { {To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers} },
  author = {Kevin Xu and Issei Sato},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.19245},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.19245}
}

@misc{lit_2505_20674,
  title = { {PonderLM: Pretraining Language Models to Ponder in Continuous Space} },
  author = {Boyi Zeng and Shixiang Song and Siyuan Huang and Yixuan Wang and He Li and Ziwei He and Xinbing Wang and Zhiyu Li and Zhouhan Lin},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.20674},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.20674}
}

@misc{lit_2505_23648,
  title = { {Continuous Chain of Thought Enables Parallel Exploration and Reasoning} },
  author = {Halil Alperen Gozeten and M. Emrullah Ildiz and Xuechen Zhang and Hrayr Harutyunyan and Ankit Singh Rawat and Samet Oymak},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.23648},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.23648}
}

@misc{lit_2506_11752,
  title = { {DART: Distilling Autoregressive Reasoning to Silent Thought} },
  author = {Nan Jiang and Ziming Wu and De-Chuan Zhan and Fuming Lai and Shaobing Lian},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2506.11752},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.11752}
}

@misc{lit_2506_17218,
  title = { {Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens} },
  author = {Zeyuan Yang and Xueyang Yu and Delin Chen and Maohao Shen and Chuang Gan},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2506.17218},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.17218}
}

@misc{lit_2506_18582,
  title = { {Parallel Continuous Chain-of-Thought with Jacobi Iteration} },
  author = {Haoyi Wu and Zhihao Teng and Kewei Tu},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2506.18582},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.18582}
}

@misc{lit_2506_21734,
  title = { {Hierarchical Reasoning Model} },
  author = {Guan Wang and Jin Li and Yuhao Sun and Xing Chen and Changling Liu and Yue Wu and Meng Lu and Sen Song and Yasin Abbasi Yadkori},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2506.21734},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.21734}
}

@misc{lit_2507_02199,
  title = { {Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer} },
  author = {Wenquan Lu and Yuechuan Yang and Kyle Lee and Yanshu Li and Enqi Liu},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2507.02199},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.02199}
}

@misc{lit_2507_06203,
  title = { {A Survey on Latent Reasoning} },
  author = {Rui-Jie Zhu and Tianhao Peng and Tianhao Cheng and Xingwei Qu and Jinfa Huang and Dawei Zhu and Hao Wang and Kaiwen Xue and Xuanliang Zhang and Yong Shan and Tianle Cai and Taylor Kergan and Assel Kembay and Andrew Smith and Chenghua Lin and Binh Nguyen and Yuqi Pan and Yuhong Chou and Zefan Cai and Zhenhe Wu and Yongchi Zhao and Tianyu Liu and Jian Yang and Wangchunshu Zhou and Chujie Zheng and Chongxuan Li and Yuyin Zhou and Zhoujun Li and Zhaoxiang Zhang and Jiaheng Liu and Ge Zhang and Wenhao Huang and Jason Eshraghian},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2507.06203},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.06203}
}

@misc{lit_2507_07996,
  title = { {Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs} },
  author = {Ziyue Li and Yang Li and Tianyi Zhou},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2507.07996},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.07996}
}

@misc{lit_2507_10524,
  title = { {Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation} },
  author = {Sangmin Bae and Yujin Kim and Reza Bayat and Sungnyun Kim and Jiyoun Ha and Tal Schuster and Adam Fisch and Hrayr Harutyunyan and Ziwei Ji and Aaron Courville and Se-Young Yun},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2507.10524},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.10524}
}

@misc{lit_2508_00574,
  title = { {SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought} },
  author = {Jianwei Wang and Ziming Wu and Fuming Lai and Shaobing Lian and Ziqian Zeng},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2508.00574},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.00574}
}

@misc{lit_2508_03440,
  title = { {LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking} },
  author = {Junhong Wu and Jinliang Lu and Zixuan Ren and Gangqiang Hu and Zhi Wu and Dai Dai and Hua Wu},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2508.03440},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.03440}
}

@misc{lit_2509_02350,
  title = { {Implicit Reasoning in Large Language Models: A Comprehensive Survey} },
  author = {Jindong Li and Yali Fu and Li Fan and Jiahong Liu and Yao Shu and Chengwei Qin and Menglin Yang and Irwin King and Rex Ying},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2509.02350},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.02350}
}

@misc{lit_2509_20317,
  title = { {SIM-CoT: Supervised Implicit Chain-of-Thought} },
  author = {Xilin Wei and Xiaoran Liu and Yuhang Zang and Xiaoyi Dong and Yuhang Cao and Jiaqi Wang and Xipeng Qiu and Dahua Lin},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2509.20317},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.20317}
}

@misc{lit_2510_04573,
  title = { {LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning} },
  author = {Haoqiang Kang and Yizhe Zhang and Nikki Lijing Kuang and Nicklas Majamaki and Navdeep Jaitly and Yi-An Ma and Lianhui Qin},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2510.04573},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.04573}
}

@misc{lit_2510_15522,
  title = { {LLM Latent Reasoning as Chain of Superposition} },
  author = {Jingcheng Deng and Liang Pang and Zihao Wei and Shicheng Xu and Zenghao Duan and Kun Xu and Yang Song and Huawei Shen and Xueqi Cheng},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2510.15522},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.15522}
}

@misc{lit_2510_24940,
  title = { {SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens} },
  author = {Yinhan He and Wendy Zheng and Yaochen Zhu and Zaiyi Zheng and Lin Su and Sriram Vasudevan and Qi Guo and Liangjie Hong and Jundong Li},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2510.24940},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.24940}
}

@misc{lit_2510_25741,
  title = { {Scaling Latent Reasoning via Looped Language Models} },
  author = {Rui-Jie Zhu and Zixuan Wang and Kai Hua and Tianyu Zhang and Ziniu Li and Haoran Que and Boyi Wei and Zixin Wen and Fan Yin and He Xing and Lu Li and Jiajun Shi and Kaijing Ma and Shanda Li and Taylor Kergan and Andrew Smith and Xingwei Qu and Mude Hui and Bohong Wu and Qiyang Min and Hongzhi Huang and Xun Zhou and Wei Ye and Jiaheng Liu and Jian Yang and Yunfeng Shi and Chenghua Lin and Enduo Zhao and Tianle Cai and Ge Zhang and Wenhao Huang and Yoshua Bengio and Jason Eshraghian},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2510.25741},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.25741}
}

@misc{lit_2511_07384,
  title = { {Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence} },
  author = {Sean McLeish and Ang Li and John Kirchenbauer and Dayal Singh Kalra and Brian R. Bartoldson and Bhavya Kailkhura and Avi Schwarzschild and Jonas Geiping and Tom Goldstein and Micah Goldblum},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2511.07384},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.07384}
}

@misc{lit_2511_08577,
  title = { {Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning} },
  author = {Tianyu Fu and Yichen You and Zekai Chen and Guohao Dai and Huazhong Yang and Yu Wang},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2511.08577},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.08577}
}

@misc{lit_2511_21581,
  title = { {Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning} },
  author = {Alex Ning and Yen-Ling Kuo and Gabe Gomes},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2511.21581},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.21581}
}

@misc{lit_2512_21711,
  title = { {Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought} },
  author = {Yuyi Zhang and Boyu Tang and Tianjie Ju and Sufeng Duan and Gongshen Liu},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2512.21711},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.21711}
}

@misc{lit_2601_21358,
  title = { {Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization} },
  author = {Jiecong Wang and Hao Peng and Zhanyi Wang and Chunyang Liu and Guanlin Wu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2601.21358},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.21358}
}

@misc{lit_2601_21576,
  title = { {Chain Of Thought Compression: A Theoretical Analysis} },
  author = {Juncai Li and Ru Li and Yuxiang Zhou and Boxiang Ma and Jeff Z. Pan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2601.21576},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.21576}
}

@misc{lit_2601_21598,
  title = { {Beyond Imitation: Reinforcement Learning for Active Latent Planning} },
  author = {Zhi Zheng and Wee Sun Lee},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2601.21598},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.21598}
}

@misc{lit_2602_00449,
  title = { {Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks} },
  author = {Jia Liang and Liangming Pan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2602.00449},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.00449}
}

@misc{lit_2602_01148,
  title = { {Capabilities and Fundamental Limits of Latent Chain-of-Thought} },
  author = {Jiaxuan Zou and Yaozhong Xiong and Yong Liu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2602.01148},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.01148}
}

@misc{lit_2602_08332,
  title = { {Latent Reasoning with Supervised Thinking States} },
  author = {Ido Amos and Avi Caciularu and Mor Geva and Amir Globerson and Jonathan Herzig and Lior Shani and Idan Szpektor},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2602.08332},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.08332}
}

@misc{lit_2602_11683,
  title = { {ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces} },
  author = {Xin Xu and Tong Yu and Xiang Chen and Haoliang Wang and Julian McAuley and Saayan Mitra},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2602.11683},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.11683}
}

@misc{lit_2603_02023,
  title = { {PonderLM-3: Adaptive Token-Wise Pondering with Differentiable Masking} },
  author = {He Li and Feichen Song and Boyi Zeng and Shixiang Song and Zhiqin John Xu and Ziwei He and Zhouhan Lin},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2603.02023},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.02023}
}

@misc{lit_2604_02371,
  title = { {Internalized Reasoning for Long-Context Visual Document Understanding} },
  author = {Austin Veselka},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2604.02371},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.02371}
}

@misc{lit_2604_24881,
  title = { {Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate} },
  author = {John Seon Keun Yi and Aaron Mueller and Dokyun Lee},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2604.24881},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.24881}
}

@misc{lit_2605_28600,
  title = { {Transformers Provably Learn to Internalize Chain-of-Thought} },
  author = {Yixiao Huang and Hanlin Zhu and Zixuan Wang and Jiantao Jiao and Stuart Russell and Somayeh Sojoudi and Song Mei},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2605.28600},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.28600}
}

@misc{lit_2606_01243,
  title = { {Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention} },
  author = {Shuochen Chang and Tong Bai and Xiaofeng Zhang and Qianli Ma and Qingyang Liu and Zhaohe Liao and Yibo Miao and Li Niu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2606.01243},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.01243}
}

@misc{lit_2606_12689,
  title = { {Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models} },
  author = {Darpan Aswal and Thomas Palmeira Ferraz and Yongxin Zhou and Maxime Peyrard},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2606.12689},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.12689}
}

@misc{lit_2606_13106,
  title = { {Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning} },
  author = {Jiayu Yang and Chao Chen and Shengen Wu and Yinhong Liu and Yuxuan Fan and Lujundong Li and Songning Lai and Chengwei Qin and Zhijiang Guo},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2606.13106},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.13106}
}

@misc{lit_2606_18206,
  title = { {Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers} },
  author = {Sajad Movahedi and Vera Milovanović and Shlomo Libo Feigin and Alexander Theus and Thomas Hofmann and Valentina Boeva and T. Konstantin Rusch and Antonio Orvieto},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2606.18206},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.18206}
}

@misc{lit_2606_20075,
  title = { {What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis} },
  author = {Xinghao Chen and Chak Tou Leong and Wenjin Guo and Jian Wang and Wenjie Li and Xiaoyu Shen},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2606.20075},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.20075}
}

@misc{lit_2607_00341,
  title = { {DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning} },
  author = {Hengyu Fu and Tianyu Guo and Zixuan Wang and Hanlin Zhu and Jason D. Lee and Jiantao Jiao and Stuart Russell and Song Mei},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2607.00341},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.00341}
}

@misc{lit_2608_13570,
  title = { {Think in Latent, Explain in Language: Self-Explainable Latent Reasoning} },
  author = {Dayuan Zhao and Shengcao Cao and Yu-Xiong Wang and Liang-Yan Gui},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.13570},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.13570}
}

@misc{lit_2607_06648,
  title = { {Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories} },
  author = {Hengyu Jin and Shu Yang and Di Wang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2607.06648},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.06648}
}

@misc{lit_2607_15178,
  title = { {T²MLR: Transformer with Temporal Middle-Layer Recurrence} },
  author = {Ziyang Cai and Xingyu Zhu and Yihe Dong and Yinghui He and Sanjeev Arora},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2607.15178},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.15178}
}

@misc{lit_2607_16972,
  title = { {Training Continuous Chain of Thought Models: A Tale of Two Regimes} },
  author = {Varun Yerram and He He and Eunsol Choi},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2607.16972},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.16972}
}

@misc{lit_2608_02585,
  title = { {GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning} },
  author = {Zhaoxin Yu and Qi Shen and Hengli Li and Zhaowei Zhang and Song-Chun Zhu and Chi Zhang and Zilong Zheng},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.02585},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.02585}
}

@misc{lit_2608_03624,
  title = { {LoopMTP: A looped transformer guided by latent multi-token prediction} },
  author = {Behzad Shomali and Markus Frey and David Berghaus and Joachim Koehler and Mehdi Ali},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.03624},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.03624}
}

@misc{lit_2608_04928,
  title = { {Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?} },
  author = {Pedro Ferreira and Wilker Aziz and Ivan Titov},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.04928},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.04928}
}

@misc{lit_2608_18222,
  title = { {Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth} },
  author = {Ivan Viakhirev and Kirill Borodin and Amirah Almutairi and Serguei Barannikov and Maxim Abramov and Grach Mkrtchian},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.18222},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.18222}
}

@misc{lit_2608_18230,
  title = { {Allocating Recurrent Compute in Looped Language Models} },
  author = {Ruhai Lin and Yiyang Guo and Rui-Jie Zhu and Hao Ye and Jason K. Eshraghian},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.18230},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.18230}
}

@misc{lit_2608_29956,
  title = { {Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators} },
  author = {Armaan Singh and Ryan Trinh Le and Jasmine Kaur and Abdullah Sultan and Edward Lue Chee Lip and Kiran Nijjer and Adnan Ahmed and Vasu Sharma},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.29956},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.29956}
}

@misc{lit_2609_22197,
  title = { {Dissecting Hierarchical Reasoning Models: A Mechanistic Study} },
  author = {Leo Raphael Rodrigues and Jian Kang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.22197},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.22197}
}

@misc{lit_2609_00874,
  title = { {A Score Is Not a Policy: Measuring the Value of Adaptive Revision} },
  author = {Ayushi Chadha},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.00874},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.00874}
}

@misc{lit_2609_01117,
  title = { {Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs} },
  author = {Zhaoliang Chen and Jie Fu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.01117},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01117}
}

@misc{lit_2609_01343,
  title = { {SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers} },
  author = {Shaowen Wang and Ge Zhang and Kairong Luo and Yuhao Wu and Shaofan Liu and Jiaheng Liu and Wenhao Huang and Shen Yan and Jian Li},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.01343},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01343}
}

@misc{lit_2609_01449,
  title = { {Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning} },
  author = {Mariia Drozdova and Aidan Sirbu and Pietro Miotti and Robert Obryk and Mayalen Etcheverry and Eyvind Niklasson and Blake Richards},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.01449},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01449}
}

@misc{lit_2609_01924,
  title = { {Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?} },
  author = {Wenlong Wang and Fergal Reid},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.01924},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01924}
}

@misc{lit_2609_03379,
  title = { {RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory} },
  author = {Yuxiang Wang and Kunyu Feng and Yingda Shen and Haoning Xu and Junyu Wang and Zhizheng Wu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.03379},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.03379}
}

@misc{lit_2609_03807,
  title = { {Almost Free State Prediction Separation} },
  author = {John Langford and Nathan Godey and Giovanni Monea and Yoav Artzi and Harry Dong and Ying Fan and Gustavo de Rosa and Zheng Zhan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.03807},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.03807}
}

@misc{lit_2609_04489,
  title = { {Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective} },
  author = {Jaehyeon Kim and Suhwan Kim and Nakyung Lee and Yeongoon Kim and Jimin Seo and Giho Lee and Jungwoo Lee},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.04489},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.04489}
}

@misc{lit_2609_04963,
  title = { {Fractal basins trap latent reasoning} },
  author = {Jeffrey Lai and Anthony Bao and John Quinn and William Gilpin},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.04963},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.04963}
}

@misc{lit_2609_05988,
  title = { {DART: Distributional Adversarial Recurrent Training for Algorithm Learning} },
  author = {Hieu Tran Bao and Phung Thanh Dang and Pham Quang Nhat Minh and Hoang Thanh Tung},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.05988},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.05988}
}

@misc{lit_2609_09928,
  title = { {Structural Process Supervision for Latent Chain-of-Thought Reasoning} },
  author = {Yiqi Li and Xu Chen and Chen Ju and Jiangchao Yao and Zhaoyang Li and Jinsong Lan and Xiaoyong Zhu and Yu Wang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.09928},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.09928}
}

@misc{lit_2609_13060,
  title = { {CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models} },
  author = {Blake Olson and Yuhang Song and Emmett McQuinn and Yuan Shangguan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.13060},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.13060}
}

@misc{lit_2609_15160,
  title = { {T-LoopFormer: Token-Level Elastic-Depth Looped Transformers with Dynamic Routing} },
  author = {Mingqian Yu and Wenpeng Zhang and Shaobo Cui and Peilin Zhao},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.15160},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.15160}
}

@misc{lit_2609_16372,
  title = { {Register Tokens for Bounded-State Reasoning in Diffusion Language Models} },
  author = {Albert Ge and Chandan Singh and Yufan Zhuang and Xiaodong Liu and Jianfeng Gao and Frederic Sala},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.16372},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.16372}
}

@misc{lit_2609_16665,
  title = { {Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers} },
  author = {Zhihao Guo and Zonghan Wu and Haizhou Du and Huan Huo and Yilei Shao and Athanasios V. Vasilakos and Qingsong Wen},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.16665},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.16665}
}

@misc{lit_2609_17184,
  title = { {LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers} },
  author = {SangLyul Cho and Langqing Cui and Sehoon Kim and Dongsu Han and Insu Han},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.17184},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.17184}
}

@misc{lit_2609_19107,
  title = { {How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents} },
  author = {Zixi Chen and Akshay Vegesna and Samip Dahal and Andrew Gordon Wilson},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.19107},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.19107}
}

@misc{lit_2609_19521,
  title = { {Storing Is Not Remembering: LSTM-UT and Bounded Gated Memory for Looped Transformers} },
  author = {Aras Kavuncu and Muhammad Burhan Hafez},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.19521},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.19521}
}

@misc{lit_2609_19717,
  title = { {Learn Your Own Thoughts: Abstract Token Curriculum} },
  author = {Khashayar Gatmiry and Avrajit Ghosh and Parsa Mirtaheri and Jason D. Lee and Nika Haghtalab and Emmanuel Abbe and Peter Bartlett},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.19717},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.19717}
}

@misc{lit_2609_19878,
  title = { {Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning} },
  author = {Haoqiang Kang and Yizhe Zhang and Nikki Lijing Kuang and Jiatao Gu and Yian Ma and Lianhui Qin},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.19878},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.19878}
}

@misc{lit_2609_20398,
  title = { {Schema-Anchored Latent Reasoning for Semantic Parsing-Based Knowledge Base Question Answering} },
  author = {Guangze Gao and Zixuan Li and Sikui Zhang and Chunfeng Yuan and Wenjuan Li and Bing Li and Xiaolong Jin and Weiming Hu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.20398},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.20398}
}

@misc{lit_2609_20981,
  title = { {CaLR: Causal Latent Revision for Robust Diffusion Reasoning} },
  author = {Wei Cai and Jian Zhao and Yuchen Yuan and Xuelong Li},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.20981},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.20981}
}

@misc{lit_2609_21605,
  title = { {Trading Depth for Time in Recurrent Transformers} },
  author = {Zeyi Huang and Xuehai He and Yelong Shen and Yong Jae Lee},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.21605},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.21605}
}

@misc{lit_2609_21662,
  title = { {When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap} },
  author = {Gaoxiang Huang and Lei Qi},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.21662},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.21662}
}

@misc{lit_2609_23033,
  title = { {WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models} },
  author = {Hyeongju Ha and Jae-Joon Kim},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.23033},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.23033}
}

@misc{lit_2609_24196,
  title = { {LoopCD: Loop-wise Contrastive Decoding for Improving Reasoning in Looped Language Models} },
  author = {Byeongho Yu and Junhyuk So and Eunhyeok Park},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.24196},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.24196}
}

@misc{lit_2609_24346,
  title = { {LADDER: Graph-Guided Diffusion Language Models for Efficient Multi-Hop Reasoning} },
  author = {Senlei Zhang and Linhao Luo and Qian-Wen Zhang and Siyu An and Junnan Dong and Shuhao Zhang and Xing Sun},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.24346},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.24346}
}

@misc{lit_2609_27220,
  title = { {LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models} },
  author = {Guoshenghui Zhao and Tan Yu and Weijie Zhao},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.27220},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27220}
}

@misc{lit_2609_27373,
  title = { {Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models} },
  author = {Ke Wan and Chen Chen},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.27373},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27373}
}

@misc{lit_2609_28272,
  title = { {Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models} },
  author = {Dian Jin and Kairong Han and Baohong Li and Xinpeng Dong and Zijing Hu and Nuanqiao Shan and Fei Wu and Kun Kuang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.28272},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.28272}
}

@misc{lit_2609_29102,
  title = { {ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks} },
  author = {Zeyu Michael Li and William Xingxu Chen and Bingshuo Qian and Jiayin Liu and Xiang Cheng},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.29102},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.29102}
}

@misc{lit_2610_08820,
  title = { {Task-Oriented Key-Layer KV Communication for Efficient Latent Multi-Agent Collaboration} },
  author = {Dongsen Zhang and Peipei Li and Zekun Li and Wenjun Xu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.08820},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.08820}
}

@misc{lit_2609_30783,
  title = { {Skip the Talk, Re-Focus on Vision: Latent Reasoning for Reasoning Segmentation in Multimodal Large Language Models} },
  author = {Tianhang Guo and Yulin He and Wei Chen and Wenjuan Zhou and Yuhang Li and Xinbiao Gan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.30783},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.30783}
}

@misc{lit_2609_33134,
  title = { {Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought?} },
  author = {Jiashu He and Jinxuan Fan and Xiao Xiao and Radu Marculescu and Alejandro Ribeiro},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.33134},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.33134}
}

@misc{lit_2609_33144,
  title = { {Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers} },
  author = {Jia Liang and Xi Jin and Liangming Pan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.33144},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.33144}
}

@misc{lit_2609_33270,
  title = { {Structured Sparse Memory for Recurrent Reasoning} },
  author = {Zixuan Zhao and Samuel Wheeler and Neil Getty and Xiaotian Duan and Rick Stevens and Fangfang Xia},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.33270},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.33270}
}

@misc{lit_2609_33271,
  title = { {Next Thoughts Are Distributions: Generative Autoregressive Reasoning in the Latent Space} },
  author = {Yang Li and Yi Wang and Shiyuan Huang and Yang Liu and Hao Wang and Chengzhi Mao},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.33271},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.33271}
}

@misc{lit_2609_33402,
  title = { {VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings} },
  author = {Peixi Wu and Mingzhou Jiang and Feipeng Ma and Biao Yang and Yunhao Zhou and Wei Yuan and Bosong Chai and Huizu Lin and Jie Chen and Zhangchi Hu and Fan Yang and Wenwu Ou and Hebei Li and Xiaoyan Sun},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.33402},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.33402}
}

@misc{lit_2609_34218,
  title = { {Loop Dropout: Regularizing Shared Updates in Looped Language Models} },
  author = {Zirui Zhu and Hailun Xu and Xuanlei Zhao and Yong Liu and Yingxuan Ren and Kanchan Sarkar and Kun Xu and Yang You},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.34218},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34218}
}

@misc{lit_2609_34408,
  title = { {Distilling Visual Reasoning into Text Space} },
  author = {Wenhan Yang and Nilay Naharas and Ali Payani and Baharan Mirzasoleiman},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.34408},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34408}
}

@misc{lit_2609_34488,
  title = { {FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL} },
  author = {Xun Wang and Ruishuo Chen and Yu Chen and Zhuoran Li and Longbo Huang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.34488},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34488}
}

@misc{lit_2609_34538,
  title = { {Shallow Queries, Mature Values: Depth-Asynchronous Self-Speculation for Looped Transformers} },
  author = {Guanghao Li and Zihan Su and Hao Yu and Jinyang Jiang and Tao Ren and Zehao Li and Feng Lu and Ming Tang and Chun Yuan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.34538},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34538}
}

@misc{lit_2609_35472,
  title = { {Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning} },
  author = {Yan Zhan and Shaobo Liu and Zhijun Gao},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.35472},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.35472}
}

@misc{lit_2609_35694,
  title = { {Reasoning with Continuous Latent Diffusion} },
  author = {Xiang Cheng},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.35694},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.35694}
}

@misc{lit_2609_35748,
  title = { {Improving Test-Time Scaling with Adaptive Looped Transformers} },
  author = {Yichen You and Tianyu Fu and Aosong Feng and Xingtai Lv and Xuefei Ning and Ning Ding and Yu Wang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.35748},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.35748}
}

@misc{lit_2609_35751,
  title = { {How to Loop MoE: Flatten the Experts, Untie the Attention} },
  author = {Shouren Wang and Chuang Ma and Mohsen Hariri and Debargha Ganguly and Wang Yang and Xiaoqing Tong and Qianying Liu and Xiaotian Han and Vipin Chaudhary},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.35751},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.35751}
}

@misc{lit_2610_08833,
  title = { {CoDR: Training-Free Confidence-Drift Remasking for Diffusion Language Models} },
  author = {Yue Wu and Qinghe Zhang and Yu Zhang and Jian Huang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.08833},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.08833}
}

@misc{lit_2609_36452,
  title = { {Reliable Parallel Decoding in Masked Diffusion Language Models} },
  author = {Zhenghao He and Bohan Liu and Guangzhi Xiong and Aidong Zhang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.36452},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.36452}
}

@misc{lit_2609_36636,
  title = { {What Makes Recurrence Effective in Looped Language Models?} },
  author = {Xinlin Zhuang and Siyuan Wang and Imran Razzak and Weiyang Liu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.36636},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.36636}
}

@misc{lit_2609_36653,
  title = { {Scheduling Recursive Reasoning in Looped Transformers} },
  author = {Boyuan Wang and Chengyao Yu and Jiaxi Ren and Hongxin Wei and Bingyi Jing and Yuxin Tao},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.36653},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.36653}
}

@misc{lit_2609_37351,
  title = { {Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling} },
  author = {Zeyu Jia},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.37351},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.37351}
}

@misc{lit_2609_37379,
  title = { {Looped Transformers as Optimizers} },
  author = {Yulong Huang and Chen Jiang and Zhanpeng Zhou and Hongtao Zhang and Tianyu Li and Tianyu He and Xiangyu Zhang and Bojun Cheng},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.37379},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.37379}
}

@misc{lit_2609_37432,
  title = { {Looped Actor: Depth-Recurrent Reasoning Models for Reinforcement Learning} },
  author = {T. Konstantin Rusch and Tim Seyde and Jared Boyer and Zach J. Patterson and Daniela Rus},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.37432},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.37432}
}

@misc{lit_2609_38426,
  title = { {LoopVL: Recurrent Visual Intelligence} },
  author = {Zhe Qian and Ziyang Gong and Zhongxing Xu and Hehan Li and Zhonghua Wang and Hanmeng Liu and Liwei Qian and Xin Pei and Peizhi Xu and Fei Luo and Mingxuan Wang and Xue Yang and Shiwei Liu and Yanbiao Ma and Junchi Yan and Jungong Han},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.38426},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.38426}
}

@misc{lit_2609_38806,
  title = { {Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems} },
  author = {Woosang Jeon and Jaeyeon Kim and Sham Kakade and Yilun Du and Amrit Singh Bedi and Arun Kumar Chithanar and Chul Lee and Taehyeong Kim and Sitan Chen},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.38806},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.38806}
}

@misc{lit_2609_39740,
  title = { {LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation} },
  author = {Xiaoqiang Wang and Suyuchen Wang and Bang Liu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.39740},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.39740}
}

@misc{lit_2609_39892,
  title = { {Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does} },
  author = {Jiaju Wu and Yi Hu and Muhan Zhang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.39892},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.39892}
}

@misc{lit_2609_39967,
  title = { {What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling} },
  author = {Yuliana Shakhvalieva and Dmitrii Kharchev and Viacheslav Bezrukov and Inessa Fedorova and Dmitry Bocharov and Ivan Oseledets and Valerii Ternovskii},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.39967},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.39967}
}

@misc{lit_2609_40316,
  title = { {Scaling Laws for Looped Mixture of Experts} },
  author = {Yanbei Chen and Anirudh Goyal and Raghuraman Krishnamoorthi},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2609.40316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.40316}
}

@misc{lit_2610_00661,
  title = { {Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models} },
  author = {Yue Yu and Bowen Zuo and David Crandall and Yinglun Zhu and Dongruo Zhou},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.00661},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.00661}
}

@misc{lit_2610_00673,
  title = { {Closing the Loop: Practical Training Recipes for Looped Language Models} },
  author = {Andrei Marchenko and Viacheslav Bezrukov and Oleg Kashurin and Inessa Fedorova and Dmitry Bocharov and Yuliana Shakhvalieva and Maria Tikhonova and Valerii Ternovskii},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.00673},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.00673}
}

@misc{lit_2610_14030,
  title = { {Rotate the Loop: Blockwise Conformality for Looped Transformers} },
  author = {Alexey Zemtsov and Albina Klepach and Vadim Lomshakov and Andrei Polubarov and Nikita Lyubaykin and Alexander Derevyagin and Vladislav Kurenkov and Alexander Nikulin},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.14030},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.14030}
}

@misc{lit_2610_01153,
  title = { {Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts} },
  author = {Di He and Pengxiang Li and Da Chang and Qingyan Meng and Lu Yin and Shiwei Liu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.01153},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.01153}
}

@misc{lit_2610_01177,
  title = { {Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models} },
  author = {Darpan Aswal and Céline Hudelot},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.01177},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.01177}
}

@misc{lit_2610_02185,
  title = { {Decoding Looped Transformers Better for (Almost) Free} },
  author = {Weihao Liu and Huangjie Zheng and Tianrong Chen and Rohit Dilip and Richard He Bai and Yizhu Jiao and Yuyang Wang and Ruixiang Zhang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.02185},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.02185}
}

@misc{lit_2610_02193,
  title = { {Hierarchical Continuous Diffusion Language Models} },
  author = {Hui Ren and Zihan Li and Chang Liu and Huidong Liu and Alexander Schwing},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.02193},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.02193}
}

@misc{lit_2610_02383,
  title = { {The Surprising Effectiveness of Shared Memory in Looped Transformers} },
  author = {Giovanni Monea and Keshav Ramji and Yousef El-Kurdi and Luis A. Lastras and Yoav Artzi and Nathan Godey and Ramón Fernandez Astudillo},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.02383},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.02383}
}

@misc{lit_2610_02665,
  title = { {Large Language Continuous Diffusion Models} },
  author = {Zhihan Yang and Wei Guo and Jean-Marie Lemercier and Simon Welker and Yonggan Fu and Mohammad Mahdi Kamani and Sajad Norouzi and Julius Berner and Tomas Geffner and Karsten Kreis and Yongxin Chen and Molei Tao and John Thickstun and Pavlo Molchanov and Ante Jukić and Arash Vahdat and Morteza Mardani},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.02665},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.02665}
}

@misc{lit_2610_02741,
  title = { {On the Chain-of-Thought Monitorability of Looped Language Models} },
  author = {Han Wang and Ishwar B Balappanawar and Huan Zhang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.02741},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.02741}
}

@misc{lit_2610_03665,
  title = { {Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models} },
  author = {Seo Hyun Kim and Sunwoo Hong and Younwoo Choi and Chen-Hao Chao and Se-Young Yun and Rahul G. Krishnan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.03665},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.03665}
}

@misc{lit_2610_06949,
  title = { {AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models} },
  author = {Lee Seung-woo and Bowen Qi},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.06949},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.06949}
}

@misc{lit_2610_04864,
  title = { {Enhancing Long-Video VLM Embeddings with Query-Aware Streaming Latent Reasoning} },
  author = {Haozhe Chi and Song Jin and Yang Jin and Yadong Mu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.04864},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.04864}
}

@misc{lit_2610_06666,
  title = { {What Matters for Latent Reasoning with Flow Matching} },
  author = {Yassine Ouali and Adrian Bulat and Georgios Tzimiropoulos},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.06666},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.06666}
}

@misc{lit_2610_06833,
  title = { {Towards Looped Models Done Right, Part II: Rethinking at Fixed Points} },
  author = {Benhao Huang and Chufan Shi and Junlin Chen and Shicheng Wen and Zhengzhong Liu and Eric Xing and Xuezhe Ma},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.06833},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.06833}
}

@misc{lit_2610_07175,
  title = { {CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression} },
  author = {Zhaoyang Wei and Bowen Jiang and Yanchao Hao and Wenchao Ding and Zheng Wei and Shaocheng Wu and Zhenjun Han and Jianbin Jiao},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.07175},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.07175}
}

@misc{lit_2610_07591,
  title = { {Recurrent Looped Transformer} },
  author = {Yifan Zhang and Jichen Feng and Shihan Qin and Sun-Yuan Kung and Mengdi Wang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.07591},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.07591}
}

@misc{lit_2610_07730,
  title = { {SanSi: A Looped Typed Decision Model for System 1.5 Thinking} },
  author = {Shuyu Gan and Young-Jun Lee and Dongyeop Kang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.07730},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.07730}
}

@misc{lit_2610_07907,
  title = { {Continuous Memory Machines} },
  author = {Ciaran Regan and Kai Arulkumaran and Luke Darlow and Stefania Druga and Sebastian Risi and Llion Jones},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.07907},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.07907}
}

@misc{lit_2610_09145,
  title = { {Noise Your Prompt: Noising Conditioning Tokens in Continuous Diffusion Language Models} },
  author = {Justin Jung},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.09145},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.09145}
}

@misc{lit_2610_09416,
  title = { {Efficient Reasoning with Flow Language Models} },
  author = {Hanru Bai and Faissal Izermine and Oscar Davis and T. Konstantin Rusch},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.09416},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.09416}
}

@misc{lit_2610_09876,
  title = { {Think Before You Paint: Recursive Latent Reasoning for Diffusion Models} },
  author = {Paweł Skierś and Małgorzata Grzanka and Wojciech Masarczyk and Jan-Willem van de Meent and Kamil Deja},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.09876},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.09876}
}

@misc{lit_2610_10623,
  title = { {Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models} },
  author = {Yi Wang and Rui Qian and Yu Li and Haoyang Yao and Wenjie Wang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.10623},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.10623}
}

@misc{lit_2610_10625,
  title = { {Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models} },
  author = {Yi Wang and Xiuyuan Qi and Dongqi Han and Dongsheng Li and Wenjie Wang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.10625},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.10625}
}

@misc{lit_2610_10996,
  title = { {Invariant-Measure Reasoners: Stable Representations for Latent Reasoning} },
  author = {Yuto Inui and Takuya Konishi and Yoshinobu Kawahara},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.10996},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.10996}
}

@misc{lit_2610_20641,
  title = { {AbridgeKV: Compressing Long Reasoning into the KV Cache of Learned Pause Tokens} },
  author = {Jack Cai and Lijie Yang and Vasilis Kontonis and Dimitris Papailiopoulos and Shivam Garg},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.20641},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.20641}
}

@misc{lit_2610_11570,
  title = { {Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals} },
  author = {Pengxiang Li and Dilxat Muhtar and Di He and Guinan Su and Lu Yin and Shiwei Liu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.11570},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.11570}
}

@misc{lit_2610_12582,
  title = { {One Model to Loop Them All: Elastic Latent Recurrence for Language Models} },
  author = {Faisal Ladhak and Shantanu Acharya and Santiago Akle Serano and Simeng Sun and Boris Ginsburg and Krishna C Puvvada},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.12582},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.12582}
}

@misc{lit_2610_13330,
  title = { {Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning} },
  author = {Mengdi Liu and Chenghao Jia and Hong Chang and Shiguang Shan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.13330},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.13330}
}

@misc{lit_2610_13527,
  title = { {S-Space: Exploring Spatial Workspace in Multimodal Language Models} },
  author = {Zhiyuan Shi and Xiang Li and Xingzhuo Guo and Shangchen Miao and Weiliang Chen and Qiyu Dai and Jinshan Ren and Jiangran Lyu and Fangfu Liu and Mingsheng Long and Jialong Wu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.13527},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.13527}
}

@misc{lit_2610_14252,
  title = { {Adaptive-Depth Is a Finishing Stage} },
  author = {Andrei Piterbarg and Sean McLeish and Dhruv Pai and Benjamin Keigwin},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.14252},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.14252}
}

@misc{lit_2610_14456,
  title = { {Learning to Extrapolate in Depth with Looped Transformers} },
  author = {Huitao Yang and Jianhao Huang and Zixuan Wang and Baharan Mirzasoleiman},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.14456},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.14456}
}

@misc{lit_2610_15081,
  title = { {Knowledge transfer between simple discrete worlds} },
  author = {Silvère Gangloff and Jan Hula},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.15081},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.15081}
}

@misc{lit_2610_15097,
  title = { {Anchors Enhance Controllability and Reasoning of Diffusion Language Models} },
  author = {Feiyu Qu and Zheng Huang and Andrea Zanette},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.15097},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.15097}
}

@misc{lit_2610_15218,
  title = { {Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models} },
  author = {Seyedarmin Azizi and Erfan Baghaei Potraghloo and Arya Fayyazi and Saeid Shokoufa and Massoud Pedram},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.15218},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.15218}
}

@misc{lit_2610_15501,
  title = { {Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers} },
  author = {Ziyi Chen and Yan Zhang and Jianhui Wei and Jianing Yin and Daoan Zhang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.15501},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.15501}
}

@misc{lit_2610_16427,
  title = { {Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning} },
  author = {Maxime Illouz},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.16427},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.16427}
}

@misc{lit_2610_17679,
  title = { {Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning} },
  author = {Ying Li and Yuqi Chen and Sixuan Li and Yunfeng Cai},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.17679},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.17679}
}

@misc{lit_2610_18127,
  title = { {Monitoring latent reasoning in looped language models} },
  author = {Pawel Olszowiec and Paulina Tomaszewska and Maciej Żelaszczyk and Michal Byra and Neo Christopher Chung},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.18127},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.18127}
}

@misc{lit_2610_18162,
  title = { {LoOPSD: On-Policy Self-Distillation with Looped Teachers} },
  author = {Wei Fan and Qingyue Yang and Chao-Hong Tan and Qian Chen and Wen Wang and Xiangang Li and Kejiang Chen and Weiming Zhang and Nenghai Yu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.18162},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.18162}
}

@misc{lit_2610_18174,
  title = { {Looped Reasoning Finishes Earlier Than You Think} },
  author = {Sumin Park and T. Konstantin Rusch},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.18174},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.18174}
}

@misc{lit_2610_18547,
  title = { {Input-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners} },
  author = {Haochen Shi and Tianwen Fu and Qianggang Ding and Yinhan Lu and Yizhan Li and Huan Zhang and Yajie Zhao and Xingdi Yuan and Hengyang Lu and Bang Liu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.18547},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.18547}
}

@misc{lit_2610_19080,
  title = { {Backpropagating Verifier Rewards Through Continuous Flow Language Models} },
  author = {Xu Han and Jiajing Hu and Li-Ping Liu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.19080},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19080}
}

@misc{lit_2610_19220,
  title = { {Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine} },
  author = {Thomas Hannagan},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.19220},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19220}
}

@misc{lit_2610_19408,
  title = { {ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models} },
  author = {Zhaoyan Jia and Chengwei Zhou and Gourav Datta and Massoud Pedram},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.19408},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19408}
}

@misc{lit_2610_19568,
  title = { {INTACT: Inducing Latent Reasoning on a Frozen Backbone} },
  author = {Kutay Tire and Atula Tejaswi and Haris Vikalo and Sujay Sanghavi},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.19568},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19568}
}

@misc{lit_2610_19768,
  title = { {Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers} },
  author = {Peilong Zhou and Hongtao Zhang and Yulong Huang and Cangyuan Li and Mingyu Chen and Ying Wang},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.19768},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19768}
}

@misc{lit_2610_19871,
  title = { {Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning} },
  author = {Mingyeong Kim and Gyusang Cho and Juho Lee and Giung Nam},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.19871},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19871}
}

@misc{lit_2610_21182,
  title = { {Does Latent Chain-of-Thought Actually Reason? A Single, Unifying Taxonomy for Latent Reasoning} },
  author = {Jingjie Qiu and Sheldon Yu and Xunyi Jiang and Jiajin Liu and Zihan Huang and Zhendong Chu and Tong Yu and Julian McAuley and Junda Wu},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.21182},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.21182}
}

@misc{lit_2610_21594,
  title = { {LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models} },
  author = {Zixuan Liu and Nan Xue and Rui Bao and Yuhang Xu and Xiaofeng Cao and Jiangchao Yao and Zhiyong Chen},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.21594},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.21594}
}

@misc{lit_precursor_1603_08983,
  title = { {Adaptive Computation Time for Recurrent Neural Networks} },
  author = {Alex Graves},
  year = {2016},
  note = {arXiv preprint},
  eprint = {1603.08983},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1603.08983}
}

@misc{lit_precursor_1807_03819,
  title = { {Universal Transformers} },
  author = {Mostafa Dehghani and Stephan Gouws and Oriol Vinyals and Jakob Uszkoreit and Łukasz Kaiser},
  year = {2018},
  note = {arXiv preprint},
  eprint = {1807.03819},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1807.03819}
}

@misc{lit_precursor_1909_01377,
  title = { {Deep Equilibrium Models} },
  author = {Shaojie Bai and J. Zico Kolter and Vladlen Koltun},
  year = {2019},
  note = {arXiv preprint},
  eprint = {1909.01377},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1909.01377}
}

@misc{lit_precursor_2106_04537,
  title = { {Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks} },
  author = {Avi Schwarzschild and Eitan Borgnia and Arjun Gupta and Furong Huang and Uzi Vishkin and Micah Goldblum and Tom Goldstein},
  year = {2021},
  note = {arXiv preprint},
  eprint = {2106.04537},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2106.04537}
}

@misc{lit_precursor_2107_05407,
  title = { {PonderNet: Learning to Ponder} },
  author = {Andrea Banino and Jan Balaguer and Charles Blundell},
  year = {2021},
  note = {arXiv preprint},
  eprint = {2107.05407},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2107.05407}
}

@misc{lit_precursor_2305_14699,
  title = { {Can Transformers Learn to Solve Problems Recursively?} },
  author = {Shizhuo Dylan Zhang and Curt Tigges and Stella Biderman and Maxim Raginsky and Talia Ringer},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2305.14699},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.14699}
}

@misc{lit_precursor_2311_12424,
  title = { {Looped Transformers are Better at Learning Learning Algorithms} },
  author = {Liu Yang and Kangwook Lee and Robert Nowak and Dimitris Papailiopoulos},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2311.12424},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.12424}
}

@misc{lit_precursor_2402_13572,
  title = { {AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures} },
  author = {Yihang Gao and Chuanyang Zheng and Enze Xie and Han Shi and Tianyang Hu and Yu Li and Michael K. Ng and Zhenguo Li and Zhaoqiang Liu},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2402.13572},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.13572}
}