# Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning

Authors: Mengdi Liu, Chenghao Jia, Hong Chang, Shiguang Shan.

ChemDiffAgent denoises interleaved textual reasoning and tool-use trajectories, letting tool decisions depend on context across the trajectory. A chemistry benchmark and matched-budget comparisons test this alternative to left-to-right agent generation.

First public: 2026-10-09.
ArXiv initial submission: 2026-10-09.

[Original paper](https://arxiv.org/abs/2610.13330) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.13330/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.13330/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.13330/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.13330/record.json)

## Approaches

- [Alternative generation methods](https://latent-implicit-thinking.github.io/topics/alternative-reasoning-schedules/): Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. These are related approaches: some still produce written chains of thought.

Summary and categories are editorial. Read the original paper to verify claims and limitations. A citation to a paper does not, by itself, establish that a later method builds on it.

Reading-list version 0.9.5; literature checked through 2026-10-18.