# Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding

Authors: Minoo Ahmadi, Seyedarmin Azizi, Mehdi Kamal, Massoud Pedram.

Changes resampling in diffusion-model search to preserve more distinct candidate histories, combining unequal-weight resampling with a floor on low weights. Tests the effect on candidate coverage and final-answer accuracy under several answer-selection rules.

First public: 2026-10-19.
ArXiv initial submission: 2026-10-19.

[Original paper](https://arxiv.org/abs/2610.25932) · [PDF](https://arxiv.org/pdf/2610.25932) · [HTML](https://arxiv.org/html/2610.25932v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.25932/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.25932/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.25932/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.25932/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. Some produce written chains of thought.

Reading-list version 0.11.0; literature checked through 2026-10-26.