# Reasoning or Just Prompting? Probing the Mechanism of Latent Chemical Reasoning

Authors: Kaiyuan Lu, Jiatong Li, Yatao Bian.

Replaces, removes and perturbs latent sequences in a chemical reasoning model. Swapping sequences between molecules often preserves task scores, and a fixed prefix can match input-dependent latent sequences.

First public: 2026-10-25.
ArXiv initial submission: 2026-10-25.

[Original paper](https://arxiv.org/abs/2610.34173) · [PDF](https://arxiv.org/pdf/2610.34173) · [HTML](https://arxiv.org/html/2610.34173v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.34173/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.34173/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.34173/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.34173/record.json)

## Approaches

- [Continuous-state reasoning](https://latent-implicit-thinking.github.io/topics/continuous-states/): Use vectors—lists of numbers—to carry intermediate reasoning from one step to the next, instead of selecting a text token at every step. Some methods use the model's hidden states; others combine several candidate token representations.
- [Analysis and evaluation](https://latent-implicit-thinking.github.io/topics/implicit-reasoning-evaluation/): Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.

Reading-list version 0.12.0; literature checked through 2026-11-02.