LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become increasingly separable with layer depth. This structure already exists in base models, while reasoning training primarily accelerates convergence toward termination-related subspaces rather than introducing new representational organization. While early reasoning steps follow similar trajectories, correct and incorrect solutions diverge systematically at late stages. This late-stage divergence enables mid-reasoning prediction of final-answer correctness wit...
| Authors | Lihao Sun, Hang Dong, Bo Qiao et al. |
|---|---|
| Primary category | cs.CL |
| Published | 7 April 2026 |
| Last updated at source | 7 April 2026 |
Connected in the knowledge graph
- TAGOOZ/reasoning-trajectory-qwen2.5Dataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.