✳flâneur — a map of the web's best reading
Reasoning as Trajectories
slhleosun.github.io · 1,061 words · saved by 1 readers
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
Reasoning as Trajectories LLM Reasoning as Trajectories : Step-Specific Representation Geometry and Correctness Signals Lihao Sun , Hang Dong , Bo Qiao , Qingwei Lin , Dongmei Zhang , Saravan Rajmohan Microsoft ACL 2026 (Main) Paper arXiv Code Chain-of-thought reasoning in LLMs traces structured trajectories through representation space. Step-specific regions become linearly separable with depth, late-step geometry predicts correctness, and trajectory-based steering enables both error correction and reasoning length control at inference time. Step-specific representation structure across layer
Explore this link on the map →saved by
related reading
- Explore | alphaXivalphaxiv.org
- the-illusion-of-thinking.pdfml-site.cdn-apple.com
- DeepSeek-R1arxiv.org
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
- [2510.24941] Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thoughtarxiv.org
- Explore | alphaXivalphaxiv.org
- Announcing ReasoningLens — Visualizing and Diagnosing LLM Reasoning at a Glancehuggingface.co
- Thought Anchors: Which LLM Reasoning Steps Matter? — LessWronglesswrong.com
- Reasoning Models Reason Well, Until They Don'tarxiv.org
- [2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com