1
LLM Reasoning Traces Are Not Audit Records
大模型的思维链并非真实决策的审计日志，揭开推理可解释性的关键盲区。
Article URL: https://rye.ai/blog/cot-faithfulness-reasoning-traces-not-audit-logs/ Comments URL: https://news.ycombinator.com/item?id=49371034 Points:…
2
Rewarding Better Thinking for LLM Preference Alignment
提出通过奖励更优思考过程来对齐LLM偏好，超越仅评估最终结果，提升推理轨迹指导。
arXiv:2607.19824v1 Announce Type: cross Abstract: LLM preference alignment aims to optimize models toward human preferences across diverse user instru…
3
Constraint-Anchored Reasoning Traces
15页论文提出约束锚定推理痕迹方法，为AI推理提供新视角，ACM MM 2026收录。
arXiv:2607.16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorr…
4
Lightweight Latent Reasoning for Narrative Tasks
轻量级潜推理技术利用强化学习优化LLM生成推理轨迹，提升叙事类任务表现
arXiv:2512.02240v2 Announce Type: replace Abstract: Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoni…
5
Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
大模型推理时的“内心独白”可能被窃取，一篇揭示LLM推理轨迹暴露风险的研究
arXiv:2606.00642v1 Announce Type: new Abstract: Reasoning traces have become a valuable form of learning signals for improving and transferring the ca…
6
ReasonOps: Operator Segmentation for LLM Reasoning Traces
新方法将LLM推理轨迹分割为操作符，提升可解释性与效率
arXiv:2605.29192v1 Announce Type: new Abstract: Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack …