The paper introduces Reasoning Exposure Prompting (REP), a method that demonstrates that even when LLMs hide internal reasoning traces from users, useful reasoning supervision can still be elicited th…

The paper introduces TRACE, a novel metric that evaluates the logical structure of LLM reasoning (CoT) by integrating Toulmin's argumentation theory, demonstrating that sound reasoning structure corre…

The paper introduces TraceGuard, a detectability-aware antidistillation method that identifies and poisons 'thought anchors'—sparsely critical sentences—to degrade student model learning without makin…

ReasonOps introduces an unsupervised method to segment and analyze the common, compositional structure of LLM reasoning traces, discovering universal reasoning operators that predict model identity an…

The paper introduces Contrastive Reflection (CORE), a novel non-parametric method that rapidly improves language model reasoning by distilling contrasts between successful and unsuccessful problem att…

This paper proposes a method to recover recoverability structure from failed traces of post-trained language models, enabling test-time routing and post-training analysis.

The paper proposes a novel bi-level exact unlearning attack targeting Large Reasoning Models (LRMs) that forces incorrect final answers while generating misleading reasoning traces, highlighting new s…

This paper investigates the production-evaluation gap in Large Reasoning Models (LRMs), finding that while LRMs excel at generating solutions, they struggle significantly to evaluate flawed reasoning,…

ThinkSwitch introduces a low-compute co-training procedure that distills the reasoning benefit of large language models into weights, significantly improving performance on specific reasoning tasks.

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

The paper proposes a structured prompt engineering framework to enhance the integrity and reliability of Chain-of-Thought (CoT) reasoning in LLMs, demonstrating significant improvements in security-se…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

The paper addresses the 'detection-to-abstention gap' in reasoning models, where detecting insufficient information does not lead to abstention, by proposing a novel control framework that forces mode…

This paper localizes the attention heads within LLMs responsible for specific reasoning steps, finding that specialized heads handle factual retrieval while higher layers manage global information int…

The paper identifies a failure mode called unfaithful capitulation (UC), where reasoning models maintain a correct internal thought process (chain-of-thought) but output an incorrect final answer when…

The paper proposes interaction-layer antidistillation watermarks by embedding behavioral markers into the system prompt, which successfully track knowledge distillation even when paraphrasing attacker…

The paper identifies and demonstrates that post-conclusion continuation in answer-correct long-CoT traces is harmful during LLM fine-tuning, proposing a method to cut this continuation.

AEGIS is a novel multi-agent framework that grounds vulnerability reasoning by reconstructing per-variable dependency chains over a Code Property Graph, achieving state-of-the-art performance on the P…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

The paper introduces Entropy-Cut Metropolis-Hastings, an efficient sampling method that uses next-token entropy to identify and resample from critical decision points in a reasoning trace, significant…