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 analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

This paper introduces RREDCoT, a method for approximating optimal reward redistribution in Chain-of-Thought reasoning language models without additional generation.

This paper introduces RREDCoT, a method for approximating optimal reward redistribution in Chain-of-Thought reasoning language models without additional generation.

The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.

DenoiseRL is a novel reinforcement learning framework that improves reasoning in large language models by optimizing directly from the failures and incorrect reasoning traces of weak models, eliminati…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

The paper analyzes the entropy dynamics of Chain-of-Thought (CoT) reasoning, identifying a transition from an exploratory Uncertainty Region to a stable Confidence Region, which enables superior early…

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 proposes using an LLM aggregator that analyzes complete reasoning traces, demonstrating that trace-level synthesis is superior to traditional consensus methods like majority voting for solvi…

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…

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 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,…

This paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and benef…

DenseSteer is a training-free inference-time framework that improves the math reasoning capabilities of small language models by steering their internal representations toward a 'Dense Reasoning' patt…

The paper theoretically explains that optimizing LLMs solely on outcomes leads to brittle reasoning (Reward-Induced Manifold Collapse) by favoring low-complexity shortcuts, and proposes process-based…

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

The paper introduces COVCAL, a risk-controlled method that precisely determines when a partial formalization signal from an autoformalizer can be trusted to certify the correctness of natural-language…

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.