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

The eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.

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…

The paper introduces TRON, an online, rule-verifiable environment substrate that generates an unbounded stream of fresh, controllable visual reasoning training instances, significantly improving RL pe…

The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving sign…

The paper introduces Reasoning in Memory (RiM), a latent reasoning method that replaces autoregressive token generation with fixed memory blocks to enable compute-efficient internal working memory for…

This paper investigates how different types of compressed reasoning data (Explicit, Composed, Implicit CoT) affect LLM performance during post-training, finding that the choice of compression and subs…

The paper introduces REFT, a novel method that diversifies rollouts by sampling the first token after the reasoning marker, significantly improving performance in Reinforcement Learning with Verifiabl…

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 introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

The paper introduces Contextual Belief Management (CBM) to address how LLMs should manage accumulating information over long interactions, showing that reinforcement learning significantly improves be…

MindZero introduces a self-supervised reinforcement learning framework that trains multimodal large language models (MLLMs) for efficient and robust online mental reasoning without requiring explicit…

The paper proposes CSMR, a cognitive scheduling framework that allows a language model to dynamically decide when to acquire task-relevant visual evidence, significantly improving multimodal reasoning…

This paper unifies the fragmented field of Tree-of-Thoughts (ToT) reasoning by mapping LLM-based search processes onto a formal taxonomy derived from classical heuristic search theory.

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

The paper proposes RIEQE, a two-stage training framework that synergistically co-evolves implicit and explicit reasoning capabilities in Large Reasoning Models (LRMs) to significantly improve fine-gra…

The paper proposes Faithful Agentic XAI (FAX), a verification framework that explicitly checks LLM-generated explanations against model behavior, significantly improving explanation faithfulness on a…

The paper introduces Group Prioritized Off-Policy Optimization (POPO), a novel framework that efficiently accelerates RL finetuning for LLM reasoning by leveraging effective off-policy training batche…

This paper proposes NF-CoT, a latent reasoning framework that preserves the advantages of chain-of-thought in large language models.