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

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…

AdaptR1 is a novel Reinforcement Learning framework that adaptively manages reasoning effort at every step of multi-hop Question Answering, significantly reducing unnecessary computational cost withou…

The paper introduces Hierarchical Adaptive Budgeter (HAB), a framework that improves LLM reasoning efficiency by adaptively allocating computational resources to match the intrinsic complexity of both…

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 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 Continuous Reasoning for Vision-Language-Action (VLA) models, arguing that effective reasoning must be a shared, verifiable internal latent space rather than discrete text tokens, l…

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

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 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…

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

The study demonstrates that domain adaptation primarily reshapes the linguistic explanatory framework of language models, causing shifts in cosmological stance secondarily, rather than directly modify…

The paper proposes an unsupervised Reinforcement Learning approach that enforces cross-lingual self-consistency to significantly enhance the multilingual reasoning capabilities of large language model…

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

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 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 introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memo…

The paper introduces LinTree, a method that explicitly structures the search history of LLM reasoning traces using parent pointers, significantly improving task performance and search efficiency compa…