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…

This paper proposes a training-free framework called ReasonAlloc to mitigate inference bottlenecks in large language models by recasting decoding-time key-value compression as a hierarchical budget al…

This paper proposes a training-free framework called ReasonAlloc to mitigate inference bottlenecks in large language models by recasting decoding-time key-value compression as a hierarchical budget al…

LongAttnComp introduces a novel, two-stage fine-tuning framework for context compression that significantly improves long-context reasoning performance, matching or exceeding full-context accuracy on…

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…

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.

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 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…

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compress…

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

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

HMPO introduces a single-stage, cost-effective reinforcement learning framework that achieves significant token compression of Chain-of-Thought reasoning with minimal loss of accuracy, applicable acro…

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

This paper investigates whether model compression techniques (like quantization and pruning) preserve a Large Language Model's ability to quantify its own uncertainty, finding that accuracy-only evalu…

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 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 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 a black-box attack using a hierarchical genetic algorithm to induce 'overthinking' in Large Reasoning Models, demonstrating that this vulnerability can cause significant resource ex…

The paper introduces an Integrated, cross-Architecture Reasoning (IAR) framework to provide a unified and robust method for interpreting the opaque reasoning processes within Large Language Models.

The paper demonstrates that extended pure neural reasoning fails on complex, deterministic state-tracking tasks beyond a certain 'Deterministic Horizon,' necessitating the integration of external tool…