The paper introduces Thinking as Compression (TaC), a novel paradigm showing that the inherent reasoning process of a large language model can naturally compress long context inputs, outperforming ded…

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.

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 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 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…

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…

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.

COFT is a training-free decoding method that significantly reduces societal biases in large language model chain-of-thought reasoning by applying token-level fairness control at decode time.

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…

The paper proposes SLAT, a segment-level adaptive trimming framework, which efficiently reduces redundant reasoning in large language model CoT outputs by selectively suppressing segments with low mar…

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…

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.

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

The paper proposes R-CoT, a reasoning-layer watermarking framework that embeds ownership watermarks directly into the stable reasoning path of LLMs, achieving high robustness against perturbations.

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 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.

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…