Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
Recent reasoning-focused language models achieve high accuracy by generating lengthy intermediate reasoning paths before producing final answers. While this approach is effective in solving problems that require logical thinking, long reasoning paths significantly increase memory usage and throughput of token generation, limiting the practical deployment of such models. We propose Reasoning Path Compression (RPC), a training-free method that accelerates inference by leveraging the semantic sparsity of reasoning paths. RPC periodically compresses the KV cache by retaining KV cache that receive high importance score, which are computed using a selector window composed of recently generated queries. Experiments show that RPC improves generation throughput of QwQ-32B by up to 1.60$\times$ compared to the inference with full KV cache, with an accuracy drop of 1.2% on the AIME 2024 benchmark. Our findings demonstrate that semantic sparsity in reasoning traces can be effectively exploited for compression, offering a practical path toward efficient deployment of reasoning LLMs. Our code is available at https://github.com/jiwonsong-dev/ReasoningPathCompression.
Code (1)
Similar Papers 제목 키워드 기반
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance. Existing works focus on compressing generated CoT …
Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models
Long chains of thought (Long CoTs) are widely employed in multimodal reasoning models to tackle complex tasks by capturing detailed visual information. However, these Long CoTs are often excessively lengthy and contain r…
Reinforcement LearningMultimodal ReasoningDiscrete Flow Maps
The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models offer a path to parallel generation, they traditionally demand expens…
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information loss during decoding, creating critical challenges for KV cache compress…
Reinforcement LearningReinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization
Chain-of-thought reasoning in large language models can trigger an "overthinking trap": longer rollouts raise cost and latency yet often yield unreliable accuracy gains. Existing methods use global, static controls that …
Reinforcement LearningInstruction Following