AI RESEARCH
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
arXiv CS.CL
•
ArXi:2510.08525v3 Announce Type: replace 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 compression. Existing token-dropping methods directly disrupt reasoning chains by removing intermediate steps, while head-reallocation methods, designed for retrieval tasks, fail to preserve the heads essential for generative reasoning.