作者位次 #8/10ACL 2026Findings· Findings of ACL
Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning
Fanding Huang · Guanbo Huang · Xiao Fan · Yi He · Xiao Liang · Xiao Chen · Qinting Jiang · Faisal Nadeem Khan · Jingyan Jiang · Zhi Wang
摘要
Reinforcement Learning with Verifiable Rewards (RLVR) for LLM reasoning is often framed as balancing exploration and exploitation in action space, typically operationalized with token-level proxies (e.g., output entropy or confidence). We argue that this apparent trade-off is largely a measuremen...