一作ACL 2026Findings· Findings of ACL
Verifier-Free RL for LLM s via Intrinsic Gradient-Norm Reward
Xuexiang Wen · Hang Yu · Linchao Zhu · Gaoang Wang
摘要
While Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising post-training paradigm for Large Language Models (LLMs), its dependency on the gold label or domain-specific verifiers limits its scalability to new tasks and domains. In this work, we propose Verifier...