Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning
Gengyang Li, Zheng-Fan Wu, Siqi Bao +1
Reinforcement-learning-based post-training has become a key approach for improving the reasoning ability of large language models, but its token-level learning signals remain poorl…
cs.CL2025
InfoFlow: Reinforcing Search Agent Via Reward Density Optimization
Kun Luo, Hongjin Qian, Zheng Liu +5
Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward De…