Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
Boyang Liu, Senjie Jin, Peixin Wang +15
Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongoing trajectory before those…
cs.AI2026
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
Senjie Jin, Peixin Wang, Boyang Liu +8
While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether t…
cs.AI2026
CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space
Bingyi Liu, Jinbo He, Haiyong Shi +5
Hybrid action space, which combines discrete choices and continuous parameters, is prevalent in domains such as robot control and game AI. However, efficiently modeling and optimiz…