← Search

Boying Gong

2 accepted papers

2026

On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement

ICML 2026poster

Tool-integrated (TI) reinforcement learning (RL) enables large language models (LLMs) to perform multi-step reasoning by interacting with external tools such as search engines and retrievers. Group Relative Policy Optimization (GRPO), exemplified by the recent Search-R1, offers fast convergence and …

Cited by 0SourceScholar
2026

Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning

ICLR 2026poster

Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open problem. We introduce Token Hidden Reward (THR), a token-level metric that quantifies…

Cited by 0SourceScholar