4 papers
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…
Learning Latent Reasoning Traces for Scalar Reward Models End-to-End
Sanwoo Lee, Clive Bai, Hsiu-Yuan Huang +3
Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs enable efficient and probabilis…
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Xin Xu, Clive Bai, Kai Yang +7
Large-scale verifiable prompts underpin the success of Reinforcement Learning with Verifiable Rewards (RLVR), but they contain many uninformative examples and are costly to expand…
ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
Kun Liang, Clive Bai, Xin Xu +5
Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thought (CoT) reasoning, but uniformly applying overlong reasoning at inference tim…