8 papers
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
Songjun Tu, Chengdong Xu, Qichao Zhang +6
Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while mi…
Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
Kaiqiang Ke, Shenghong He, Chengdong Xu +3
Offline goal-conditioned reinforcement learning (GCRL) is challenging in long-horizon tasks, where distant state--goal pairs provide weak supervision and value estimates become vul…
Dynamic Dual-Granularity Skill Bank for Agentic RL
Songjun Tu, Chengdong Xu, Qichao Zhang +5
Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for ma…
PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review
Songjun Tu, Yiwen Ma, Jiahao Lin +6
Large language models can generate fluent peer reviews, yet their assessments often lack sufficient critical rigor when substantive issues are subtle and distributed across a paper…
Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
Songjun Tu, Jiahao Lin, Qichao Zhang +4
Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce…
Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization
Songjun Tu, Qichao Zhang, Jingbo Sun +6
While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: p…