activity
20242026
collaborators

7 papers

cs.AI2026

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…

cs.CL2026

Are Full Rollouts Necessary for On-Policy Distillation?

Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7

On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm…

cs.LG2026

-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data

Yaocheng Zhang, Yuanheng Zhu, Wenyue Chong +7

Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit…

cs.AI2026

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…

cs.AI2026

AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning

Jingbo Sun, Wenyue Chong, Songjun Tu +7

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. Howeve…

cs.CL2025

CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic

Yaocheng Zhang, Haohuan Huang, Zijun Song +4

Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization i…