collaborators

6 papers

cs.LG2026

DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

Haisen Luo, Yiwei Liu, Haoning Wang +13

Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks. Existing self-distilla…

cs.CR2026

JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

Ge Shi, Jun Yin, Donglin Xie +3

Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are express…

cs.IR2026

Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning

Yuqin Dai, Shuo Yang, Guoqing Wang +10

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges.…

cs.CL2026

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Xiaoyu Tian, Haotian Wang, Shuaiting Chen +12

Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing meth…

cs.CL2025

EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes

Yuqin Dai, Guoqing Wang, Yuan Wang +13

Retrieval-Augmented Generation (RAG) has advanced open-domain question answering by incorporating external information into model reasoning. However, effectively leveraging externa…

cs.LG2025

Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learning

Junxi Yin, Haisen Luo, Zhenyu Li +4

While Reinforcement Learning with Verifiable Rewards (RLVR) enhances complex reasoning in LLMs, current methods struggle to balance exploration and exploitation. This leads to crit…