activity
20242026
collaborators

6 papers

cs.AI2026

PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

Yipeng Shi, Zhipeng Ma, Yue Wang +4

In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimizati…

cs.AI2026

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

Leo Luo, Haining Xie, Siqi Shen +8

Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors. Yet voting alone is not enough,…

cs.CL2026

Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement

Dingwei Chen, Zefang Zong, Zhipeng Ma +5

Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that agentic RL training induces in…

cs.CL2026

ATGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping

Dingwei Chen, Zefang Zong, Zhipeng Ma +5

Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of i…

cs.CL2025

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation

Runchuan Zhu, Zinco Jiang, Jiang Wu +6

Refusal-Aware Instruction Tuning (RAIT) aims to enhance Large Language Models (LLMs) by improving their ability to refuse responses to questions beyond their knowledge, thereby red…

cs.CL2024

Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning

Runchuan Zhu, Zhipeng Ma, Jiang Wu +4

Refusal-Aware Instruction Tuning (RAIT) enables Large Language Models (LLMs) to refuse to answer unknown questions. By modifying responses of unknown questions in the training data…