conftrace_

Wenjin Yang

2 papers · 2024–2026 · 2 conferences · across top CS/AI conferences

Conferences

ACL (1) ICLR (1)

Top co-authors

Lanxiao Huang (1) Xin Li (1) Yang Wei (1) Zheng Pan (1) Lan-Zhe Guo (1) Jing Dai (1) Dehua Zheng (1) Wei Liu (1) Xianliang Wang (1) Feiyu Liu (1)

Keywords

reward modeling (1) reinforcement learning from human feedback (1) agent trajectory (1) tool-integrated environment (1) preference benchmark (1)

Papers

Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling ACL 2026 Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain ICLR 2024