12 papers
Steer, Don't Solve: Training Small Critic Models for Large Code Agents
Shubham Gandhi, Yiqing Xie, Atharva Naik +2
End-to-end code agent training is resource-intensive and plateaus on the strategy-level reasoning needed to resolve code issues, since jointly optimizing code-level execution and s…
Reinforcing Human Behavior Simulation via Verbal Feedback
Weiwei Sun, Xuhui Zhou, Jiarui Liu +13
Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for…
Mind the Sim2Real Gap in User Simulation for Agentic Tasks
Xuhui Zhou, Weiwei Sun, Qianou Ma +8
As NLP evaluation shifts from static benchmarks to multi-turn interactive settings, LLM-based simulators have become widely used as user proxies, serving two roles: generating user…
Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
Yiqing Xie, Emmy Liu, Gaokai Zhang +7
When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use, these agents solve more v…
REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Yisu Wang, Ming Wang, Haoyuan Song +4
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently ar…
PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models
Chengbing Wang, Wuqiang Zheng, Yang Zhang +5
Large Language Models (LLMs) are increasingly deployed in human-centric applications, yet they often fail to provide substantive emotional support. While Reinforcement Learning (RL…