11 papers
SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents
Ziyi Wang, Yuxuan Lu, Yimeng Zhang +8
Language model agents are increasingly effective in solving realistic tasks through multi-turn tool use. However, training reliable tool-using agents remains challenging in practic…
WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale
Yuxuan Lu, Ziyi Wang, Jing Huang +10
Reinforcement learning (RL) for web agents demands environments that are both effective for evaluation and efficient enough for large-scale on-policy training. Current web environm…
OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation
Ziyi Wang, Yuxuan Lu, Wenbo Li +13
Can large language models (LLMs) accurately simulate the next web action of a specific user? While LLMs have shown promising capabilities in generating ``believable'' human behavio…
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents
Ziyi Wang, Yuxuan Lu, Yimeng Zhang +12
Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and…
Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
Yimeng Zhang, Tian Wang, Jiri Gesi +14
Large Language Models (LLMs) have recently demonstrated strong potential in generating 'believable human-like' behavior in web environments. Prior work has explored augmenting trai…
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
Jiacheng Lin, Zhongruo Wang, Kun Qian +14
Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their gene…