22 citations · 25 across the 10 of their papers we have counts for
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…
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…
See, Think, Act: Online Shopper Behavior Simulation with VLM Agents
Yimeng Zhang, Jiri Gesi, Ran Xue +10
LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generate…
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…
LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?
Lu Sun, Shihan Fu, Bingsheng Yao +7
Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as th…
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…
Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
Jiaju Chen, Yuxuan Lu, Xiaojie Wang +6
Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real h…
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…
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…
UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agents
Yuxuan Lu, Bingsheng Yao, Hansu Gu +7
Usability testing is a fundamental research method that user experience (UX) researchers use to evaluate and iterate their new designs. But what about evaluating and iterating the…
UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design
Yuxuan Lu, Bingsheng Yao, Hansu Gu +7
Usability testing is a fundamental yet challenging (e.g., inflexible to iterate the study design flaws and hard to recruit study participants) research method for user experience (…