Non-Collaborative User Simulators for Tool Agents
Tool agents interact with users through multi-turn dialogues to accomplish various tasks. Recent studies have adopted user simulation methods to develop these agents in multi-turn settings. However, existing user simulators tend to be agent-friendly, exhibiting only cooperative behaviors, failing to train and test agents against non-collaborative users in the real world. We propose a novel user simulator architecture that simulates four categories of non-collaborative behaviors: requesting unavailable services, digressing into tangential conversations, expressing impatience, and providing incomplete utterances. Our user simulator can simulate challenging and natural non-collaborative behaviors while reliably delivering all intents and information necessary to accomplish the task. Our experiments on MultiWOZ and τ-bench reveal significant performance degradation in state-of-the-art tool agents when encountering non-collaborative users, as well as agent weaknesses under each non-collaborative condition such as escalated hallucinations and dialogue breakdowns. Our findings point to the need for methods that can improve agent robustness to the wide range of user behaviors encountered in deployment. We release the extensible simulation framework to help the community develop and stress-test tool agents under realistic conditions within their own service domains. Our code is available at https://github.com/holi-lab/NCUser.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Understanding Perspectives of Patients, Caregivers and Clinicians towards Emerging Collaborative-decision Making Technologies
In pediatrics, patients, caregivers, and clinicians share responsibility for health decisions, but limited collaboration can undermine outcomes. We conducted a qualitative study examining decision-makers perceptions towa…
Decision MakingExploring Personality-Aware Interactions in Salesperson Dialogue Agents
The integration of dialogue agents into the sales domain requires a deep understanding of how these systems interact with users possessing diverse personas. This study explores the influence of user personas, defined usi…
The Indispensable Role of User Simulation in the Pursuit of AGI
Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive systems and acquiring the vast interaction data needed for training adaptive …
Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations
Agentic recommendations cast recommenders as large language model (LLM) agents that can plan, reason, use tools, and interact with users of varying preferences in web applications. However, most existing agentic recommen…
Collaborative FilteringLeveraging User Simulation to Develop and Evaluate Conversational Information Access Agents
We observe a change in the way users access information, that is, the rise of conversational information access (CIA) agents. However, the automatic evaluation of these agents remains an open challenge. Moreover, the tra…
Conversational Information AccessReinforcement LearningUser Simulation