ARGUS: An Agenda-Driven Framework for Reliable User Simulation

arXiv:2610.21346v1 Announce Type: new Abstract: High-fidelity user simulators are essential for evaluating and training agents in interactive environments. However, current LLM-based simulators struggle with reliability issues, such as goal omission and policy non-compliance. We propose ARGUS (Agenda-dRiven Goal-oriented User Simulator), a neuro-symbolic framework that maintains the user's goal state using a dynamic agenda stack manipulated via symbolic operations. By rigorously decoupling state tracking from natural language generation, ARGUS facilitates strict goal progression and constraint-aligned interactions. For cost-efficient deployment, we distill ARGUS into compact models using a unified pipeline: evaluator-guided SFT followed by online RL with dense step-level rewards. To rigorously evaluate behavioral fidelity, we introduce a rubric-based metric Composite Behavioral Score (CBS). Evaluations on au^3-Bench and MultiWOZ demonstrate the significant superiority of the ARGUS architecture and the efficacy of our training pipeline. Code and data will be released soon.

Related

• MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
• Beyond Surface Style: Aligning Multi-Turn User Simulators with Behavioral Consistency
• UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training
• Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints

Source: arXiv cs.AI | 2026-10-16