LATIDIA · Investigación

ARGUS: un marco basado en la agenda para una simulación confiable del usuario

arXiv: 2610.21346v1Tipo de anuncio: nuevo Resumen: Los simuladores de usuario de alta fidelidad son esenciales para evaluar y capacitar a los agentes en entornos interactivos. Sin embargo, los simuladores actuales basados en LLM tienen dificultades con la fiabilidad

La noticia

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