Metraipolis › archive › dc_f57fde194ccc

ARGUS: An Agenda-Driven Framework for Reliable User Simulation — arXiv:2610.21346

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21346
License (as archived)
CC0-1.0
Archived
2026-10-16T09:03:04.817Z
SHA-256 of the archived text
8dea625be10e37570effefbaee8c438e48efaca05e0c7bee3e457430df086fc9
Stable URL of this page
https://metraipolis.com/documento/dc_f57fde194ccc

How to cite

ARGUS: An Agenda-Driven Framework for Reliable User Simulation — arXiv:2610.21346 — arXiv (en), https://arxiv.org/abs/2610.21346 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f57fde194ccc (Metraipolis archive dc_f57fde194ccc, sha256 8dea625be10e37570effefbaee8c438e48efaca05e0c7bee3e457430df086fc9)
BibTeX
@misc{dcf57fde194ccc,
  title = {ARGUS: An Agenda-Driven Framework for Reliable User Simulation — arXiv:2610.21346},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21346},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f57fde194ccc; sha256 8dea625be10e37570effefbaee8c438e48efaca05e0c7bee3e457430df086fc9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21346. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 $\tau^3$-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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.21346 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T08:44:17.731Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).