Metraipolis › archive › dc_0874a90cb184
Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue — arXiv:2610.21156
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21156
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:55:35.360Z
- SHA-256 of the archived text
372420e90a996f40f88212c858092b21094f1edb03499275d5be005c7744b09f- Stable URL of this page
https://metraipolis.com/documento/dc_0874a90cb184
How to cite
Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue — arXiv:2610.21156 — arXiv (en), https://arxiv.org/abs/2610.21156 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0874a90cb184 (Metraipolis archive dc_0874a90cb184, sha256 372420e90a996f40f88212c858092b21094f1edb03499275d5be005c7744b09f)
BibTeX
@misc{dc0874a90cb184,
title = {Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue — arXiv:2610.21156},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21156},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0874a90cb184; sha256 372420e90a996f40f88212c858092b21094f1edb03499275d5be005c7744b09f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21156. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing planners improve system side action selection through search, learned policies, or user aware planning, but are often trained and evaluated against fixed or overly compliant simulators; as a result, high simulated success can reflect soft user bias rather than robust dialogue ability. We introduce MASP, a Mentalized Adversarial Self Play framework that treats proactive dialogue as a partially observable game between a system and a rationally resisting user. MASP represents the user's evolving mental state with a BDI based latent state, separates reward side teacher mentalization from policy side student mentalization, and alternates self play updates for the system and user policies. This turns robustness to rational resistance into a training objective rather than only an evaluation condition. Across diverse proactive dialogue benchmarks, compared with the widely used SFT and Planner-only approaches, MASP substantially improves success rate (SR) and rationality constrained success (RCSR), reduces average turns (AT), and performs better against hard users who make the task goal more difficult to achieve. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.21156 — 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 2026-10-16T08:44:47.625Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).