Metraipolis › archive › dc_2d59bcf72f00

Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation — arXiv:2608.09420

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09420
License (as archived)
CC0-1.0
Archived
2026-10-19T08:50:22.066Z
SHA-256 of the archived text
c826b1a93cb165625d7632cfb59c969d2c8a12e7fc16584f84c85f11c68218e7
Stable URL of this page
https://metraipolis.com/documento/dc_2d59bcf72f00

How to cite

Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation — arXiv:2608.09420 — arXiv (en), https://arxiv.org/abs/2608.09420 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d59bcf72f00 (Metraipolis archive dc_2d59bcf72f00, sha256 c826b1a93cb165625d7632cfb59c969d2c8a12e7fc16584f84c85f11c68218e7)
BibTeX
@misc{dc2d59bcf72f00,
  title = {Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation — arXiv:2608.09420},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09420},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d59bcf72f00; sha256 c826b1a93cb165625d7632cfb59c969d2c8a12e7fc16584f84c85f11c68218e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09420. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

User simulators are widely used as scalable environments for training and evaluating interactive assistants. Generating the next user turn is inherently one-to-many: the same profile and dialogue context may support multiple plausible continuations with different local interaction intents. A fluent response may therefore advance the dialogue through an inappropriate intent, such as acceptance rather than repair. Our key insight is that controllable user simulation should separate which local interaction intent the next user turn should realize from how that intent is expressed in language. We introduce UserIDA (User Intent-Directive Alignment), which exposes interaction intent as an explicit per-turn directive. UserIDA defines a six-way intent interface, learns directive-conditioned generation through supervised fine-tuning, and uses intent-calibrated policy optimization during group-based reinforcement learning. The reward preserves composite response quality while ensuring that intent-violating candidates rank below compliant alternatives in mixed groups. On LMSYS-USP, UserIDA achieves 86.6\% intent accuracy, outperforming the strongest dedicated user-simulator baseline by 24.3 percentage points while improving semantic and stylistic similarity. In within-context interventions, it realizes at least four of the six target intents in 91.7\% of evaluated dialogue states, compared with 22.9\% for the strongest external baseline. These results establish per-turn intent control as a complementary dimension to response fidelity in user simulation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.09420 — 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 2026-10-19T08:49:41.927Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).