Metraipolis › archive › dc_7e786641bf91

Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues — arXiv:2610.32435

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.32435
License (as archived): CC0-1.0
Archived: 2026-10-26T19:53:37.859Z
SHA-256 of the archived text: 4c1d3bac645bd456573454bcbdb912327671e1fa913b6dedc5524b46eeb58058
Stable URL of this page: https://metraipolis.com/documento/dc_7e786641bf91

How to cite

Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues — arXiv:2610.32435 — arXiv (en), https://arxiv.org/abs/2610.32435 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e786641bf91 (Metraipolis archive dc_7e786641bf91, sha256 4c1d3bac645bd456573454bcbdb912327671e1fa913b6dedc5524b46eeb58058)

BibTeX

@misc{dc7e786641bf91,
  title = {Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues — arXiv:2610.32435},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32435},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e786641bf91; sha256 4c1d3bac645bd456573454bcbdb912327671e1fa913b6dedc5524b46eeb58058},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32435. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Building Task-Oriented Dialogue (TOD) systems for high-value scenarios such as financial marketing requires large volumes of domain-specific dialogue data, which privacy regulations, annotation costs, and the need for expert labor make hard to obtain. User simulation offers a remedy, but existing methods target general-domain dialogue and exhibit two key limitations: insufficient modeling of domain-specific business processes and compliance constraints, and inadequate capture of the colloquial, spoken-language character of voice interactions. We propose ProfileSim, a profile-driven user simulation framework for financial marketing outbound calls. It jointly models user profiles---demographics and Big Five personality traits---and business profiles---intents reverse-engineered from real call logs---enabling fine-grained control over simulated behavior. The base model is fine-tuned on real voice dialogue data and refined by Group Relative Policy Optimization (GRPO) with hierarchical rewards at the dialogue and utterance levels. Paired with a customer service agent integrating Standard Operating Procedure (SOP) constraints and Retrieval-Augmented Generation (RAG), ProfileSim achieves the highest colloquial naturalness, the strongest user profile adherence and the lowest agent score on long-tail intents among all evaluated user generators, while producing substantially shorter user utterances at comparable business compliance. The generated dialogue data is designed to support intent recognition training, agent evaluation, and rapid cold-start deployment.

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/2610.32435 — 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 2026-10-26T19:45:48.362Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).