DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (36) · 29967-29975
DOI: 10.1609/aaai.v40i36.40244 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Tazeek Bin Abdur Rakib und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Large-language-model (LLM) agents excel at reactive dialogue but struggle with proactive, goal-driven interactions due to myopic decoding and costly planning. We introduce DialogXpert, which leverages a frozen LLM to propose a small, high-quality set of candidate actions per turn and employs a compact Q-network over fixed BERT embeddings trained via temporal-difference learning to select optimal moves within this reduced space. By tracking the user's emotions DialogXpert tailors each decision to advance the task while nurturing a genuine, empathetic connection. Across negotiation, emotional support, and tutoring benchmarks, DialogXpert drives conversations to under 3 turns with success rates exceeding 94% and, with a larger LLM prior, pushes success above 97% while markedly improving negotiation outcomes. This framework delivers real-time, strategic, and emotionally intelligent dialogue planning at scale.
Zitieren
APA
Rakib, T. B. A., Mehrish, A., Soon, L., Lim, W. H., & Poria, S. (2026). DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 29967-29975. https://doi.org/10.1609/aaai.v40i36.40244
Vancouver
Rakib TBA, Mehrish A, Soon L, Lim WH, Poria S. DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(36):29967-29975. doi:10.1609/aaai.v40i36.40244
BibTeX
@article{Rakib2026,
author = {Rakib, Tazeek Bin Abdur and Mehrish, Ambuj and Soon, Lay-Ki and Lim, Wern Han and Poria, Soujanya},
title = {DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {36},
pages = {29967--29975},
doi = {10.1609/aaai.v40i36.40244}
}
EUVIMED