Abdur Rakib, Tazeek Bin, et al. “DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning With LLM Priors”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 36, Mar. 2026, pp. 29967-75, doi:10.1609/aaai.v40i36.40244.