Huang, Heyan, Yizhe Yang, Huashan Sun, Jiawei Li, and Yang Gao. 2026. “Simulated Rewards, Skewed Strategies: Tracing the Acquired Preference Bias in LLM-Based Dialogue Planners”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (26):21948-56. https://doi.org/10.1609/aaai.v40i26.39348.