Kavli Affiliate: Wei Gao
| Summary:
Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user’s concerns and steers the conversation toward acceptance within a bounded number of turns. Yet post-trained LLMs are inherently conservative, and reward-shaping RL (e.g., GRPO) struggles since it only re-weights what an already passive policy samples. We show that conditioning on the user’s latent concerns unlocks proactive capability that no amount of sampling can undermine, establishing these concerns as a pivotal training-time signal. To operationalize this finding, we build the textbfCognitive User Simulator, which models each user as a stratified persona comprising observable external traits and hidden internal concerns. The simulator produces faithful and diverse interactions, while emitting per-turn state dynamics that track persuasion progress. We then introduce textbfSimulator-Induced Asymmetric-View Policy Optimization, which converts the modeled concerns and the simulation state transition into complementary training objectives: (1) emphAsymmetric On-Policy Self-Distillation that transfers concern-aware behavior from a privileged view of the same policy into its deployable, conversation-only view; and (2) emphState-Transition Policy Refinement …
| Search Query:arXiv Query: search_query=au:”Gao Wei”&id_list=&start=0&max_results=10
Read More