Dissertation Talk: Multi-Turn Reinforcement Learning for Real-World Dialogue Agents

Event details Date: Friday, July 31, 2026 Time: 10:00 AM to 10:00 AM Location: Gateway 4355 Type: Lecture / Workshop Audience: Faculty,Students About this event Large Language Models (LLMs) are increasingly deployed as agents in real world interactive settings such as teaching, negotiation, and mental health. However, standard LLMs are optimized for single-turn instruction following, and rarely pursue goal-directed behavior across extended interactions. In this talk, I introduce the tools needed to build such agents. Firstly, I present multi-turn RL as a framework for training LLMs to plan, gather information, and optimize goals in dialogue. Next, I will argue that consistent human simulations are essential as off-the-shelf LLMs often drift from their assigned personas, contradict earlier statements, or abandon role-appropriate behavior. Finally, I show how these tools come together in strategic dialogue tasks such as negotiation, where multi-turn RL enables safe outcomes and the ability for agents to reason hierarchically, generalize across unseen tasks, and adapt to diverse opponents towards cooperative, value-creating outcomes. Official event details: https://events.berkeley.edu/eecs/event/324899-dissertation-talk-multi-turn-reinforcement-learning-f