AI RESEARCH
From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator
arXiv CS.AI
•
ArXi:2605.26403v1 Announce Type: new A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline logs (Static Context RL) or using a prompt-based simulator (Interactive RL). In this work, we theoretically show that both paradigms are fundamentally limited by context distribution shift--a mismatch between dialogue histories observed during