Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap

ArXi:2605.24432v1 Announce Type: new Large Language Model (LLM) interactions are typically underspecified, with users clarifying all necessary details across multiple conversational turns. Yet recent work shows that LLMs perform far worse in this multi-turn setting than in a single turn with same information being available at once, a phenomenon termed "Lost-in-Conversation." However, bridging this gap effectively remains an open problem. Here we