DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs

ArXi:2601.07994v4 Announce Type: replace Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints. We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction.