Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models

ArXi:2605.30251v1 Announce Type: cross Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the same complete user evidence, the model should still arrive at the same answer. We argue that a key reason for this gap is self-anchored drift: responses produced under partial information