When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents
Intent drift is established as a measurable multi-turn failure mode and explicit state maintenance as a partial mitigation and IntentFlux is introduced, an executable benchmark that converts verifiable tasks into dialogues with controlled intent changes while preserving their original graders.
Yan-Jie Zhang, Bo-Wen Cao, Zi-Xin Chen et al.
· 0 citations