LLMs Get Lost in Evolving User Intent

  • 类型:arxiv
  • 标识:2607.20734
  • 链接:https://arxiv.org/abs/2607.20734
  • 主分类:agent
  • 形态:application
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This work introduces a framework that transforms static, single-turn tasks into dynamic multi-turn conversations in which the user's intent evolves across turns, while preserving each task's original evaluation protocol, enabling existing benchmarks to be reused as controlled testbeds without new annotation.
  • OpenAlex ID:W7170427881
  • OpenAlex DOI:10.48550/arxiv.2607.20734
  • DOI:10.48550/arxiv.2607.20734
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.20734
  • OpenAlex更新:2026-08-24
  • 待LLM分类:否
  • 标题中文:LLM 在演化用户意图中迷失
  • TLDR中文:本文提出一个框架,将静态的单轮任务转化为动态多轮对话,其中用户意图在多轮间持续演化,同时保留每个任务原有的评估协议,使现有基准能够在无需新增标注的情况下作为受控测试平台被复用。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-24-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]