1
LLMs Get Lost in Evolving User Intent
研究发现大型语言模型在用户意图动态演变时容易“迷失”，揭示了多轮对话中推理与记忆的脆弱性。
arXiv:2607.20734v1 Announce Type: new Abstract: As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-de…
研究发现大型语言模型在用户意图动态演变时容易“迷失”，揭示了多轮对话中推理与记忆的脆弱性。
arXiv:2607.20734v1 Announce Type: new Abstract: As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-de…