冻结智能体的受限角色在分类任务中与检索匹配，但在回归任务中不匹配

中文摘要 AI 辅助

个性化语言智能体必须在推理时将用户的交互历史转换为对每个新请求的行为，目前有两种主流策略：检索策略会将用户最相关的少量过往条目拉入提示，该策略准确但需承担随历史增长的每查询选择和上下文成本；蒸馏策略则会将历史一次性压缩为紧凑的自然语言角色，该角色是受限的、与查询无关且可解释的，但普遍被认为会牺牲准确性。蒸馏角色能否匹配检索以及在哪些任务上匹配尚未被清晰刻画。我们提出PersonaLink，这是一种无需训练的方法，可将用户历史蒸馏为受限的三字段角色并进行递归优化：每次迭代都会在用户自身标记历史的保留切片上对冻结智能体进行自评估，根据错误重写角色，仅当角色在该切片上未出现性能下降时保留结果。由于所有对比均使用同一冻结的7B主干模型，仅在上下文放置内容上存在差异，该设计将表示的影响与模型的影响隔离开来。结果显示存在明显的任务类型不对称：在LaMP-2的200名用户（15类新闻分类）上，PersonaLink达到0.745-0.755的准确率，与BM25检索（0.760-0.765）在统计上无差异。

英文摘要

A personalized language agent must convert a user's interaction history into behavior on each new request at inference time. Two strategies dominate. Retrieval pulls a few of the user's most relevant past items into the prompt, which is accurate but pays a per-query selection and context cost that grows with the history. Distillation instead compresses the history once into a compact natural-language persona, which is bounded, query-independent, and interpretable, but is widely assumed to sacrifice accuracy. Whether, and on which tasks, a distilled persona can match retrieval has not been characterized cleanly. We introduce PersonaLink, a training-free method that distills a user's history into a bounded three-field persona and recursively refines it: each pass self-evaluates the frozen agent on a held-out slice of the user's own labeled history, rewrites the persona from its errors, and keeps the result only when it does not regress on that slice. Because every comparison shares one frozen 7B backbone and differs only in what is placed in context, the design isolates the effect of representation from that of the model. The result is a clear task-type asymmetry. On 200 users of LaMP-2 (15-way news categorization), PersonaLink reaches 0.745-0.755 accuracy, statistically indistinguishable from BM25 retrieval (0.760-0.765).

发表机构

• Seoul National University（首尔国立大学）
• KAIST（韩国科学技术院）
• Korea University（高丽大学）

机构由 AI 辅助整理，请以论文原文为准。