Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent

受限人格在分类任务中可媲美检索，但在回归任务中表现不佳

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. 个性化语言智能体必须在推理时将用户的交互历史转化为针对每个新请求的行为。目前主要有两种策略。检索（Retrieval）将用户最相关的几条历史记录提取到提示词中，这种方法准确性高，但需要支付随历史记录增长的单次查询选择成本和上下文成本。

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. 蒸馏（Distillation）则将历史记录一次性压缩为紧凑的自然语言人格，这种人格是受限的、与查询无关且可解释的，但普遍被认为会牺牲准确性。目前，蒸馏人格能否在哪些任务上达到检索的效果，尚未得到明确的界定。

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. 我们引入了 PersonaLink，这是一种无需训练的方法，它将用户的历史记录蒸馏为受限的三字段人格并进行递归优化：每一轮迭代都会在用户已标注历史记录的留出部分上对冻结的智能体进行自我评估，根据错误重写人格，并仅在未出现性能倒退时保留结果。

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). 由于所有对比均共享同一个冻结的 7B 参数主干模型，且仅在上下文内容上有所不同，该设计将表征的影响与模型本身的影响隔离开来。结果显示出明显的任务类型不对称性。在 LaMP-2 数据集的 200 名用户（15 类新闻分类任务）上，PersonaLink 的准确率达到了 0.745-0.755，与 BM25 检索（0.760-0.765）在统计学上没有显著差异。