arXiv cs.MA· Bruno Arcanjo, Zhaoxing Li, Sebastian Stein·· 2 天前AI 评分25
Agentic-Priors：用 LLM 解决偏好 elicitation 的冷启动问题
Agentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference Elicitation
AI 导读
Agentic-Priors 让 LLM 以可解释的方式陈述新用户的权衡（如支付意愿、时间价值），并将其映射为多项 logit 系数的先验，再由贝叶斯学习器随观测到的选择逐步修正。
正文 · 原文
Abstract:An agent that learns a user's preferences from their choices faces a cold start problem: before any choices are observed, it must rely solely on a prior. Informative priors are usually fitted to historical choice data, which new tasks and deployments lack. To address this, we present Agentic-Priors, which lets agentic systems use the implicit knowledge of large language models (LLMs) instead. Specifically, an LLM states a new user's trade-offs in interpretable terms, such as willingness to pay or value of time, which we map to a prior over multinomial logit coefficients. This prior is then refined by a Bayesian learner as choices are observed. Across seven choice datasets, Agentic-Priors improves cold start accuracy over an uninformed prior by 5-40 percentage points. It also outperforms AutoElicit, a state-of-the-art LLM prior-elicitation method, on three datasets and loses on one. It is up to 18 points more accurate than in-context learning, and never significantly worse. Against hierarchical Bayes models fitted to surveys of increasing size, our approach is worth roughly 6-40 surveyed users, in terms of log-loss, so its value is concentrated in a deployment's first users.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21938 [cs.MA] |
| (or arXiv:2610.21938v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21938 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bruno Arcanjo Mr [view email]
[v1]
Thu, 15 Oct 2026 14:14:04 UTC (277 KB)
来源：arXiv cs.MA · arxiv.org