arXiv cs.CL· Shuqing Shi, Ziyan Wang, Milind Tambe, Yali Du·· 10 天前AI 评分8
基于显式人格推断的异构偏好下大语言模型编排研究（已撤稿）
Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference
AI 导读
论文提出 HARP 框架，将 LLM 编排中对智能体隐藏偏好的信念从提示词中移出，改为每个智能体在有限候选偏好集上维护一个数值后验，并用贝叶斯规则闭式更新，语言模型只提供动作与各候选的似然。
正文 · 原文
This paper has been withdrawn by Shuqing Shi
No PDF available, click to view other formats
Abstract:LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The agents are typically heterogeneous, each holding a private preference that it pursues but does not reveal. Inferring such hidden preferences from behavior has been a subject of long-standing research in game theory and multi-agent systems. The core challenge lies in maintaining a belief over every agent's preference and updating it from the agents' observed actions. Existing LLM orchestrators carry that belief as prompt text with no explicit update rule. This lets early errors persist and propagate rather than be corrected. We therefore propose \textbf{HARP} (Heterogeneous-preference Agent oRchestration via Preference inference), a novel framework that moves the belief out of the prompt. Specifically, HARP maintains one numeric posterior per agent over a finite set of candidate preferences and updates it in closed form by Bayes' rule. The language model supplies only actions and per-candidate likelihoods, so estimation is decoupled from its reasoning. We prove that HARP attains the same $\tilde O(\sqrt K)$ Bayesian regret as explicit joint inference when the factorization is exact. Furthermore, HARP\textsuperscript{+} augments planning with a bonus for actions that distinguish the candidates, so inference continues even when the optimal action is uninformative. Empirical results on three substrates, ranging from payoffs the preferences fully determine, through payoffs that depend on more than them, to scales where explicit joint inference is infeasible, demonstrate that HARP\textsuperscript{+} is the strongest non-oracle method across the class our theory identifies.
| Comments: | There are confusions on the preferences and personas in the introductions and also misunderstanding in the title |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.07587 [cs.CL] |
| (or arXiv:2610.07587v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07587 arXiv-issued DOI via DataCite |
Submission history
From: Shuqing Shi [view email]
[v1]
Tue, 6 Oct 2026 01:24:56 UTC (1,047 KB)
[v2]
Wed, 7 Oct 2026 11:21:43 UTC (1 KB) (withdrawn)
来源：arXiv cs.CL · arxiv.org