PolicyMediator：面向 OPC 生态的多地区政策学习中介智能体框架
PolicyMediator: Multi-Regional Policy Learning through Mediation Agents with Evolving Skills in OPC Ecosystems
AI 导读
研究者提出 PolicyMediator，一个面向一人公司（OPC）跨地区政策协调的认知约束 Stackelberg 领导-多追随者框架，中介智能体向 OPC 解释经核验政策、向政府反馈需求以支持政策学习。在中国六地区、五类 OPC、五种场景和三种 OPC 模拟骨干的实验中，它在全部 15 个组合中排名第一，相比八个基线的均值将政府综合目标提升 42.4%，OPC 平均效用提升 40.9%。
正文 · 原文
Abstract:One-person companies (OPCs) are emerging enterprises operated by individual entrepreneurs through digital platforms and LLM-based AI agents. These highly skilled entrepreneurs are characterized by being digital nomads, with limited reliance on local ecosystems. Governments in China use distinct regional support policies to attract mobile OPCs, turning local support into a cross-regional coordination problem. OPCs compare regions to maximize their own utility, but imperfect policy perceptions may cause them to reject otherwise suitable locations. Existing policy-learning methods optimize resources under fixed perceptions, while consensus-formation methods aggregate views without feeding cognitive changes back into policy learning. This disconnect produces mismatched location choices and inefficient regional policy adjustment. We introduce PolicyMediator, a cognition-constrained leader-multi-follower Stackelberg framework with bilateral mediation. The mediator explains verified policies to OPCs to build awareness and trust, and reports their needs and unresolved concerns to governments for policy learning. Its self-evolving skills retain, revise, or prune strategies using verification, allocation, capacity, and objective trajectories rather than mediation success alone. Across six-region simulations in China with five OPC types, five scenarios, and three OPC-simulator backbones, PolicyMediator ranks first in all 15 OPC-backbone--scenario combinations. Over the eight-baseline mean, it improves the aggregate government objective, combining economic performance, employment benefit, and policy-access equality, by 42.4% and average OPC utility by 40.9%.
| Comments: | 12 pages, 5 figures |
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.35997 [cs.MA] |
| (or arXiv:2610.35997v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35997 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jie Li [view email]
[v1]
Mon, 26 Oct 2026 13:21:44 UTC (1,569 KB)
来源：arXiv cs.AI · arxiv.org