arXiv cs.MA· Zhengye Han, Linda Ng Boyle·· 11 小时前AI 评分31
从涌现到可逆性：迈向可逆多智能体系统
From Emergence to Reversibility: Toward Reversible Multi-Agent Systems
AI 导读
论文提出“可逆多智能体系统”研究议程：多智能体集体在成长过程中，授权监督者仍能限制指定效果，并在智能体适应后保持限制有效。作者指出，随着智能体学习、共享记忆、委派任务和修复故障，集体可能绕过原有机制找到实现同一效果的替代路径，而常规性能与合规检查仍会通过。研究识别出三个问题：追踪能力所依赖的机制、在旧机制失效前移交控制权、区分合法修复与未授权重建。
正文 · 原文
Abstract:Multi-agent systems become capable through institutional mechanisms, such as rules that route information to agents that act on it. These mechanisms are also natural places to restrict the system. Yet as agents learn, share memory, delegate, and repair failures, the collective can find other paths to the same effects: a restriction on the original mechanism still operates but no longer stops them, while routine performance and compliance checks pass. We propose \textbf{Reversible Multi-agent Systems} as a research agenda: collectives that grow while an authorized supervisor can still restrict specified effects, keep them restricted as agents adapt, and reconstitute useful cooperation under renewed authority. What is reversed is the ability to produce a specified effect; restrictions must hold even if learned knowledge persists. The goal is to preserve effective intervention, not a particular mechanism: at every step of growth, some authorized intervention must keep a specified prohibited effect rare while maintaining required service. We identify three research problems: tracking what capabilities depend on, handing off control before an old mechanism loses its effect, and separating legitimate repair from unauthorized reconstruction. We outline how to evaluate control across growth paths, back control claims with evidence, and allocate the rights to restrict and restore.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.09054 [cs.MA] |
| (or arXiv:2611.09054v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2611.09054 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhengye Han [view email]
[v1]
Fri, 6 Nov 2026 06:29:41 UTC (345 KB)
来源：arXiv cs.MA · arxiv.org