arXiv cs.AI· Ruiyi Yang, Gayathri Lihinikaduarachchi, Rahat Masood, Flora D. Salim, Salil S. Kanhere·· 1 小时前AI 评分30
GuardianAgentFlow：多智能体协同保护 Web 隐私
GuardianAgentFlow: Multi-Agent Coordination for Web Privacy Protection
AI 导读
arXiv 论文提出 GuardianAgentFlow，一个通过显式发布契约中介 Web 请求外发的多智能体框架，包含限制检查、共享保护范围与候选反馈修订机制。在带人工审核意图标签的请求及 PrivacyLens、AgentDAM 动作提案评估中，请求契约成功率提升，且与隐私感知智能体组合时提供互补保护。小模型中介下协调收益仍存在，专用服务器中介延迟低于全策略推理。
正文 · 原文
Abstract:Web agents need to use private context without unnecessarily disclosing it. Effective protection must distinguish between requests that may be sent after sanitization and those that must be withheld, while preserving the information needed for authorized tasks. We present GuardianAgentFlow, a multi-agent framework that mediates outgoing Web requests through an explicit release contract. A dedicated restriction check grounds permission in the user's instruction; a shared protection scope aligns rewriting with disclosure checking; and candidate-grounded feedback guides revision before transmission. Experiments on Web requests with human-reviewed intent labels show improved request-contract success, while controlled comparisons and role ablations identify the contributions of restriction handling, policy evidence, and candidate checking. Evaluations of action proposals from PrivacyLens and AgentDAM demonstrate complementary protection when mediation is composed with privacy-aware agents. Experiments with smaller mediation models show that the coordination benefit persists with reduced model capacity. Dedicated-server measurements show lower mediation latency than full-policy reasoning, while real-site browser tests quantify integration overhead.
| Comments: | 13 pages, 3 figures |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.15097 [cs.AI] |
| (or arXiv:2611.15097v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15097 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ruiyi Yang [view email]
[v1]
Wed, 11 Nov 2026 06:19:31 UTC (597 KB)
来源：arXiv cs.AI · arxiv.org