AgentSocialBench：評估以人為本代理社交網絡中的隱私風險

AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks

April 1, 2026

作者: Prince Zizhuang Wang, Shuli Jiang

cs.AI

摘要

隨著OpenClaw等個性化、持久性大型語言模型代理框架的興起，以人為中心的代理化社交網絡正逐漸成為現實——在這種網絡中，協作式AI代理團隊將在多個領域為社交網絡中的個體用戶提供服務。這種設定帶來了新的隱私挑戰：代理必須跨領域協調、在人類之間進行調解，並與其他用戶的代理互動，同時還需保護敏感個人信息。雖然現有研究已評估過多代理協調與隱私保護機制，但以人為中心的代理化社交網絡的動態特性和隱私風險仍未被探索。為此，我們推出首個系統性評估此類場景隱私風險的基準測試框架AgentSocialBench，該框架包含七大類情境，涵蓋雙向及多方互動，並基於具有分層敏感度標籤的真實用戶畫像和定向社交圖譜構建。我們的實驗表明，代理化社交網絡中的隱私保護本質上比單代理場景更為困難：(1) 跨領域和跨用戶的協調會產生持續的資訊洩漏壓力，即使代理被明確指示保護信息；(2) 教導代理抽象化敏感信息的隱私指令反而會引發更多相關討論（我們稱之為抽象化悖論）。這些發現凸顯出現有大型語言模型代理缺乏在以人為中心的代理化社交網絡中實現隱私保護的穩健機制，且要實現代理中介式社交協調的安全實際部署，需要超越提示詞工程的新方法。

English

With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are becoming a reality. This setting creates novel privacy challenges: agents must coordinate across domain boundaries, mediate between humans, and interact with other users' agents, all while protecting sensitive personal information. While prior work has evaluated multi-agent coordination and privacy preservation, the dynamics and privacy risks of human-centered agentic social networks remain unexplored. To this end, we introduce AgentSocialBench, the first benchmark to systematically evaluate privacy risk in this setting, comprising scenarios across seven categories spanning dyadic and multi-party interactions, grounded in realistic user profiles with hierarchical sensitivity labels and directed social graphs. Our experiments reveal that privacy in agentic social networks is fundamentally harder than in single-agent settings: (1) cross-domain and cross-user coordination creates persistent leakage pressure even when agents are explicitly instructed to protect information, (2) privacy instructions that teach agents how to abstract sensitive information paradoxically cause them to discuss it more (we call it abstraction paradox). These findings underscore that current LLM agents lack robust mechanisms for privacy preservation in human-centered agentic social networks, and that new approaches beyond prompt engineering are needed to make agent-mediated social coordination safe for real-world deployment.