提出隐私约束下多智能体协作评估基准，揭示隐私限制导致协作性能下降。
PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints
- 构建PAC-Bench基准，系统评估隐私约束下的多智能体协作表现。
- 隐私约束使协作效率下降，结果更依赖发起方而非合作方。
- 发现三类协调失效机制，需新协作框架应对隐私挑战。
我们正进入个人与组织广泛部署专用AI智能体并与其他智能体交互协作的时代。然而，隐私约束下的多智能体协作动态仍不清晰。本文提出PAC-Bench，一个用于系统评估隐私约束下多智能体协作的基准。在PAC-Bench上的实验表明，隐私约束显著降低协作性能，并使结果更依赖于发起智能体而非合作智能体。进一步分析揭示，性能下降由重复出现的协调失败引起，包括早期隐私违规、过度保守抽象及隐私诱导的幻觉。综合来看，本研究将隐私感知的多智能体协作识别为一个独特且未解决的挑战，需要超越现有智能体能力的新协调机制。
原文摘要 · Abstract (English)
We are entering an era in which individuals and organizations increasingly deploy dedicated AI agents that interact and collaborate with other agents. However, the dynamics of multi-agent collaboration under privacy constraints remain poorly understood. In this work, we present $PAC\text{-}Bench$, a benchmark for systematic evaluation of multi-agent collaboration under privacy constraints. Experiments on $PAC\text{-}Bench$ show that privacy constraints substantially degrade collaboration performance and make outcomes depend more on the initiating agent than the partner. Further analysis reveals that this degradation is driven by recurring coordination breakdowns, including early-stage privacy violations, overly conservative abstraction, and privacy-induced hallucinations. Together, our findings identify privacy-aware multi-agent collaboration as a distinct and unresolved challenge that requires new coordination mechanisms beyond existing agent capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。