PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints

arXiv:2604.11523v1 Announce Type: new Abstract: 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 PACext{-}Bench, a benchmark for systematic evaluation of multi-agent collaboration under privacy constraints. Experiments on PACext{-}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.

Related

• Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
• Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
• SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems
• MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration

Source: arXiv cs.AI | 2026-04-14