Newest papers

MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems

Mohammad Kachuee, Phu Mon Htut, Li Sheng, Nikolaos Pappas, Miguel Ballesteros Martinez, Yassine Benajiba, Sujith Ravi, Dan Roth · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28397 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

複雑なワークフローの計画および実行に反応を生成し、複雑なワークフローを構築し、そのユーティリティを大幅に拡大し、アプリケーションを不安全な行動、情報漏洩および敵対的な操作にさらす。 複数のエージェントシステムは、専門化と協力を通じてこれらの能力をさらに拡大しますが、分散された権限、異質な役割、および透明または潜在的に損なわれた参加者は、保護をさらに挑戦します。 既存の防衛は、重要な個々のタスクに対処しますが、ローカル実行、システムレベルの相互作用、および執行基準の分散されたカバーを提供します。 我々は、分散された権限、異なる役割、および単一および複数のエージ

Machine translation (Meta M2M100); the English original follows.

Abstract

Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe actions, information leakage, and adversarial manipulation. Multi-agent systems further expand these capabilities through specialization and collaboration, but distributed authority, heterogeneous roles, and opaque or potentially compromised participants make safeguarding even more challenging. Existing defenses address important individual threats but provide fragmented coverage across local execution, system-level interactions, and enforcement mechanisms. We introduce MAS-Guard, a unified framework that closes this gap for safeguarding single- and multi-agent AI applications containing both instrumentable and opaque agents. Within instrumentable agents, the proposed local Agent Guardrail (A-Guard) layer applies task-specific experts to assess agentic events. At the system level, developer-owned Agent Charters and a Control Plane combine deterministic structural checks of routes, agent capabilities, and message formats with semantic assessments of roles and message content. These complementary layers enable enforcement through a shared set of interventions: allow, reflection, confirmation, and block. Evaluated across six benchmarks covering diverse single- and multi-agent scenarios with three agent LLMs from different providers, MAS-Guard reduces the overall attack success rate by 71.5-86.3% relative to unguarded agents, while meeting the utility reference criterion on benign tasks.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Safeguarding, Computer science, Enforcement, Set (abstract data type), Computer security, Adversarial system

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange