Mohammad Kachuee, Phu Mon Htut, Sheng Li, Nikolaos Pappas, Miguel Ballesteros Martinez, Yassine Benajiba, Sujith Ravi, Dan Roth · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28397 · open-access PDF
A Agente AI estende os grandes modelos de linguagem (LLMs) da geração de respostas ao planejamento e execução de fluxos de trabalho complexos, expandindo substancialmente a sua utilidade enquanto expõe os aplicativos a ações inseguras, vazamento de informações e manipulação adversária.Os sistemas multi-agentes expandem ainda mais essas capacidades através de especialização e colaboração, mas autoridade distribuída, papéis heterogêneos e participantes opacos ou potencialmente comprometidos tornam a proteção ainda mais desafiadora.
Machine translation (Meta M2M100); the English original follows.
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
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28397, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange