Newest papers

Certified Execution Harness for Agentic AI: Safe and Least-Intrusive Petri-Net Supervisory Control Between Reasoning and Action

Chao Gu, Quanyan Zhu · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31376 · open-access PDF

Portuguese

Este artigo estuda o problema da execução segura de ferramentas para agentes de grande modelo de idioma (LLM) sob injeção rápida. Usando redes de Petri, formalizamos a ligação de execução entre o LLM e suas ferramentas como um problema de controle de supervisão, no qual as marcas representam capacidades, aprovações e orçamentos. Uma vez que uma transição só atinge se as marcas de que necessita estiverem presentes, um pedido injetado cujas condições prévias não são atendidas ou já gastas é recusado independentemente de sua formulação. Tratando os resultados da ferramenta como incontroláveis, aplicamos a segurança pelo supervisor permissivo máximo convencional, e esta transferência de segurança

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

Abstract

This paper studies the problem of safe tool execution for large language model (LLM) agents under prompt injection. Using Petri nets, we formalize the execution harness between the LLM and its tools as a supervisory control problem, in which marks represent capabilities, approvals and budgets. Since a transition fires only if the marks it needs are present, an injected request whose preconditions are unmet or already spent is refused regardless of its wording. Treating tool outcomes as uncontrollable, we enforce safety by the conventional maximally permissive supervisor, and this safety transf

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31376, 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.txt

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