Lili Quan, Longtian Wang, Yuelin Wang, Mingfei Cheng, Chao Shen, Sen Chen, Xiaofei Xie · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28116 · open-access PDF
Los agentes del modelo de idioma grande (LLM) cada vez más ejecutan operaciones comerciales a través de herramientas e interactúan directamente con datos de aplicaciones y servicios. Más allá de completar solicitudes de usuarios, estos agentes deben obedecer reglas comerciales específicas de dominio que restringen cuándo se permiten acciones y qué datos o recursos pueden verse afectados. Violar tales reglas puede conducir a errores de lógica empresarial, incluso cuando una tarea parece tener éxito. Detectar estos errores es difícil porque las reglas rara vez están disponibles como especificaciones explícitas y probables.
Machine translation (Meta M2M100); the English original follows.
Large language model (LLM) agents increasingly execute business operations through tools and interact directly with application data and services. Beyond completing user requests, these agents must obey domain-specific business rules that constrain when actions are permitted and what data or resources may be affected. Violating such rules can lead to business logic bugs, even when a task appears successful. Detecting these bugs is difficult because the rules are rarely available as explicit, testable specifications. They are distributed across system prompts and tool definitions, while others
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=2610.28116, 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