Youmna Farag, Svetlana Stoyanchev, Simon Keizer, Mohan Li, Rama Doddipatla · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28381 · open-access PDF
O raciocínio sobre a segurança é essencial para agentes incorporados alimentados por modelos de grande linguagem (LLMs). Introduzimos o Contextual Action and Plan Safety Benchmark (CAPSafe), projetado para avaliar o raciocínio de segurança em dois níveis: (1) um conjunto de dados de nível de ação que testa se uma única ação é segura dado o seu contexto ambiental, e (2) um conjunto de dados de nível de plano que avalia se os agentes podem gerar planos seguros de longo horizonte para tarefas domésticas perigosas complexas.
Machine translation (Meta M2M100); the English original follows.
Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate safety reasoning at two levels: (1) an action-level dataset that tests whether a single action is safe given its environmental context, and (2) a plan-level dataset that evaluates whether agents can generate safe long-horizon plans for complex hazardous household tasks. CAPSafe models safety conditions where hazards are situational (inferred from object properties), multiple hazards can co-occur within the
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=2610.28381, 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