Jens Lehmann, Sahar Vahdati · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30499 · open-access PDF
Um sistema geralmente inteligente adquire novas habilidades de forma eficiente sem exigir que os seres humanos redesenhem seu armário de software para cada nova tarefa. No entanto, os modelos de linguagem raramente agem sozinhos. Um armário é um programa simbólico que orquestra chamadas para o modelo, manipula a percepção, a memória, o uso de ferramentas, a recuperação e a atribuição de inferências em nome do modelo. O ARC-AGI-3 é um benchmark interativo no qual os agentes devem explorar ambientes desconhecidos, descobrir seus objetivos no vôo e continuar aprendendo.
Machine translation (Meta M2M100); the English original follows.
A generally intelligent system acquires new skills efficiently without requiring humans to redesign its software scaffold for every new task. Yet language models rarely act alone. A harness is a symbolic program that orchestrates calls to the model, handling perception, memory, tool use, recovery, and inference allocation on the model's behalf. ARC-AGI-3 is an interactive benchmark in which agents must explore unfamiliar environments, figure out their goals on the fly, and keep learning as they go. On it, human-steered systems already report ceiling scores across the public games, so we know e
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=2610.30499, 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