Shibo Jin, Zhiqiu Xu, Yiling Zou, Shangyu Gong, Mayur Naik · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30116 · open-access PDF
Através de uma mistura de interações do mundo real, de pipelines de treinamento sintéticos a dados compartilhados na web aberta, os LLMs de fronteira absorvem o que seus antecessores e concorrentes criam. Quão bem cada modelo desempenha seu papel neste ecossistema, como criador e como solvente? Introduzimos Environment Duels, um benchmark de agência dinâmico que avalia ambas as capacidades em ambientes interativos. Cada modelo escreve ambientes, cada um com uma dica privilegiada, visando tarefas que os solventes capazes falham sem a dica e passam com ele.
Machine translation (Meta M2M100); the English original follows.
Through a tangle of real-world interactions, from synthetic training pipelines to data shared on the open web, frontier LLMs absorb what their predecessors and competitors create. How well does each model play its role in this ecosystem, as a creator and as a solver? We introduce Environment Duels, a dynamic agentic benchmark that evaluates both capabilities on interactive environments. Each model writes environments, each with a privileged hint, aiming for tasks that capable solvers fail without the hint and pass with it. Across nine frontier LLMs, solving and authoring prove to be distinct s
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=2610.30116, 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