3 papers
cs.CL2026
OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents
Andrea Caciolai, Pere-Lluís Huguet Cabot, Chierh Cheng +11
Agentic benchmarks aim to measure how well AI agents plan, search, execute, and recover within realistic multi-tool environments, but they are almost exclusively in English. As AI…
cs.AI2026
Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
Romain Froger, Pierre Andrews, Matteo Bettini +21
We introduce Gaia2, a benchmark for evaluating large language model agents in realistic, asynchronous environments. Unlike prior static or synchronous evaluations, Gaia2 introduces…
cs.AI2025
ARE: Scaling Up Agent Environments and Evaluations
Romain Froger, Pierre Andrews, Matteo Bettini +21
We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of age…