ARE: Scaling Up Agent Environments and Evaluations
This work addresses the need for scalable and robust evaluation frameworks for AI agents, enabling the community to create tailored benchmarks, though it is incremental in building on existing environment and benchmark concepts.
The authors introduced Meta Agents Research Environments (ARE), a platform for scalable agent environment creation and evaluation, and Gaia2, a benchmark built on ARE to measure general agent capabilities, finding that no system dominates across all intelligence aspects and that stronger reasoning often reduces efficiency.
We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to build complex and diverse environments, each with their own rules, tools, content, and verifiers, helping to bridge the gap between model development and real-world deployment. We also propose Gaia2, a benchmark built in ARE and designed to measure general agent capabilities. Beyond search and execution, Gaia2 requires agents to handle ambiguities and noise, adapt to dynamic environments, collaborate with other agents, and operate under temporal constraints. Unlike prior benchmarks, Gaia2 runs asynchronously, surfacing new failure modes that are invisible in static settings. Our experiments show that no system dominates across the intelligence spectrum: stronger reasoning often comes at the cost of efficiency, and budget scaling curves plateau, highlighting the need for new architectures and adaptive compute strategies. Perhaps more importantly, ARE abstractions enable continuous extension of Gaia2 to other environments, empowering the community to rapidly create new benchmarks tailored to their domains. In AI's second half, progress increasingly depends on defining meaningful tasks and robust evaluations to drive frontier capabilities forward.