GitHub 仓库

facebookresearch/meta-agents-research-environments

Python 首次收录 2025-09-11 更新于 2026-07-16 查看源 ↗

GitHub 仓库 中按Star排名第 701 / 共 783

526 Star

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.

项目介绍

A research environment for simulating complex, real-life tasks that require multi-step reasoning and dynamic adaptation.

Meta Agents Research Environments (ARE) is a platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this research platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges. In particular, ARE runs the Gaia2 benchmark, a follow-up to Gaia, evaluating a broader range of agent capabilities.

Looking for the container-based Gaia2-CLI benchmark stack? Start with gaia2-cli.

ARE addresses critical gaps in AI agent evaluation by providing:…

摘自 github.com/facebookresearch/meta-agents-research-environments

最新指标

Star 526 2026-07-16
Fork 70 2026-07-16
提交 29 2026-07-16
发布 0 2026-07-16
Watcher 7 2026-07-16
开放 issue 15 2026-07-16
开放 PR 18 2026-07-16