Grégoire Mialon

AI researcher known for GAIA benchmark for general AI assistants and prior work on tool-augmented language models at Meta FAIR.

Role: researcher
Twitter: twitter.com/GregoireMialon
GitHub: github.com/gregoiremialon
Scholar: scholar.google.com/citations
Papers: 3

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile: scholar.google.com/citations

Attribution policy →

3papers·1eval contribs

Authored papers

3

ARE: Scaling Up Agent Environments and Evaluations

arXiv 2025

GAIA: A Benchmark for General AI Assistants

ICLR

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

self-supervised-learning-with-lie-symmetries

Eval contributions

1

GAIA (General AI Assistants)

Meta FAIR (Fundamental AI Research)

466 real-world questions requiring tool use, multi-step reasoning, and web browsing - easy for humans (~92%) but hard for AI assistants.

ActiveTool CallingBrowser UsePlanningAgentic

Affiliations

Previously

Hugging Faceinfra Meta FAIR (Fundamental AI Research)open lab

Frequent co-authors

10

from 3 papers

Thomas Scialom

researcher

2 shared papers

Yann LeCun

VP & Chief AI Scientist

2 shared papers

Amar Budhiraja

Amine Benhalloum

Andrey Rusakov

Bobak T. Kiani

Clémentine Fourrier

researcher

Craig Swift

researcher

Danyal Rehman

Dheeraj Mekala