MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.
Introducing openai o3 and o4-mini
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.