BAAI’s AREX agent uses recursive verification to improve deep research answers
BAAI · hf · 2026-07-24
Key idea
AREX is a recursively self-improving deep research agent that separates discovery from verification: it first gathers evidence and drafts a provisional answer, then runs an outer loop that audits the answer constraint by constraint and launches targeted follow-up research on unresolved claims.
What is new
- Introduces an autonomous context-update tool that compresses long interaction history into a compact improvement state, preserving verified evidence and open constraints without relying on another model.
- Trains the agent with verified synthetic tasks and high-quality trajectories using agentic mid-training and long-horizon reinforcement learning.
- Uses step emphasis to address sparse rewards, focusing learning on moments when decisive evidence is found or a bad research path is corrected.
Results
- Instantiates both a dense 4B model and a 122B-A10B MoE model.
- Reports strong results on BrowseComp, WideSearch, DeepSearchQA, Humanity's Last Exam (HLE) and other reasoning/tool-use benchmarks.
- The paper says AREX beats comparable-scale baselines and remains competitive with models that activate far more parameters.
Related event: BAAI Introduces AREX: A Recursive Self-Improving Research Agent(2 posts)→
More from Research
- Programmable Cellular Automata: CA rules as readable code for explainability — Amidos2006 · 2026-09-11
- GEVIBench launches as a comprehensive benchmark for comparing voltage indicators — drmichaellevin · 2026-09-11
- Gaussian Light Transport: 13D Gaussian Mixtures Speed Up Global Illumination — ssh4net · 2026-09-11
- Llama Loves Pirates — Goodfire's Tom McGrath on teaching math without the pirate style — Machine Learning Street Talk · 2026-09-11
- Fortnow: P vs NP beyond AI's reach, but NP vs L separations could fall — fortnow · 2026-09-11
- MaP-WAM tackles non-Markovian robot manipulation with memory-grounded planning — Sizhe Zhao · 2026-09-11