BAAI's AREX-2 Trains Self-Improving Agents, Hits 92.2 on GAIA and 81.8 on MLE-bench Lite
BAAI · hf · 2026-10-01
BAAI presents AREX-2, which trains test-time self-improvement by synthesizing long-horizon reflective trajectories from ML and algorithmic programming tasks. The Qwen3.8-27B-based agent scores 81.8 on MLE-bench Lite, 70.7 on Frontier-CS, and transfers to deep research with 84.0 on BrowseComp, 52.6 on HLE, 92.2 on GAIA, and 93.8 on DeepSearchQA, improving as its round budget grows.
Related event: BAAI Open-Sources AREX-2: 27B Long-Horizon Self-Improving Agent(5 posts)→
More from coding & agent
- Blender MCP hits 34.5k stars: direct 3D modeling in plain language with any LLM — sidahuj · 2026-11-15
- 18 agents coding overnight on one Linux box: 'I'm the bottleneck now' — AIOSAI · 2026-11-15
- IBM Engineer on Trustworthy AI Evals: Calibrate LLM Judges, Check Agent Trajectories — TejasKumar_ · 2026-11-15
- Antigravity Browser Agent Swarm Turns a Portrait Into Google Sheets Pixel Art — Saboo_Shubham_ · 2026-11-15
- CrommaCode launches: a gamified desktop terminal for watching Claude Code and Codex work — huangyun_122 · 2026-11-15
- MCP server + Ollama drives Final Cut Pro: 30-min video rough cut in under 5 minutes — Technovangelist · 2026-11-15