Applied Compute Launches Ari Autoresearch Agent for Autonomous Post-Training

Applied Compute released Ari Autoresearch, an agent that autonomously runs post-training experiments on the AC2 platform. In a single 16-hour unattended run, it boosted chess puzzle reward from 0.118 to 0.629, a 5.3x improvement.

2026-11-05 ~ 2026-11-05 · 2 related posts

• Ari agent post-trains Qwen3.5-9B unsupervised for 16h, reward 0.118→0.629 — ypatil125 · 2026-11-05
• Applied Compute's Ari Autoresearch lifts Qwen3.5-9B chess reward 5.3x in a 16-hour autonomous run — ypatil125 · 2026-11-05