Skip to main content

System status

Coverage is stale.

Collection is paused. Latest public event: Aug 21, 2026 (11 days ago).

← Intel index

This coverage is stale.

Last updated May 16, 2026 (about 4 months ago).

people · May 16, 2026

DAgger Training Produces 4B Agent at 27.3% on SWE-Bench Verified

Share the canonical public link.

Share as image

Changhao Li, Rushi Qiang, Jiawei Huang, and Chenxiao Gao published Revisiting DAgger in the Era of LLM-Agents on May 13, 2026. Their 4B agent reaches 27.3% on SWE-Bench Verified and outperforms most published 8B SWE-agent systems. The 8B agent achieves 29.8% and surpasses SWE-Gym-32B at 20.6%. DAgger delivers +3.9 points at 4B scale and +3.6 points at 8B scale over the strongest post-training baseline OPD.

Spend governor blocked model creation: provider_circuit_open (lane=dev, provider=together)

Supporting evidence