Research
Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes…
Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes from 22.2% to 54.8% on Spider 2.0-SQLite when it is trained
Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes from 22.2% to 54.8% on Spider 2.0-SQLite when it is trained in the same execution harness it uses at deployment. Text-to-SQL models are usually trained to write one static query. Deployed database agents inspect schemas, run probe queries and revise, and the harness for that only appears at inference time. HarnessSQL builds isolated executable databases with hidden answer checks. Teachers run inside the target harness; we keep only verified trajectories for SFT, then apply execution-reward RL. In addition, Qwen3-8B rises from 15.5% to 45.2%, and both models transfer to BIRD-Interact and LiveSQLBench. Paper: https://arxiv.org/abs/2610.12274 Chat with Paper: https://academy.dair.ai/papers/harnesssql-harness-native-training-for-sql-agents-in-realistic-database-environm-2610.12274
Related
- Banger paper from CMU on harness learning. (bookmark it) Also, pay attention to this important new AI engineering skill of improving agents …
- Banger paper on harness continual learning. (bookmark it) If you already are allowing your agents to rewrite their own prompts, skills, or m…
- The Top AI Papers of the Week (July 20 - July 26): - GAMUT - PRO-LONG - Harness Handbook - From Memory to Skills - Progressive Disclosure - …
Source: DAIR.AI (X) | 2026-10-10