FlexSQL: multi-path Text-to-SQL agent hits 65.4% on Spider2, beating o3-based agents
xiye_nlp · x · 2026-10-08
New COLM paper FlexSQL introduces a Text-to-SQL agent whose key idea is not collapsing complex queries into one schema/interpretation/SQL program too early — it keeps multiple grounded solution paths alive and executes each with the tools it needs. Built on gpt-oss, it reaches 65.4% on Spider2, outperforming agents built with larger models like DeepSeek-R1 and o3. Poster session Thursday morning, Imperial 70.
More from coding & agent
- Durable Actors: open-source Durable Objects alternative built for agent fleets — ritakozlov · 2026-10-08
- Essential tech skills in the AI era: Linux, Claude Code, Git, LaTeX and more — jessi_cata · 2026-10-08
- Prompting is becoming more like hiring a human: make the model prove it understands your repo first — seanmcdonaldxyz · 2026-10-08
- Sentry CEO: benchmarks show nearly all code review models surface the same primary issues — zeeg · 2026-10-08
- Meta, UW et al. open-source Context Language Models that natively manage their own context — RulinShao · 2026-10-08
- Dev says he can't remember the last time he ran a git command by hand — haydendevs · 2026-10-08