🤖 What happens when you hand an agent the full SFT data-research task?
This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
🤖 What happens when you hand an agent the full SFT data-research task? It only mixes ratios. No repaired samples, no new responses, no synthetic data — a word cloud full of "weights" and "proportions", and almost no score gain over dozens of rounds. AutoSFT (THUNLP × BUPT × ModelBest × UIUC × CUHK) splits the data-research lifecycle into roles: a dedicated Executor, 4 Analysis Subagents (training data / failure cases / learning dynamics / research history), a Synthesis writer with a verifier, and a meta agent that picks the next recipe. 1️⃣ Single-agent baseline: 33 rounds, only Mixture; co
Posted by OpenBMB (13.2k followers) 1 h ago · 3 likes · 338 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: autosft.
More dev work like this
- 🚀 Novita Sandbox is now available in Miles by @radixark . — @novita_labs
- 让 Claude Code 装上 Papermorph 这个 Skill 后，给它一本课本 PDF，就能做成带旁白的互动网页课，故事能做成纸偶动画，书还能做成纪录片和竖屏短片。 — @GitHub_Daily
- What’s new in Lovable, featuring the people who built it! — @Lovable
- For five days I'm building a coding agent with Pydantic AI, one capability at a time.… — @marcelotryle
- When in doubt and you think you are losing your mind, let alone your businesses... ask… — @PixelRainbowNFT
- Impressive paper from CMU. — @omarsar0
- 本来只是随手截个图试试 Snippai，半小时后，我常用的 OCR 就被卸了。 — @bkdgiffug
- If RugBot’s limits feel pulled. Do this: — @_junaidkhalid1
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.6k posts from 5k X accounts over the last 21 days, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 15:02 UTC. Full method.