AutoSFT 透過將 SFT 資料研究流程拆分為多角色代理，顯著提升模型微調表現。
- - 基準對比：單一代理 33 回合僅做 Mixture，IFEval 最高 50 回合仍未達 63。
- AutoSFT 30 回合全 6 個行動族，IFEval 第 6 回合 63.33，30 回合 67.10，提升 6.5 分。
AI 伴隨問答
針對這篇報導有疑問？可直接點選快捷問題或向 AI 追問背景脈絡與技術細節：
🤖 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; context hit 94.7%, compressed 10 times; Executor cuts compression 10→5 and shell events 58%→29%.
2️⃣ AutoSFT: all 6 action families appear across 30 rounds; IFEval round 6 = 63.33, beating the baseline's best over 50 rounds; +6.5 at the same budget; round 30 = 67.10.
3️⃣ Synthesis alone: IFEval +3.4, IFBench +2.9; MBPP+ coding +3.7.
The takeaway: automating data research may depend more on covering diverse data actions than on a stronger single action.
📄 Paper: https://t.co/dzsl4fZe2J
💻 Code: https://t.co/fUphrIzn9M
#AIAgent #SFT #LLM #DataCentricAI #PostTraining #RSI #AgenticAI #THUNLP #AutoSFT #FineTuning