Princeton and Meta propose Self-Direction: storing agent error-correction experience as reusable LoRA adapters
A new paper from Princeton and Meta proposes the Self-Direction method, which lets a failed agent reflect on the current run and trains the lessons into a LoRA adapter about 0.02% the size of the model; a router then loads the closest adapter when a similar failure is encountered. On Qwen3.6-27B, the GAIA task success rate rises from 38.8% to 55.8%, outperforming in-context reflection and the Skills.md file approach. Of 185 errors that had occurred previously, 67.3% of fixes were still effective by the third encounter, versus 42.9% for simple retries.
Why read this
AI score 58
The paper solidifies the agent's error-correction experience into LoRA adapters about 0.02% the size of the model, loaded on demand via routing, and presents a success-rate comparison on GAIA.
Topics
Body
Nice new paper on continuous improvement of AI agents from Princeton and Meta
Finds that agents repeat fewer mistakes when each fix is saved as a LoRA adapter and reused on similar tasks.
Agents can fix a mistake within a session, then often repeat it in the next one. Notes in context get forgotten, and full fine-tuning is costly and can disrupt other skills.
With Self-Direction, a failing agent reflects on its run and trains the lesson into a LoRA adapter about 0.02% of the model's size. A router later loads the closest adapter when the agent fails a similar task.
With Qwen3.6-27B, task success on GAIA rose from 38.8% to 55.8%, beating in-context reflections and a Skills.md file. Across 185 earlier mistakes, 67.3% of repairs still worked by the third encounter, against 42.9% for plain retrying.
If your agents keep making the same mistakes, save each fix as a small adapter they can reload, not only as prompt notes.