https://superagi.com/wp-content/uploads/2023/07/Recursive-Agent-Trajectory-Fine-Tuning.pdf
Recursive Agent Trajectory Fine-Tuning
Post-execution, the agent would perform a self-analysis, debugging its path trajectory and identifying areas of potential improvement. It then compiles an optimized instruction set for the next run, essentially creating a self-improvement recursive loop for trajectory fine-tuning.
This automated instruction set generation feeds back into the input for the next run, forming a self-improvement loop. You can bootstrap the initial run by giving feedback at every step and once it has tuned its ideal trajectory, you can let go of the bootstraps for subsequent runs.
Note
“comment”: cannot find demo for this