Learning to Recover from LLM Agent Failures at Test Time
Repository Index
47,133 repositories indexed
1–4 of 4 · Most stars
A framework for continual learning and recursive self-improvement through harness adapter evolution.
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
- deep-learning
- llm-agents
- optimizer
- pytorch