Self-Improvement Memory Enables Continual Recursive Self-Improvement
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Researchers at Google Cloud AI and Google DeepMind propose Continual Recursive Self-Improvement, which continues automated agent-harness optimization after a benchmark or policy-model change. Their Self-Improvement Memory stores, for each recurring harness problem, the attempted edits, their rationale, predicted and observed outcomes, and evaluation context, and conditions later proposals on that…