No AI summary available for this article.
Why It Matters
People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a language-model agent improve its future actions by training only on explanations of its own experience? We investigate this question by studying Retrospection-Only Fine-Tuning (ROFT), a minimal online procedure designed to isolate the effect of explanation-only training on subsequent behavior. The agent attempts a task, observes available feedback, generates a retrospective explanation, and is fine-tuned with a next-token p...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.35741v1 · Indexed 39 minutes ago