Metraipolis › archive › dc_eae20cfa4786
Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision? — arXiv:2610.33029
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33029
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:26.713Z
- SHA-256 of the archived text
f33ff0be5830f79e30e3adf0c05825f10dfa9968c446baea78defe3740ef3f36- Stable URL of this page
https://metraipolis.com/documento/dc_eae20cfa4786
How to cite
Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision? — arXiv:2610.33029 — arXiv (en), https://arxiv.org/abs/2610.33029 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eae20cfa4786 (Metraipolis archive dc_eae20cfa4786, sha256 f33ff0be5830f79e30e3adf0c05825f10dfa9968c446baea78defe3740ef3f36)
BibTeX
@misc{dceae20cfa4786,
title = {Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision? — arXiv:2610.33029},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33029},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eae20cfa4786; sha256 f33ff0be5830f79e30e3adf0c05825f10dfa9968c446baea78defe3740ef3f36},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33029. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-improving agents write lessons from the outcomes of their runs; when outcomes are noisy, a lesson can carry chance into later decisions. We measure one link of this chain in a registered study. In 256 synthetic worlds, each a recurring task with two interchangeable tools of recorded reliability, a scripted previous run used the more reliable tool (a good decision) or the less reliable one (a bad decision), with an assigned outcome: success or a transient failure. A model wrote a lesson from the run with ReasoningBank's memory-writing instruction; a fresh session of the same model, holding the authoritative log and the previous result, chose the next run's first tool with one memory item: that lesson, the lesson from the other outcome, an irrelevant item, or an unreasoned directive. The protocol was frozen, deposited and timestamped before any confirmatory call; 11 LLM endpoints gave 90,084 answers. After a chance failure of the better tool, the panel's lessons carried the chance (registered reading luck-carrying; interaction +0.112, 95% interval [+0.097, +0.126]): readers named the worse tool in 11.6% of next runs with the lesson written from that failure, against 0.4% with an irrelevant item and 0.4% with the lesson written from a success. The effect was +0.042 where the log stated that failures are independent and +0.181 where it did not (descriptive). After a lucky success of the worse tool, the interaction was bounded below 0.10 (+0.002), a bound, not evidence of no harm. In exploratory readings, 6 endpoints carried the chance (up to +0.352); 5 were bounded below 0.10. In secondary comparisons, a three-sentence decision-quality note in the writing instruction lowered the worse-tool rate after a chance failure to 7.5%, and one instruction for both outcomes with a no-change option to 3.1%; neither met the registered harm-reduction rule at every such endpoint. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2610.33029 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:30.791Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).