Metraipolis › archive › dc_f73a08cda928
When Is Enough Enough in Self-Evolving LLM Systems? — arXiv:2610.04756
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04756
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:24:47.199Z
- SHA-256 of the archived text
f916f0e2e43225296c75357a1630e42a9f817702445bf06c2667832803e15b73- Stable URL of this page
https://metraipolis.com/documento/dc_f73a08cda928
How to cite
When Is Enough Enough in Self-Evolving LLM Systems? — arXiv:2610.04756 — arXiv, https://arxiv.org/abs/2610.04756 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f73a08cda928 (Metraipolis archive dc_f73a08cda928, sha256 f916f0e2e43225296c75357a1630e42a9f817702445bf06c2667832803e15b73)
BibTeX
@misc{dcf73a08cda928,
title = {When Is Enough Enough in Self-Evolving LLM Systems? — arXiv:2610.04756},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04756},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f73a08cda928; sha256 f916f0e2e43225296c75357a1630e42a9f817702445bf06c2667832803e15b73},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04756. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-evolving large language model (LLM) systems repeatedly propose, evaluate, and incorporate updates to prompts, skills, or other persistent artifacts. Despite their growing effectiveness, these systems typically operate under a predetermined iteration or compute budget, without a principled criterion to determine when further evolution is no longer worthwhile. This can lead to two undesirable consequences: unnecessary computation after performance has saturated and the risk of returning late updates that overfit or exploit the evaluation signal. These issues motivate us to study two fundamental questions: when should a self-evolving system stop, and what should it output once it stops? We address the first by formulating an online sequential testing problem and constructing an anytime-valid restart detector using the per-item paired evaluation outcomes already produced by self-evolving LLM systems. We address the second by formulating a change-point estimation problem and using the estimated transition to select an earlier artifact for output. The resulting procedure is plug-and-play and requires no modification of the underlying self-evolving algorithms. Across two self-evolving frameworks, three LLM model families, and five benchmarks, our method substantially reduces computation costs while maintaining comparable unseen-test performance. For example, on SearchQA with SkillOpt and DeepSeek V4 Flash, our method stops at round 4 rather than the full budget of 40, reducing token usage by 91.6% while achieving 82.43% unseen-test accuracy versus 82.00% under the full-budget run. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.04756 — 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 2026-10-06T05:24:05.514Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).