Metraipolis › archive › dc_bf2c7e2af00e
When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents — arXiv:2610.19910
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19910
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:18:46.410Z
- SHA-256 of the archived text
e2bceeda580c072ce96f816732c39e886123a47ceb5e6bc2830087fa4b2073cd- Stable URL of this page
https://metraipolis.com/documento/dc_bf2c7e2af00e
How to cite
When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents — arXiv:2610.19910 — arXiv (en), https://arxiv.org/abs/2610.19910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf2c7e2af00e (Metraipolis archive dc_bf2c7e2af00e, sha256 e2bceeda580c072ce96f816732c39e886123a47ceb5e6bc2830087fa4b2073cd)
BibTeX
@misc{dcbf2c7e2af00e,
title = {When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents — arXiv:2610.19910},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19910},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf2c7e2af00e; sha256 e2bceeda580c072ce96f816732c39e886123a47ceb5e6bc2830087fa4b2073cd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks. Existing evaluations largely examine clean learning or perturbations encountered after skills are frozen, leaving robustness during self-evolution insufficiently understood. We introduce RSE-Bench, to our knowledge the first benchmark for evaluating skill self-evolution under ordinary, non-adversarial noise. It spans four domains and six benchmarks, with controlled perturbations to instructions, environmental evidence, execution records, and outcome--record pairings that preserve the underlying tasks and native scoring rules. The protocol separates noise during learning from input-side noise at evaluation, testing frozen skill stores on held-out tasks. We also introduce \textsc{RSEClaw}, a method-agnostic framework supporting consistent noise injection and process diagnostics of actual exposure and skill updates. Across three methods and two backbones, noisy learning retains only $25.5\%$--$42.1\%$ of the aggregate gain achieved by clean self-evolution, depending on the noise type. Perturbations confined to execution records and outcome--record pairings cause average losses comparable to input-side noise, despite leaving the original executions and evaluations intact. Diagnostics further identify differences in candidate skill text that coexist with small changes in mean held-out performance.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.19910 — 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 2026-10-15T13:53:35.670Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).