Metraipolis › archive › dc_035454341d38
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness — arXiv:2610.19424
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19424
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:02:39.243Z
- SHA-256 of the archived text
2f0db0bb20c2d077dc44397f4b73d0e456054a4fbc71cef4f15cc33521d00444- Stable URL of this page
https://metraipolis.com/documento/dc_035454341d38
How to cite
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness — arXiv:2610.19424 — arXiv (en), https://arxiv.org/abs/2610.19424 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_035454341d38 (Metraipolis archive dc_035454341d38, sha256 2f0db0bb20c2d077dc44397f4b73d0e456054a4fbc71cef4f15cc33521d00444)
BibTeX
@misc{dc035454341d38,
title = {VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness — arXiv:2610.19424},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19424},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_035454341d38; sha256 2f0db0bb20c2d077dc44397f4b73d0e456054a4fbc71cef4f15cc33521d00444},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19424. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory. Recursive harness evolution can automate their design, but how it can reliably discover generalizable systems from limited, noisy, and repeatedly reused feedback remains unclear. We study this question in agentic video understanding, where rich multimodal evidence and coupled mechanisms make harness optimization challenging. We first introduce VideoHarness-BRSI, a recursive self-improvement framework that evolves video harnesses around a frozen vision-language model. Analyzing over 4,000 evolved candidates, we find it competitive with hand-engineered systems but identify three interconnected failure modes: validation overfitting, search-budget dilution, and the early-experience trap. We trace all three to a common root: the same imperfect validation evidence drives both harness revisions and the proposer's search strategy. We therefore propose VideoHarness-SRSI, an evidence-governed framework in which every search decision rests on evidence that is transferable, sufficient, and gathered before the search commits. It restricts the proposer to content-free feedback, informs exploration with instrumented warm-up experiments, and develops mechanisms in isolated probe-race branches before factorial composition and joint refinement. Across four video understanding benchmarks, VideoHarness-SRSI improves the equally weighted mean held-out score by 6.2% relative to VideoHarness-BRSI and reduces the mean validation-test gap by 37.9%. Reliable harness evolution thus depends on how search is organized and informed, not only on how well it optimizes validation performance. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.19424 — 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 2026-10-15T19:35:48.340Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).