Metraipolis › archive › dc_630aeea2b19e

LVMH: A Meta-Optimization Harness for Long-Video Agent Memory — arXiv:2610.23904

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23904
License (as archived)
CC0-1.0
Archived
2026-10-20T08:41:48.807Z
SHA-256 of the archived text
81bf52dc0b45164cb4407a2dbe8455e828a64265e5d3ba62cbe0f3d0de61306f
Stable URL of this page
https://metraipolis.com/documento/dc_630aeea2b19e

How to cite

LVMH: A Meta-Optimization Harness for Long-Video Agent Memory — arXiv:2610.23904 — arXiv (en), https://arxiv.org/abs/2610.23904 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_630aeea2b19e (Metraipolis archive dc_630aeea2b19e, sha256 81bf52dc0b45164cb4407a2dbe8455e828a64265e5d3ba62cbe0f3d0de61306f)
BibTeX
@misc{dc630aeea2b19e,
  title = {LVMH: A Meta-Optimization Harness for Long-Video Agent Memory — arXiv:2610.23904},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23904},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_630aeea2b19e; sha256 81bf52dc0b45164cb4407a2dbe8455e828a64265e5d3ba62cbe0f3d0de61306f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23904. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-video agents must map hours or days of multimodal evidence into a bounded context while respecting token and latency budgets, making memory design a context-management challenge. Existing memory systems largely rely on hand-designed policies, leaving open how to jointly optimize memory design for performance and efficiency. We propose Long Video Meta-memory Harness (LVMH), an automated multi-agent framework that formulates memory-policy development as multi-objective code search around a fixed answer model. To guard against self-certification and development-set overfitting, LVMH separates implementation from independent review and enforces protected observation boundaries. Persistent meta-memory records past proposals, traces, costs, and failures to guide subsequent policy revisions. Through this harness, we discover Self-Evolving Evidence Memory (SEEM), a "text-first, vision-second" policy that answers from compact structured event memory and evidence specialists, consulting localized frames through a selective visual gate. The policy evolved on EgoLifeQA generalizes to unseen benchmarks, outperforming Meta-Harness on both Ego-R1 Bench and Video-MME (L) with GPT-5 mini. Across the three benchmarks, SEEM with GPT-5 achieves 65.7% average accuracy, surpassing the previous state of the art by 7.7 percentage points with approximately 32x lower average evaluation token use and 91x shorter average response time.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.23904 — 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 2026-10-20T08:41:40.082Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).