Metraipolis › archive › dc_1d77f415f4e2

LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents — arXiv:2608.07585

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07585
License (as archived)
CC0-1.0
Archived
2026-10-19T06:49:27.696Z
SHA-256 of the archived text
3fc55d36e3e3d0540977fbf7d5bab0214d9d42fcbf704eca8b7a76109edfcf83
Stable URL of this page
https://metraipolis.com/documento/dc_1d77f415f4e2

How to cite

LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents — arXiv:2608.07585 — arXiv (en), https://arxiv.org/abs/2608.07585 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1d77f415f4e2 (Metraipolis archive dc_1d77f415f4e2, sha256 3fc55d36e3e3d0540977fbf7d5bab0214d9d42fcbf704eca8b7a76109edfcf83)
BibTeX
@misc{dc1d77f415f4e2,
  title = {LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents — arXiv:2608.07585},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07585},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1d77f415f4e2; sha256 3fc55d36e3e3d0540977fbf7d5bab0214d9d42fcbf704eca8b7a76109edfcf83},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07585. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-video understanding requires models to efficiently acquire and reuse sparse visual evidence from long and redundant video streams. Recent video tool-use agents address this challenge by iteratively invoking visual Tools at different temporal scales, but their Tool-Planner communication typically relies on textual observations. Such text-only interfaces provide lossy summaries of Tool computations, causing previously computed visual evidence not verbalized to be discarded and unavailable for subsequent planning. We identify this limitation as the Tool observation bottleneck and propose Latent Visual Evidence-Enhanced Planning (LAVE), a training-free framework for reusing latent visual evidence from completed Tool calls. LAVE introduces a dual-channel observation interface: the visible channel preserves the original textual trajectory, while the latent channel stores pre-verbal visual updates with their Tool roles, source-frame timestamps, and visual locations. During planning, LAVE retrieves evidence relevant to the current Planner state but not covered by textual observations, and integrates it through bounded timestamp-aligned latent updates with entropy-constrained frame-time routing. This enables video agents to reuse existing visual computation without additional training, frame replay, or modifications to the original orchestration. Extensive experiments on Video-MME, LongVideoBench, and CG-Bench show that LAVE consistently improves video tool-use agents across backbones. Under a comparable frame budget, LAVE improves the Video-MME overall score by 3.76 points over the strongest baseline, demonstrating the effectiveness of latent visual evidence reuse for multi-step video-agent planning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.MA).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.07585 — 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 2026-10-19T06:45:31.694Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).