Metraipolis › archive › dc_77c4e15c1bf5
DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents — arXiv:2609.40306
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.40306
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:46:20.765Z
- SHA-256 of the archived text
f6af4672dd640d031dc8b0207871a648aa016fd416a5c8ca7e6e300c01a29694- Stable URL of this page
https://metraipolis.com/documento/dc_77c4e15c1bf5
How to cite
DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents — arXiv:2609.40306 — arXiv (en), https://arxiv.org/abs/2609.40306 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77c4e15c1bf5 (Metraipolis archive dc_77c4e15c1bf5, sha256 f6af4672dd640d031dc8b0207871a648aa016fd416a5c8ca7e6e300c01a29694)
BibTeX
@misc{dc77c4e15c1bf5,
title = {DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents — arXiv:2609.40306},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.40306},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77c4e15c1bf5; sha256 f6af4672dd640d031dc8b0207871a648aa016fd416a5c8ca7e6e300c01a29694},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40306. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system component should be revised. We propose DynaHarness, a dynamic physical harness that couples semantic reasoning with physical governance through a shared execution contract and turns failure evidence into validated capability revisions. To be more specific, the slow brain proposes capabilities and symbolic arguments, while the fast brain grounds and monitors commands, refuses unresolved actions, substitutes capabilities, and requests replans when needed. The physical execution contract bounds each accepted command and records execution evidence across analytic skills, recovery skills, and the frozen VLA. Failure attribution localizes faults in these records and directs targeted revisions of reusable capabilities or execution mechanisms. Paired regression checks govern admission or rejection, closing the self-evolution loop. On LIBERO-Pro, DynaHarness achieves 75.2% on 800 newly sampled initial states, compared with 17.5% for the frozen policy. With the same capability library, full dynamic execution reaches 74.0% versus 63.9% under nominal one-step replanning. This demonstrates the value of DynaHarness as a dynamic physical harness that governs how existing capabilities are grounded, monitored, and coordinated during execution. Our project page is at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.40306 — 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 2026-10-07T12:14:14.250Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).