Metraipolis › archive › dc_1389ea4af80b

RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement — arXiv:2609.27612

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27612
License (as archived)
CC0-1.0
Archived
2026-10-08T12:53:39.739Z
SHA-256 of the archived text
69229d16f7f0b1654120bd12343f094b77786b8d9858294f0000b9fcec2bf6d0
Stable URL of this page
https://metraipolis.com/documento/dc_1389ea4af80b

How to cite

RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement — arXiv:2609.27612 — arXiv (en), https://arxiv.org/abs/2609.27612 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1389ea4af80b (Metraipolis archive dc_1389ea4af80b, sha256 69229d16f7f0b1654120bd12343f094b77786b8d9858294f0000b9fcec2bf6d0)
BibTeX
@misc{dc1389ea4af80b,
  title = {RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement — arXiv:2609.27612},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27612},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1389ea4af80b; sha256 69229d16f7f0b1654120bd12343f094b77786b8d9858294f0000b9fcec2bf6d0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27612. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon robot execution requires a clear distinction between a model's proposal, a controller's termination, and verified task completion. We present RegenHarness, an evidence-gated robot-agent harness connecting task planning to heterogeneous robot skills. Its execution architecture couples a model loop for context-conditioned proposals with an agent loop for dispatch, observation, verification, commitment, and bounded recovery. Four role-isolated contexts separate planning, supervision, verification, and recovery inputs. Versioned memory distinguishes observed facts from accepted task progress, while an identity- and version-bound commit gate controls updates to trusted task state. The runtime combines duplicate-dispatch control, resource leases, and recovery budgets under explicit backend contracts, and checks the original user goal before reporting completion. To our knowledge, we are the first to introduce an evidence-gated recursive self-improvement (RSI) protocol for embodied robotic agents. Across missions, execution records motivate candidate changes to context rules, task templates, routing, and recovery policies; fixed regression checks and release authorization govern their acceptance; versioned rollout and rollback preserve configuration traceability. This RSI protocol revises the harness configuration without online model-weight updates or permission to weaken the commit gate. A real quadruped deployment documents voice-triggered warehouse navigation, panoramic inspection, visual analysis, message delivery, return, and spoken reporting through linked audio, images, trajectories, and receipts. A separate circuit demonstrates why completion depends on execution history rather than endpoint proximity alone. Together, the cases demonstrate integrated perception, physical execution, communication, and history-dependent completion in real-world robot tasks.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.27612 — 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 2026-10-08T12:21:19.485Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).