Metraipolis › archive › dc_57905a7ced58
DeepInsight II: One Trace from Benchmark to Robot — arXiv:2608.16556
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16556
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:45:06.281Z
- SHA-256 of the archived text
b278d0fbbf25c8da4081bc74b51e5801cef9f866fec2d8c2b8db84c64aadfd07- Stable URL of this page
https://metraipolis.com/documento/dc_57905a7ced58
How to cite
DeepInsight II: One Trace from Benchmark to Robot — arXiv:2608.16556 — arXiv (en), https://arxiv.org/abs/2608.16556 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57905a7ced58 (Metraipolis archive dc_57905a7ced58, sha256 b278d0fbbf25c8da4081bc74b51e5801cef9f866fec2d8c2b8db84c64aadfd07)
BibTeX
@misc{dc57905a7ced58,
title = {DeepInsight II: One Trace from Benchmark to Robot — arXiv:2608.16556},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16556},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57905a7ced58; sha256 b278d0fbbf25c8da4081bc74b51e5801cef9f866fec2d8c2b8db84c64aadfd07},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16556. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Across a Physical AI stack, evaluation maturity is inversely aligned with deployment risk: foundation models enjoy mature, standardized harnesses, while the embodied layers on which deployment actually turns remain fragmented across benchmark-specific simulators, embodiments, and interfaces. The first DeepInsight report (v1) unified evaluation across this stack behind three abstractions---task, resource, and result---but its quantitative evidence centered on the foundation-model layer; navigation and manipulation (System 1) and whole-body control (System 0) remained simulation case studies, and physical execution was outside its empirical scope. DeepInsight II keeps that substrate fixed and quantifies the embodied half. First, it reproduces released-checkpoint references across two navigation and four manipulation benchmarks under their native protocols. Second, MotionBench places four released whole-body controllers under one workload and metric contract, then carries a qualified within-family cohort from parallel simulation to matched real-robot trials in which simulated and physical rollouts share a parent trace identity while retaining execution-domain-specific records, making the sim-to-real gap a native reduction rather than a reconciliation across toolchains. Third, a composed System 2--1--0 study extends trace localization into five evidence-grounded handoff labels, each mapped to a concrete repair action, with a measured repairability criterion and physical episodes testing the same attribution under hardware-observable state. The contribution is therefore not a new evaluation architecture, but empirical continuity from benchmark execution to matched robot evidence and repair-oriented diagnosis. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16556 — 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 2026-10-18T16:29:13.877Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).