Metraipolis › archive › dc_a5ddfff4e7a5
RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks — arXiv:2610.20935
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20935
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T08:59:32.948Z
- SHA-256 of the archived text
79a88ba0335a2173573da913632c531bd20e7300e2ba1c953698192105efcb73- Stable URL of this page
https://metraipolis.com/documento/dc_a5ddfff4e7a5
How to cite
RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks — arXiv:2610.20935 — arXiv (en), https://arxiv.org/abs/2610.20935 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5ddfff4e7a5 (Metraipolis archive dc_a5ddfff4e7a5, sha256 79a88ba0335a2173573da913632c531bd20e7300e2ba1c953698192105efcb73)
BibTeX
@misc{dca5ddfff4e7a5,
title = {RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks — arXiv:2610.20935},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20935},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5ddfff4e7a5; sha256 79a88ba0335a2173573da913632c531bd20e7300e2ba1c953698192105efcb73},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20935. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Engineering agents must produce artifacts that satisfy exact, coupled constraints. Existing solutions often require agents to make semantic decisions and also derive consequences such as precise geometry or timing from those decisions, leading to failures in constraint-governed engineering tasks. In this paper, we introduce RAC, a harness-agnostic contract for the action and feedback layer of engineering agents. It specifies authoritative observations, semantic actions, tool-based realization, independent verification, and repair evidence. The agent decides which relations an artifact should satisfy; specialized tools derive their concrete consequences. On PCB placement, routing, and repair tasks, RAC achieves the highest clean-pass rate for all nine evaluated models, averaging 90.9%, compared with 74.0% for the strongest baseline, requirements-only delegation. In job-shop scheduling, direct relational actions achieve 96.3% quality pass versus 59.6% for code-mediated delivery with access to the same scheduling backend. Our evaluations on 141 embedded-code tasks across four microcontroller identify the action contract as a source of agent capability: preserving semantic control while delegating mechanically derivable outputs improves the reliability of constrained artifacts. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.20935 — 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 2026-10-16T08:44:17.676Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).