Metraipolis › archive › dc_f33c5682c124
AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation — arXiv:2610.06481
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06481
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:28:33.802Z
- SHA-256 of the archived text
94a3a2ea29002662cd9c5bc52386899370f416578805255800c3de818febf702- Stable URL of this page
https://metraipolis.com/documento/dc_f33c5682c124
How to cite
AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation — arXiv:2610.06481 — arXiv, https://arxiv.org/abs/2610.06481 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f33c5682c124 (Metraipolis archive dc_f33c5682c124, sha256 94a3a2ea29002662cd9c5bc52386899370f416578805255800c3de818febf702)
BibTeX
@misc{dcf33c5682c124,
title = {AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation — arXiv:2610.06481},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06481},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f33c5682c124; sha256 94a3a2ea29002662cd9c5bc52386899370f416578805255800c3de818febf702},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06481. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As AI agents increasingly tackle complex repository-level coding tasks, distributing work across multiple agents is a natural way to scale beyond the capabilities of a single agent. To coordinate their interdependent work, these agents share findings and agree on interfaces between modules. However, exchanged information often serves only as context, leaving individual agents to interpret it and incorporate it into subsequent work. Consequently, shared findings may go unused and deviations from interface agreements may go undetected, undermining the reliability and efficiency of collaboration. This motivates moving part of the coordination responsibility from individual agents to the execution harness. To make shared information actionable during execution, we introduce the Artifact-Exclusive Communication Protocol (AECP). AECP requires agents to communicate exclusively through structured artifacts and specifies how the harness processes them. The harness supplies findings when agents access relevant code, screens implementations for mismatches with recorded interface commitments, and requires affected agents to revisit revised agreements. These coordination steps become part of harness execution rather than actions that agents must initiate from prior messages. Across Doc2Repo, NL2Repo, and CodeProjectEval, using closed- and open-source models including Opus-4.8 and DeepSeek-V4-Flash, AECP improves average test pass rate by 28.2% and reduces average wall time by 16.5% relative to an agent team using free-form inter-agent messages. Artifact-exclusive communication also blocks the relay of malicious instructions between agents, reducing how often they reach other agents from 95% to 0% and how often those agents act on them from 40% to 0%. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.06481 — 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 2026-10-06T05:24:20.373Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).