Metraipolis › archive › dc_147e7be2d5dd
Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development — arXiv:2609.25396
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25396
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:46:18.245Z
- SHA-256 of the archived text
b93941582f78f4a00d12342d4549ff451dfbaca76c96f698cc5a249bbcf0ddd0- Stable URL of this page
https://metraipolis.com/documento/dc_147e7be2d5dd
How to cite
Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development — arXiv:2609.25396 — arXiv (en), https://arxiv.org/abs/2609.25396 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_147e7be2d5dd (Metraipolis archive dc_147e7be2d5dd, sha256 b93941582f78f4a00d12342d4549ff451dfbaca76c96f698cc5a249bbcf0ddd0)
BibTeX
@misc{dc147e7be2d5dd,
title = {Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development — arXiv:2609.25396},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25396},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_147e7be2d5dd; sha256 b93941582f78f4a00d12342d4549ff451dfbaca76c96f698cc5a249bbcf0ddd0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25396. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Parallel coding agents can produce patches that work alone but fail when merged. This happens when one agent changes an interface or rule that another agent still relies on. We study these failures with stale, a benchmark for semantic coordination. Our evaluation runs the same tests on each patch alone and on their combination, counting only failures introduced by combining the patches. We use three tiers: synthetic tasks with controlled interface changes, pairs of merged pull requests, and constructed tasks that use real Django helpers. Among 834 runs on 417 mined Django pairs, only one showed interference after correcting the grading procedure. On constructed tasks using 12 Django helpers, interference occurred in 97% of runs. A message describing the completed concurrent change recovered 82% of runs. Reviewed pull requests may contain few unresolved parallel changes, even when agents fail on controlled tasks using real code. The constructed failure rates do not estimate how often these problems occur in practice. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.25396 — 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 2026-10-08T13:18:38.222Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).