Metraipolis › archive › dc_3ac458cb33df

When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration — arXiv:2609.36855

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.36855
License (as archived): CC0-1.0
Archived: 2026-10-07T16:23:09.145Z
SHA-256 of the archived text: fb0c22df20d20faa10d565239592e38d6e24cc56545ecf6fc7fe146a8c01f360
Stable URL of this page: https://metraipolis.com/documento/dc_3ac458cb33df

How to cite

When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration — arXiv:2609.36855 — arXiv (en), https://arxiv.org/abs/2609.36855 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ac458cb33df (Metraipolis archive dc_3ac458cb33df, sha256 fb0c22df20d20faa10d565239592e38d6e24cc56545ecf6fc7fe146a8c01f360)

BibTeX

@misc{dc3ac458cb33df,
  title = {When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration — arXiv:2609.36855},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36855},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ac458cb33df; sha256 fb0c22df20d20faa10d565239592e38d6e24cc56545ecf6fc7fe146a8c01f360},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36855. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful information or an incorrect answer that causes a downstream agent to override a correct answer supported by its own evidence. Prior work has not clearly separated the benefits of communication from the damage caused by incorrect messages. We study this problem with controlled experiments across five benchmarks and five receivers, keeping the downstream task and evidence fixed while comparing answers under three conditions: no message, the upstream agent's original message, or a message with the opposite conclusion. Our experiments reveal three key findings. First, messages often help when the downstream agent would otherwise answer incorrectly. Second, messages can also hurt: when the downstream agent would answer correctly without a message, an incorrect upstream message changes the answer in up to 32% of cases. Third, in 94% of audited harmful cases, the downstream agent copies the upstream's specific wrong answer--a pattern we term answer substitution. Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream agent.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36855 — 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 2026-10-07T15:54:53.554Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).