Metraipolis › archive › dc_f5d15fb9aa87

When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems — arXiv:2608.03421

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03421
License (as archived)
CC0-1.0
Archived
2026-10-31T12:14:34.960Z
SHA-256 of the archived text
79b4f600355bf76627c0193bb35591ae25e2e7168a45150ac673c39cef72967e
Stable URL of this page
https://metraipolis.com/documento/dc_f5d15fb9aa87

How to cite

When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems — arXiv:2608.03421 — arXiv (en), https://arxiv.org/abs/2608.03421 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5d15fb9aa87 (Metraipolis archive dc_f5d15fb9aa87, sha256 79b4f600355bf76627c0193bb35591ae25e2e7168a45150ac673c39cef72967e)
BibTeX
@misc{dcf5d15fb9aa87,
  title = {When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems — arXiv:2608.03421},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03421},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5d15fb9aa87; sha256 79b4f600355bf76627c0193bb35591ae25e2e7168a45150ac673c39cef72967e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03421. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based multi-agent systems promise effective collaborative reasoning, but communication may amplify local errors into collective risks, and while existing evaluations emphasize final outcomes, they leave the reliability and propagation dynamics of distributed information aggregation unclear, so we introduce ForesightSafety-TIDE, a controlled evaluation framework that strictly pairs all-honest collaboration with controlled deception by a key evidence holder and analyzes the aggregation process through multi-stage voting, testimony adoption, and evidence-root lineage propagation, and using 120 five-agent object-movement environments where partial observations jointly determine a unique endpoint, we evaluate 3 homogeneous LLM-based multi-agent systems, and across these paired conditions, aggregate truth recovery falls from 72.50% to 14.17%, with significant declines for every system, while process tracing and exit ablations show that a single false testimony is adopted more readily than truthful testimony, propagates to higher orders, and persists through honest agents after the deceiver exits, and observers without first-hand evidence suppress incorrect consensus but do not improve truth recovery, so together, these findings reveal both the fragility of distributed fact recovery and its underlying mechanism: false evidence gains collective influence through its adoption and continued propagation by other agents after entering communication.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.03421 — 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 2026-10-31T12:05:27.214Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).