Metraipolis › archive › dc_30b4e1cf4037
Containing Behavioral Cascades from Manipulated Claims in LLM-Powered Multi-Robot Systems — arXiv:2609.30523
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30523
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T03:14:42.872Z
- SHA-256 of the archived text
8c0638c6c7522790d506aee95dbd8b7149f987381f1e817e816c8653b1647583- Stable URL of this page
https://metraipolis.com/documento/dc_30b4e1cf4037
How to cite
Containing Behavioral Cascades from Manipulated Claims in LLM-Powered Multi-Robot Systems — arXiv:2609.30523 — arXiv (en), https://arxiv.org/abs/2609.30523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30b4e1cf4037 (Metraipolis archive dc_30b4e1cf4037, sha256 8c0638c6c7522790d506aee95dbd8b7149f987381f1e817e816c8653b1647583)
BibTeX
@misc{dc30b4e1cf4037,
title = {Containing Behavioral Cascades from Manipulated Claims in LLM-Powered Multi-Robot Systems — arXiv:2609.30523},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30523},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30b4e1cf4037; sha256 8c0638c6c7522790d506aee95dbd8b7149f987381f1e817e816c8653b1647583},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM)-powered multi-robot systems are vulnerable to semantic manipulation: an accepted false world-state claim can trigger a fleet-wide behavioral cascade, causing unnecessary replanning, increased path costs, congestion, or apparent mission infeasibility. Conditioning on a successful manipulation, we propose an active verification framework that contains its downstream effects before they propagate across the fleet. A dedicated verification module generates a structured Verify-Adapt-Hold plan: selected robots inspect consequential regions, a limited subset provisionally adapts when necessary, and the remaining robots retain their trusted plans. We evaluate the framework in a multi-robot transportation environment using injected false obstacle claims across different impacts and team sizes. Evaluation measures cascade containment, Sum-of-Costs, makespan, and coverage ratio. Results show that treating post-compromise verification as a team-level planning problem, rather than a binary trust decision, effectively limits the cascading physical consequences of semantic manipulation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.30523 — 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 2026-10-08T02:58:08.798Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).