Metraipolis › archive › dc_c30efce9f41b
Behavioral Probes for Information Flow in LLM Swarms — arXiv:2610.25966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.25966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-20T08:41:48.744Z
- SHA-256 of the archived text
3ecd573d7ace4807f9861e0c9f9aec2c22e7d10a575e0099c066e881da098daa- Stable URL of this page
https://metraipolis.com/documento/dc_c30efce9f41b
How to cite
Behavioral Probes for Information Flow in LLM Swarms — arXiv:2610.25966 — arXiv (en), https://arxiv.org/abs/2610.25966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c30efce9f41b (Metraipolis archive dc_c30efce9f41b, sha256 3ecd573d7ace4807f9861e0c9f9aec2c22e7d10a575e0099c066e881da098daa)
BibTeX
@misc{dcc30efce9f41b,
title = {Behavioral Probes for Information Flow in LLM Swarms — arXiv:2610.25966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.25966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c30efce9f41b; sha256 3ecd573d7ace4807f9861e0c9f9aec2c22e7d10a575e0099c066e881da098daa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.25966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most existing approaches to LLM swarm optimization are utility-driven, focusing on final task utility while leaving the processing, integration, and reliance of information within individual interactions largely implicit. To address this, we study LLM swarm interactions from an information-flow-based view and introduce behavioral probes to quantify information flow patterns. Specifically, we repurpose External Context Score (ECS) and Parametric Knowledge Score (PKS)---originally designed for hallucination analysis---to measure a node's external-context dependence and parametric-knowledge dependence, respectively. Across controlled and realistic swarm settings, we observe consistent patterns: ECS increases with input relevance and distinguishes useful multi-source contributions, while PKS decreases as informative context accumulates. Building on this heuristic interpretation, we demonstrate how these probes can complement utility-driven structure optimization in two controlled applications. Probe-guided node pruning reduces redundant communication and token consumption, and probe-guided reasoning-path search accelerates convergence compared to utility-only baselines. Our empirical results suggest that behavioral probes can make the internal information flow of LLM swarms observable and serve as effective auxiliary signals for structure optimization. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.25966 — 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 2026-10-20T08:41:40.080Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).