analiza aiqbench
This research introduces behavioral probes to make the internal information flow of LLM swarms observable, offering new metrics for optimizing multi-agent structures beyond simple utility maximization. By repurposing existing hallucination analysis scores, the study demonstrates how monitoring context and knowledge dependence can reduce redundant communication and accelerate convergence in swarm reasoning tasks.
Behavioral Probes for Information Flow in LLM Swarms
arXiv:2610.25966v1 Announce Type: cross Abstract: 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.
Abstract: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.
Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
arXiv:2610.25966 [cs.MA]
(or arXiv:2610.25966v1 [cs.MA] for this version)
https://doi.org/10.48550/arXiv.2610.25966 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 262 cuvinte
Subiecte conexe
Scalable Attribution and Control of Model Behavior During Training
arXiv · 30 sept. 2026
Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue
arXiv · 16 sept. 2026
Beyond Similarity: Heterogeneous Graph Learning for Multi-Objective Food Substitution in Charitable Food Agencies
arXiv · 25 aug. 2026
Nudging Sustainable Choices through LLM-Generated Recommendation Explanations
arXiv · 29 iul. 2026