Abstract:When are multi-agent LLM systems merely a collection of individual agents versus an integrated collective with higher-order structure? We introduce an information-theoretic framework to test -- in a purely data-driven way -- whether multi-agent systems show signs of higher-order structure. This information decomposition lets us measure whether dynamical emergence is present in multi-agent LLM systems, localize it, and distinguish spurious temporal coupling from performance-relevant cross-agent synergy. We implement a practical criterion and an emergence capacity criterion operationalized as partial information decomposition of time-delayed mutual information (TDMI). We apply our framework to experiments using a simple guessing game without direct agent communication and minimal group-level feedback with three randomized interventions. Groups in the control condition exhibit strong temporal synergy but little coordinated alignment across agents. Assigning a persona to each agent introduces stable identity-linked differentiation. Combining personas with an instruction to ``think about what other agents might do'' shows identity-linked differentiation and goal-directed complementarity across agents. Taken together, our framework establishes that multi-agent LLM systems can be steered with prompt design from mere aggregates to higher-order collectives. Our results are robust across emergence measures and entropy estimators, and not explained by coordination-free baselines or temporal dynamics alone. Without attributing human-like cognition to the agents, the patterns of interaction we observe mirror well-established principles of collective intelligence in human groups: effective performance requires both alignment on shared objectives and complementary contributions across members.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2; I.2.11 |
| Cite as: | arXiv:2510.05174 [cs.MA] |
| (or arXiv:2510.05174v4 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2510.05174 arXiv-issued DOI via DataCite |
Submission history
From: Christoph Riedl [view email]
[v1]
Sun, 5 Oct 2025 11:26:41 UTC (840 KB)
[v2]
Fri, 27 Feb 2026 21:22:32 UTC (930 KB)
[v3]
Sun, 15 Mar 2026 14:32:20 UTC (928 KB)
[v4]
Tue, 28 Apr 2026 21:26:55 UTC (928 KB)