Collective Cognition in Hybrid Groups: A Network Science Synthesis

Summary

Synthesises network science, collective cognition and multi-agent systems, reviewing how task environments, group topologies, agent-level processes and incentive structures shape collective outcomes in human-only and AI-only networks and asking which findings survive the move to hybrid groups. It explicitly discusses how established exploration-exploitation and efficiency-redundancy trade-offs may operate differently once agents are LLMs, and closes on implications for organizational design and governance. Useful as a bridging citation between the organizational-design canon the paper builds on and the network-science literature, and as an existing statement that classical topology results need revision for LLM agents.

Contribution

Queued — not yet read.

Method

Queued — not yet read.

Relevance to RISE

Surfaced by the 2026-08-29 literature sweep as a medium-priority candidate for the Architecture as Epistemology (ISR) paper (angle: organization theory applied to AI agents; MAS topology / structure vs. aggregation rule; epistemic quality of LLM outputs). Verified against: Opened https://arxiv.org/abs/2607.05593 (arXiv abstract page, v1 6 Jul 2026)

Critique / open questions

Queued — not yet assessed.

Key quotes

The growing integration of AI agents into human teams calls for a principled understanding of how collective intelligence emerges in hybrid systems. (abstract)

Recent frameworks clarify how attention, memory, and reasoning differences shape human-AI interaction at the individual and dyadic levels, but a formal account of how these differences scale to group-level dynamics is lacking. (abstract)