Measuring Emergent Coordination in Multi-Agent LLMs via Information Decomposition

This episode examines a 2026 ICLR paper that asks whether groups of LLM agents form genuine collectives or are just aggregates of individuals. Ten GPT-4.1 agents play a group binary search game, each privately guessing a number so the total hits a hidden target while seeing only "too high" or "too low" feedback. The only way to succeed is to take complementary offsets, since identical strategies make the group overshoot and undershoot in a loop. The hosts explain partial information decomposition, which splits information into unique, redundant, and synergistic parts. They note that the results depend on which redundancy definition is chosen, and that the leading alternative measure isn't reported. They also walk through the three prompt conditions (plain, persona, and persona plus a one-sentence theory-of-mind nudge), the emergence and coalition tests applied to short trajectories, and the statistical tension between Fisher's method and Wilcoxon tests. Listeners get a skeptical look at how much evidence supports the claim that prompting can turn a group of agents into a higher-order collective.

Sources:

1. Emergent Coordination in Multi-Agent Language Models — Christoph Riedl, 2025

http://arxiv.org/abs/2510.05174

2. Nonnegative Decomposition of Multivariate Information — Paul L. Williams, Randall D. Beer, 2010

https://scholar.google.com/scholar?q=Nonnegative+Decomposition+of+Multivariate+Information

3. Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate data — Fernando E. Rosas, Pedro A. M. Mediano, Henrik J. Jensen, Anil K. Seth, Adam B. Barrett, Robin L. Carhart-Harris, Daniel Bor, 2020

https://scholar.google.com/scholar?q=Reconciling+emergences%3A+An+information-theoretic+approach+to+identify+causal+emergence+in+multivariate+data

4. Greater than the parts: a review of the information decomposition approach to causal emergence — Pedro A. M. Mediano, Fernando E. Rosas, Andrea I. Luppi, Robin L. Carhart-Harris, Daniel Bor, Anil K. Seth, Adam B. Barrett, 2022

https://scholar.google.com/scholar?q=Greater+than+the+parts%3A+a+review+of+the+information+decomposition+approach+to+causal+emergence

5. Quantifying High-order Interdependencies via Multivariate Extensions of the Mutual Information — Fernando E. Rosas, Pedro A. M. Mediano, Michael Gastpar, Henrik J. Jensen, 2019

https://scholar.google.com/scholar?q=Quantifying+High-order+Interdependencies+via+Multivariate+Extensions+of+the+Mutual+Informatio