Representational Similarity and Model Behavior in Multi-Agent Interaction

• URL: http://arxiv.org/abs/2606.07818v1
• Date: Fri, 05 Jun 2026 19:59:17 GMT
• Title: Representational Similarity and Model Behavior in Multi-Agent Interaction
• Abstract summary: We show that representational similarity can be an important consideration in multi-agent system design.<n>We find that pairs with more similar representation spaces achieve significantly higher cooperation but exhibit reduced novelty and creativity.<n>This suggests that a central factor underlying these patterns could be the extent to which the two models share lexical and semantic grounding.
• Score: 86.305731341492
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Researchers have shown that neural similarity among humans predicts social closeness and cooperative success, whereas innovation often emerges from interactions among dissimilar individuals. We investigate whether these principles extend to artificial intelligence by examining interactions between large language models. In our experiments, 276 model pairs interact across eight games spanning both cooperation and novelty. We find that pairs with more similar representation spaces achieve significantly higher cooperation but exhibit reduced novelty and creativity. The effects of representational similarity on cooperation and novelty remain robust even after controlling for other factors such as performance disparity and model size. We also find that similarity in the early layers consistently shows the strongest association with cooperation and novelty, compared to the middle and later layers. This suggests that a central factor underlying these patterns could be the extent to which the two models share lexical and semantic grounding. Overall, representational similarity can be an important consideration in multi-agent system design.

Related papers

• A game theory for foundation models shows new paths to rational cooperation through similarity inference [56.53805518668248]
  We show that foundation model agents engaging in optimal planning consistently converge to stable cooperation.<n>By shifting from decoupled to embedded agency, these agents model themselves as part of the universe they inhabit.
  arXiv  Detail & Related papers  (2026-08-04T17:24:33Z)
• Barycentric alignment for instance-level comparison of neural representations [2.1920579994942164]
  We introduce a barycentric alignment framework that quotients out nuisance symmetries to construct a universal embedding space across many models.<n>We identify systematic input properties that predict representational convergence versus divergence across vision and language model families.<n>We also apply the same barycentric alignment framework to purely unimodal vision and language models and find that post-hoc alignment into a shared space yields image text similarity scores.
  arXiv  Detail & Related papers  (2026-02-09T21:49:44Z)
• Causes and Consequences of Representational Similarity in Machine Learning Models [4.878152686480212]
  This work explores how two factors - dataset overlap and task overlap - influence downstream model similarity.<n>We find that both task and dataset overlap cause higher representational similarity and that combining them provides the strongest effect.
  arXiv  Detail & Related papers  (2025-05-20T04:03:11Z)
• Behavior-Inspired Neural Networks for Relational Inference [6.855586051080836]
  We study how interactions between agents govern how dynamical systems evolve in space and time.<n>Recent works learn to categorize relationships between agents based on observations of their physical behavior.<n>We introduce a level of abstraction between the observable behavior of agents and the latent categories that determine their behavior.
  arXiv  Detail & Related papers  (2024-06-20T21:36:54Z)
• Scaling Large Language Model-based Multi-Agent Collaboration [72.8998796426346]
  Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning.<n>This study explores whether the continuous addition of collaborative agents can yield similar benefits.
  arXiv  Detail & Related papers  (2024-06-11T11:02:04Z)
• Predictive Churn with the Set of Good Models [61.00058053669447]
  This paper explores connections between two seemingly unrelated concepts of predictive inconsistency.<n>The first, known as predictive multiplicity, occurs when models that perform similarly produce conflicting predictions for individual samples.<n>The second concept, predictive churn, examines the differences in individual predictions before and after model updates.
  arXiv  Detail & Related papers  (2024-02-12T16:15:25Z)
• Similarity of Neural Network Models: A Survey of Functional and Representational Measures [2.56552999376511]
  Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest.<n>We provide a comprehensive overview of two complementary perspectives of measuring neural network similarity: (i) representational similarity, which considers how activations of intermediate layers differ, and (ii) functional similarity, which considers how models differ in their outputs.
  arXiv  Detail & Related papers  (2023-05-10T17:33:48Z)
• Similarity of Neural Architectures using Adversarial Attack Transferability [47.66096554602005]
  We design a quantitative and scalable similarity measure between neural architectures. We conduct a large-scale analysis on 69 state-of-the-art ImageNet classifiers. Our results provide insights into why developing diverse neural architectures with distinct components is necessary.
  arXiv  Detail & Related papers  (2022-10-20T16:56:47Z)
• Multi-Agent Imitation Learning with Copulas [102.27052968901894]
  Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents.
  arXiv  Detail & Related papers  (2021-07-10T03:49:41Z)
• A mechanism of Individualistic Indirect Reciprocity with internal and external dynamics [0.0]
  This research proposes a new variant of Nowak and Sigmund model, focused on agents' attitude. Using Agent-Based Model and a Data Science method, we show on simulation results that the discriminatory stance of the agents prevails in most cases. The results also show that when the reputation of others is unknown, with a high obstinacy and high cooperation demand, a heterogeneous society is obtained.
  arXiv  Detail & Related papers  (2021-05-28T23:28:50Z)
• Action similarity judgment based on kinematic primitives [48.99831733355487]
  We investigate to which extent a computational model based on kinematics can determine action similarity. The chosen model has its roots in developmental robotics and performs action classification based on learned kinematic primitives. The results show that both the model and human performance are highly accurate in an action similarity task based on kinematic-level features.
  arXiv  Detail & Related papers  (2020-08-30T13:58:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.