Representational Similarity and Model Behavior in Multi-Agent Interaction
This work provides empirical evidence for the role of representational similarity in multi-agent AI systems, offering design insights for balancing cooperation and innovation.
The study investigates how representational similarity between large language models affects cooperation and novelty in multi-agent interactions across eight games. Results show that higher similarity leads to significantly better cooperation but reduced novelty and creativity, with early-layer similarity being most predictive.
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.