# Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents

arXiv: https://arxiv.org/abs/2608.16578 · HTML: https://mlsanity.com/paper/2608.16578/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 76 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2504.00587/) (2025)
- [Learning to Orchestrate Agents in Natural Language with the Conductor](https://mlsanity.com/paper/2512.04388/) (2025)
- [Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions](https://mlsanity.com/paper/2505.17479/) (2025)
- [Structured Scaling of AI Discovery Across Diverse Scientific Domains](https://mlsanity.com/paper/2604.19341/) (2026)
- [Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries](https://mlsanity.com/paper/2606.10402/) (2026)
- [Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem](https://mlsanity.com/paper/2509.04537/) (2025)
- [When Is Collective Intelligence a Lottery? Multi-Agent Scaling Laws for Memetic Drift in LLMs](https://mlsanity.com/paper/2603.24676/) (2026)
- [Emergence of Biased Consensus in Multi-Agent LLM Debates](https://mlsanity.com/paper/2608.02827/) (2026)

## Built on by (most cited first, 6 of 6)

- [When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis](https://mlsanity.com/paper/2609.15309/) (2026)
- [Message capacity and claim wording set the transition points of collective truth-finding in language-model networks](https://mlsanity.com/paper/2609.19183/) (2026)
- [Local Predictability and Collective Fidelity in LLM-Agent Societies](https://mlsanity.com/paper/2609.35813/) (2026)
- [From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs](https://mlsanity.com/paper/2609.38516/) (2026)
- [Verification Pulses and the Cost of Escaping Wrong Consensus](https://mlsanity.com/paper/2610.00256/) (2026)
- [Homogenization in Multi-Agent Systems](https://mlsanity.com/paper/2610.09824/) (2026)

## Abstract (arXiv)

AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii) agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI agents, like that of other complex systems, follows compact and predictive dynamical laws.