# Local Predictability and Collective Fidelity in LLM-Agent Societies

arXiv: https://arxiv.org/abs/2609.35813 · HTML: https://mlsanity.com/paper/2609.35813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 5 of 5)

- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [On the limits of agency in agent-based models](https://mlsanity.com/paper/2409.10568/) (2024)
- [Coupling Macro Dynamics and Micro States for Long-Horizon Social Simulation](https://mlsanity.com/paper/2604.05516/) (2026)
- [Modeling Earth-Scale Human-Like Societies with One Billion Agents](https://mlsanity.com/paper/2506.12078/) (2025)
- [Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents](https://mlsanity.com/paper/2608.16578/) (2026)

## Abstract (arXiv)

Compact surrogates could reduce the cost of simulating large language model societies, but must reproduce collective behavior. We compare individual predictions and collective forecasts using 9,455 published trajectories and new experiments on opinion dynamics. Neighbor information improves individual prediction in all 16 public-data settings and pooled collective forecasts on held-out questions, although collective gains depend on transfer conditions. Tests on 24 new statements do not confirm earlier contrasting history effects in forecasts from the initial state. Qwen benefits from history after three observed rounds. These findings motivate direct collective validation, explicit limits on available observations, and comparisons with simple baselines.