# Detecting Perspective Shifts in Multi-agent Systems

arXiv: https://arxiv.org/abs/2512.05013 · HTML: https://mlsanity.com/paper/2512.05013/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 50 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 17 of 17)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [Multi-Agent Consensus Seeking via Large Language Models](https://mlsanity.com/paper/2310.20151/) (2023)
- [Multi-Agent Coordination across Diverse Applications: A Survey](https://mlsanity.com/paper/2502.14743/) (2025)
- [Network Formation and Dynamics Among Multi-LLMs](https://mlsanity.com/paper/2402.10659/) (2024)
- [Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models](https://mlsanity.com/paper/2410.04207/) (2024)
- [Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents](https://mlsanity.com/paper/2502.13012/) (2025)
- [Tracking the perspectives of interacting language models](https://mlsanity.com/paper/2406.11938/) (2024)
- [Consistent estimation of generative model representations in the data kernel perspective space](https://mlsanity.com/paper/2409.17308/) (2024)
- [Statistical inference on black-box generative models in the data kernel perspective space](https://mlsanity.com/paper/2410.01106/) (2024)
- [Mental State Classification Using Multi-graph Features](https://mlsanity.com/paper/2203.00516/) (2022)
- [Investigating social alignment via mirroring in a system of interacting language models](https://mlsanity.com/paper/2412.06834/) (2024)
- [Universally Consistent K-Sample Tests via Dependence Measures](https://mlsanity.com/paper/1910.08883/) (2019)
- [Gaussian mixture models as a proxy for interacting language models](https://mlsanity.com/paper/2506.00077/) (2025)
- [Toward a digital twin of U.S. Congress](https://mlsanity.com/paper/2505.00006/) (2025)

## Built on by (most cited first, 4 of 4)

- [Distributional AGI Safety](https://mlsanity.com/paper/2512.16856/) (2025)
- [Control Charts for Multi-agent Systems](https://mlsanity.com/paper/2605.11135/) (2026)
- [Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models](https://mlsanity.com/paper/2605.26409/) (2026)
- [The Contagion Tensor: A Framework for Measuring Output-Distribution Coupling in Multi-Agent LLM Systems -- and Auditing the Claims It Enables](https://mlsanity.com/paper/2606.28839/) (2026)

## Abstract (arXiv)

Generative models augmented with external tools and update mechanisms (or textitagents) have demonstrated capabilities beyond intelligent prompting of base models. As agent use proliferates, dynamic multi-agent systems have naturally emerged. Recent work has investigated the theoretical and empirical properties of low-dimensional representations of agents based on query responses at a single time point. This paper introduces the Temporal Data Kernel Perspective Space (TDKPS), which jointly embeds agents across time, and proposes several novel hypothesis tests for detecting behavioral change at the agent- and group-level in black-box multi-agent systems. We characterize the empirical properties of our proposed tests, including their sensitivity to key hyperparameters, in simulations motivated by a multi-agent system of evolving digital personas. Finally, we demonstrate via natural experiment that our proposed tests detect changes that correlate sensitively, specifically, and significantly with a real exogenous event. As far as we are aware, TDKPS is the first principled framework for monitoring behavioral dynamics in black-box multi-agent systems -- a critical capability as generative agent deployment continues to scale.