# WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies

arXiv: https://arxiv.org/abs/2609.05591 · HTML: https://mlsanity.com/paper/2609.05591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety](https://mlsanity.com/paper/2507.06134/) (2025)
- [ABIDES: Towards High-Fidelity Market Simulation for AI Research](https://mlsanity.com/paper/1904.12066/) (2019)
- [Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity](https://mlsanity.com/paper/2602.03794/) (2026)
- [Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs](https://mlsanity.com/paper/2601.11369/) (2026)
- [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2602.15198/) (2026)
- [Group size effects and collective misalignment in LLM multi-agent systems](https://mlsanity.com/paper/2510.22422/) (2025)
- [Conformity and Social Impact on AI Agents](https://mlsanity.com/paper/2601.05384/) (2026)
- [MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook](https://mlsanity.com/paper/2602.13458/) (2026)
- [Conformity Generates Collective Misalignment in AI Agents Societies](https://mlsanity.com/paper/2605.10721/) (2026)
- [MAEBE: Multi-Agent Emergent Behavior Framework](https://mlsanity.com/paper/2506.03053/) (2025)
- [When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms](https://mlsanity.com/paper/2511.06448/) (2025)
- [Evaluating Collective Behaviour of Hundreds of LLM Agents](https://mlsanity.com/paper/2602.16662/) (2026)
- [Emergent Risks in Generative Multi-Agent Systems](https://mlsanity.com/paper/2603.27771/) (2026)
- [Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens](https://mlsanity.com/paper/2606.30755/) (2026)
- [Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities](https://mlsanity.com/paper/2604.05339/) (2026)
- [Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy](https://mlsanity.com/paper/2606.08367/) (2026)
- [Social Networks of LLM Agents](https://mlsanity.com/paper/2607.03695/) (2026)

## Abstract (arXiv)

Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which later decisions are made. We study how collective failure changes with harmful-agent fraction and society size in a controlled financial agent society, where agents communicate over a social network and trade in a shared market. In the primary financial scenario, collective failure requires broad harmful diffusion together with severe price dislocation or liquidity stress. Across all tested society sizes, failure remains rare at low harmful fractions but rises sharply over a narrow range. As society size grows from N=100 to N=2000, the harmful fraction associated with a 50% failure probability decreases from 4.7% to 2.2%, while the corresponding number of harmful agents increases from approximately 5 to 44. In contrast, when the number of harmful agents is held fixed, their impact becomes weaker as the society grows. Controlled interventions further show that broader network reach shifts the collapse boundary toward lower harmful fractions, whereas stronger conformity alone has little effect. To characterize these effects, we introduce Agent Society Dynamics, a finite-size framework for relating harmful-agent fraction, society size, and interaction structure to collective failure. Overall, our results reveal a nonlinear, size-dependent collapse transition in financial agent societies, showing that collective failure depends not only on the prevalence of harmful agents but also on the size and interaction structure of the surrounding society. Code is available at https://github.com/SAIL-Research-Lab/WolfSociety.