# Small-world Networks of Agents Brainstorm AI Risks to Support Ideation

arXiv: https://arxiv.org/abs/2609.24859 · HTML: https://mlsanity.com/paper/2609.24859/

## 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 18 of its 58 references that are in the map.
- First posted on arXiv 21 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, 18 of 18)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [MART: Improving LLM Safety with Multi-round Automatic Red-Teaming](https://mlsanity.com/paper/2311.07689/) (2023)
- [Power to the People? Opportunities and Challenges for Participatory AI](https://mlsanity.com/paper/2209.07572/) (2022)
- [The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practice](https://mlsanity.com/paper/2310.00907/) (2023)
- [The Effects of Generative AI on Design Fixation and Divergent Thinking](https://mlsanity.com/paper/2403.11164/) (2024)
- [CreativeConnect: Supporting Reference Recombination for Graphic Design Ideation with Generative AI](https://mlsanity.com/paper/2312.11949/) (2023)
- [Farsight: Fostering Responsible AI Awareness During AI Application Prototyping](https://mlsanity.com/paper/2402.15350/) (2024)
- [AHA!: Facilitating AI Impact Assessment by Generating Examples of Harms](https://mlsanity.com/paper/2306.03280/) (2023)
- [Algorithmic Auditing and Social Justice: Lessons from the History of Audit Studies](https://mlsanity.com/paper/2109.06974/) (2021)
- [How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment](https://mlsanity.com/paper/2401.13481/) (2024)
- [Plurals: A System for Guiding LLMs Via Simulated Social Ensembles](https://mlsanity.com/paper/2409.17213/) (2024)
- [AI-generated faces influence gender stereotypes and racial homogenization](https://mlsanity.com/paper/2402.01002/) (2024)
- [WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI](https://mlsanity.com/paper/2501.01397/) (2025)
- [AIdeation: Designing a Human-AI Collaborative Ideation System for Concept Designers](https://mlsanity.com/paper/2502.14747/) (2025)
- [ExploreGen: Large Language Models for Envisioning the Uses and Risks of AI Technologies](https://mlsanity.com/paper/2407.12454/) (2024)
- [A Taxonomy of Systemic Risks from General-Purpose AI](https://mlsanity.com/paper/2412.07780/) (2024)
- [When and How AI Should Assist Brainstorming for AI Impact Assessment](https://mlsanity.com/paper/2604.27997/) (2026)

## Abstract (arXiv)

The ideation phase of participatory AI risk assessment often starts with a blank slate or a limited list of predefined risks, making it difficult to surface indirect or systemic harms. To address this limitation, we propose a three-stage ideation support tool. The tool complements participatory AI, rather than replacing it, and helps focus later engagement with affected communities. First, it dynamically discovers stakeholders depending on the given AI use and recursively expanding outward, allowing overlooked or indirect stakeholders to emerge. Second, it simulates these stakeholders with LLMs, connecting them into a network of a given topology, and having them ideate about risks. Third, it prioritizes risks using network centrality measures. In an initial evaluation, we found that betweenness centrality run through agents connected in a small-world network works best as it elevates risks raised by stakeholders who bridge disconnected groups, surfacing novel, systemic harms that traditional methods often miss. On an AI chatbot companion use case, this approach increased the novelty of the identified risks by approximately 1.1 points over single LLM brainstorming, and by 0.5 points over agentic LLM brainstorming, measured on a normalized five-point Likert scale, without reducing the plausibility or severity of the identified risks. To test whether our framework helps a human-led ideation session using the Futures Wheel approach, we divided 11 teams of non-western young chatbot users into two types: control (team) and treatment (team) in a participatory AI risk assessment. The control teams started from a list of risks generated by the 45 AI practitioners in the initial evaluation; the treatment teams started from a list generated by our framework. The treatment teams identified more risks overall, and more systemic, human-computer interaction, and environmental risks.