# Exploring Implicit Perspectives on Autism in Large Language Models Through Multi-Agent Simulations

arXiv: https://arxiv.org/abs/2601.15437 · HTML: https://mlsanity.com/paper/2601.15437/

## 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 19 of its 89 references that are in the map.
- First posted on arXiv 21 Jan 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, 19 of 19)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [AgentSims: An Open-Source Sandbox for Large Language Model Evaluation](https://mlsanity.com/paper/2308.04026/) (2023)
- [Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena](https://mlsanity.com/paper/2310.05746/) (2023)
- ["I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation](https://mlsanity.com/paper/2305.09941/) (2023)
- [A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application](https://mlsanity.com/paper/2412.17481/) (2024)
- [MuMA-ToM: Multi-modal Multi-Agent Theory of Mind](https://mlsanity.com/paper/2408.12574/) (2024)
- [Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions](https://mlsanity.com/paper/2410.02584/) (2024)
- [Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictions](https://mlsanity.com/paper/2407.05271/) (2024)
- [Unmasking Conversational Bias in AI Multiagent Systems](https://mlsanity.com/paper/2501.14844/) (2025)
- [What Do We Mean by "Accessibility Research"? A Literature Survey of Accessibility Papers in CHI and ASSETS from 1994 to 2019](https://mlsanity.com/paper/2101.04271/) (2021)
- ["It's the only thing I can trust": Envisioning Large Language Model Use by Autistic Workers for Communication Assistance](https://mlsanity.com/paper/2403.03297/) (2024)
- [AACessTalk: Fostering Communication between Minimally Verbal Autistic Children and Parents with Contextual Guidance and Card Recommendation](https://mlsanity.com/paper/2409.09641/) (2024)
- [Reimagining Support: Exploring Autistic Individuals' Visions for AI in Coping with Negative Self-Talk](https://mlsanity.com/paper/2503.17504/) (2025)
- [Exploring outlooks towards generative AI-based assistive technologies for people with Autism](https://mlsanity.com/paper/2305.09815/) (2023)

## Abstract (arXiv)

Large Language Models (LLMs) like ChatGPT offer potential support for autistic people, but this potential requires understanding the implicit perspectives these models might carry, including their biases and assumptions about autism. Moving beyond single-agent prompting, we utilized LLM-based multi-agent systems to investigate complex social scenarios involving autistic and non-autistic agents. In our study, agents engaged in group-task conversations and answered structured interview questions, which we analyzed to examine ChatGPT's biases and how it conceptualizes autism. We found that ChatGPT assumes autistic people are socially dependent, which may affect how it interacts with autistic users or conveys information about autism. To address these challenges, we propose adopting the double empathy problem, which reframes communication breakdowns as a mutual challenge. We describe how future LLMs could address the biases we observed and improve interactions involving autistic people by incorporating the double empathy problem into their design.