# LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems

arXiv: https://arxiv.org/abs/2609.33495 · HTML: https://mlsanity.com/paper/2609.33495/

## Key facts

- Cited by 1 papers in the map (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 31 of its 58 references that are in the map.
- First posted on arXiv 27 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, 30 of 31)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [Do as We Do, Not as You Think: the Conformity of Large Language Models](https://mlsanity.com/paper/2501.13381/) (2025)
- [Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View](https://mlsanity.com/paper/2405.14744/) (2024)
- [Conformity in Large Language Models](https://mlsanity.com/paper/2410.12428/) (2024)
- [AI-AI Bias: large language models favor communications generated by large language models](https://mlsanity.com/paper/2407.12856/) (2024)
- [LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions](https://mlsanity.com/paper/2508.18321/) (2025)
- [Conformity and Social Impact on AI Agents](https://mlsanity.com/paper/2601.05384/) (2026)
- [Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories](https://mlsanity.com/paper/2509.16742/) (2025)
- [Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity](https://mlsanity.com/paper/2606.01637/) (2026)
- [From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions](https://mlsanity.com/paper/2511.11789/) (2025)
- [Disentangling the Drivers of LLM Social Conformity: An Uncertainty-Moderated Dual-Process Mechanism](https://mlsanity.com/paper/2508.14918/) (2025)
- [Large Language Models Exhibit Normative Conformity](https://mlsanity.com/paper/2604.19301/) (2026)
- [From Simulation to Enaction: Post-trained language models recognize and react to their own generations](https://mlsanity.com/paper/2605.25459/) (2026)
- [I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models](https://mlsanity.com/paper/2402.10436/) (2024)
- [Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation](https://mlsanity.com/paper/2405.03862/) (2024)
- [When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents](https://mlsanity.com/paper/2601.00240/) (2026)
- [Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents](https://mlsanity.com/paper/2605.01329/) (2026)
- [Language model agents show in-group trust bias invisible to standard behavioural audits](https://mlsanity.com/paper/2605.28114/) (2026)
- [Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations](https://mlsanity.com/paper/2608.22444/) (2026)

## Built on by (most cited first, 1 of 1)

- [Anatomy of LLM Sycophancy: What a Flip Rate Hides](https://mlsanity.com/paper/2610.06522/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed in multi-agent settings, where agents observe and influence one another, making social influence a key dimension of AI behavior and safety. We investigate whether LLMs' responses depend on the social identity of other agents, beyond the effect of their consensus. We construct judgment tasks with a single correct answer, and place models in a multi-agent setting where they receive incorrect answers from other agents whose social identities (AI or human, model family, or an arbitrary minimal group) are either shared with or distinct from their own. Across 12 open-weights models and nine tasks, we find a bidirectional effect of group identity on conformity to incorrect answers: in-group consensus increases conformity (in-group favoritism), whereas out-group consensus decreases it (out-group divergence). Unlike humans, for whom one ally breaking the consensus sharply reduces conformity, models are unmoved by an ally from the majority's group. Worse, a correct ally from the opposing group intensifies this bidirectional effect. Chain-of-Thought reasoning suppresses most of these effects, yet an in-group ally still reduces conformity to an incorrect out-group majority. Labeling peers as safety-aligned shifts overall conformity but leaves in-group favoritism and out-group divergence intact. These results show that group identity shapes how LLMs aggregate information across agents, independently of its correctness, and identify a manipulation surface for multi-agent AI systems.