# From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness

arXiv: https://arxiv.org/abs/2602.12285 · HTML: https://mlsanity.com/paper/2602.12285/

## Key facts

- Cited by 3 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 6 of its 16 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, 6 of 6)

- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents](https://mlsanity.com/paper/2506.14866/) (2025)
- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)
- [DoomArena: A framework for Testing AI Agents Against Evolving Security Threats](https://mlsanity.com/paper/2504.14064/) (2025)
- [CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories](https://mlsanity.com/paper/2502.06111/) (2025)

## Built on by (most cited first, 3 of 3)

- [Personality, Role, and Expressive Style in Large Language Models: An Interactionist Analysis](https://mlsanity.com/paper/2605.28037/) (2026)
- [Set-shifting Behavioral Test for Harnessed Agents](https://mlsanity.com/paper/2607.13396/) (2026)
- [A Diagnostic Framework for AI Agent Behavior](https://mlsanity.com/paper/2607.17149/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation. While persona-induced biases in text generation are well documented, their effects on agent task performance remain largely unexplored, even though such effects pose more direct operational risks. In this work, we present the first systematic case study showing that demographic-based persona assignments can alter LLM agents' behavior and degrade performance across diverse domains. Evaluating widely deployed models on agentic benchmarks spanning strategic reasoning, planning, and technical operations, we uncover substantial performance variations - up to 26.2% degradation, driven by task-irrelevant persona cues. These shifts appear across task types and model architectures, indicating that persona conditioning and simple prompt injections can distort an agent's decision-making reliability. Our findings reveal an overlooked vulnerability in current LLM agentic systems: persona assignments can introduce implicit biases and increase behavioral volatility, raising concerns for the safe and robust deployment of LLM agents.