![[2602.12285] From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.12285] From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness
Summary
This article examines how demographic-based persona assignments in large language models (LLMs) can impact agent performance, revealing vulnerabilities in their deployment.
Why It Matters
Understanding the effects of persona-induced biases on LLM agents is crucial for ensuring their safe and reliable deployment in real-world applications. This research highlights significant performance degradation caused by biased role assignments, raising concerns about operational risks in AI systems.
Key Takeaways
- Demographic-based persona assignments can significantly degrade LLM agent performance.
- Performance variations of up to 26.2% were observed due to task-irrelevant persona cues.
- The study reveals vulnerabilities in LLM agents that could lead to biased decision-making.
- Persona conditioning and prompt injections can distort agent reliability.
- The findings emphasize the need for careful consideration in the deployment of LLM agents.
Computer Science > Computation and Language arXiv:2602.12285 (cs) [Submitted on 21 Jan 2026] Title:From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness Authors:Linbo Cao, Lihao Sun, Yang Yue View a PDF of the paper titled From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness, by Linbo Cao and 2 other authors View PDF HTML (experimental) Abstract: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 impli...
