# Rigidity in LLM Bandits with Implications for Human-AI Dyads

arXiv: https://arxiv.org/abs/2603.07717 · HTML: https://mlsanity.com/paper/2603.07717/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [Optimizing Opinions with Stubborn Agents](https://mlsanity.com/paper/1806.11253/) (2018)
- [Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities](https://mlsanity.com/paper/2505.13195/) (2025)

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

- [Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty](https://mlsanity.com/paper/2604.04182/) (2026)

## Abstract (arXiv)

We test whether LLMs show robust decision biases. Treating models as participants in two-arm bandits, we ran 20000 trials per condition across four decoding configurations. Under symmetric rewards, models amplified positional order into stubborn one-arm policies. Under asymmetric rewards, they exploited rigidly yet underperformed an oracle and rarely re-checked. The observed patterns were consistent across manipulations of temperature and top-p, with top-k held at the provider default, indicating that the qualitative behaviours are robust to the two decoding knobs typically available to practitioners. Crucially, moving beyond descriptive metrics to computational modelling, a hierarchical Rescorla-Wagner-softmax fit revealed the underlying strategies: low learning rates and very high inverse temperatures, which together explain both noise-to-bias amplification and rigid exploitation. These results position minimal bandits as a tractable probe of LLM decision tendencies and motivate hypotheses about how such biases could shape human-AI interaction.