Rigidity in LLM Bandits with Implications for Human-AI Dyads
Year: 2026
Type: conference-paper
Abstract: We test whether LLMs show robust decision biases. Treating models as participants in two-arm bandits, we ran 200×100 trials per condition across four decoding regimes. 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 policy regime: 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.
Authors: Wang, Haomiaomiao, Ward, Tomás E, Zhang, Lili
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7140323493
FWCI:
Cites:
Cited by:
Related to: