# Bayesian and Motivated Reasoning in AI Agents

arXiv: https://arxiv.org/abs/2608.00339 · HTML: https://mlsanity.com/paper/2608.00339/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 5 of 5)

- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs](https://mlsanity.com/paper/2502.08640/) (2025)
- [Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning](https://mlsanity.com/paper/2506.20020/) (2025)
- [Replicating Human Motivated Reasoning Studies with LLMs](https://mlsanity.com/paper/2601.16130/) (2026)
- [The Agentic Garden of Forking Paths](https://mlsanity.com/paper/2607.01507/) (2026)

## Abstract (arXiv)

AI agents increasingly perform open-ended tasks in settings where their conclusions can guide consequential decisions. We provide evidence that AI agents draw different conclusions from identical numerical data when the substantive framing changes. We demonstrate this behavior in high-stakes domains in medicine, election forensics, and geopolitical forecasting by holding the evidence fixed while changing the scenario in which the evidence appears. Across twelve agent-domain comparisons, agents' conclusions are strongly influenced by their prior beliefs. They are more likely to reach an affirmative conclusion when it is framed around a proposition they already regard as likely, while the reverse holds when the framing conflicts with their prior. The framing also changes how some agents work: they search more extensively, choose different analytical specifications, and evaluate the same evidence differently. These results identify a particular risk of delegating decision-making to AI agents, as their decisions may depend on prior beliefs that are neither specified in the task nor visible in the decision record.