Belief at Risk: Quantifying Agentic AI Model Risk with LLM-Inferred Bayesian State Filters

By Matthew Dixon

Published 2026-06-16

Everscope rating

1629.9

Relevance to quantitative trading

8 / 10

Implementation complexity

5 / 10

Reproducibility

4 / 5

About this paper

Methodology: LLM-Inferred Bayesian State Filtering for Agentic AI Model Risk. Problem types: Risk Management, Portfolio Optimization, Density Estimation, Classification, Reinforcement Learning.

arXiv:2606.15473 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.