The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models

Junyao Zhang, Jinglai Li, Junqi Tang
1/12/2026
cs.LGcs.MA

No confident code implementation found for this paper.

Abstract

Agent-Based Models (ABMs) are gaining great popularity in economics and social science because of their strong flexibility to describe the realistic and heterogeneous decisions and interaction rules between individual agents. In this work, we investigate for the first time the practicality of test-time training (TTT) of deep models such as normalizing flows, in the parameters posterior estimations of ABMs. We propose several practical TTT strategies for fine-tuning the normalizing flow against distribution shifts. Our numerical study demonstrates that TTT schemes are remarkably effective, enabling real-time adjustment of flow-based inference for ABM parameters.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Calibrated Test-Time Guidance for Bayesian Inference

80% match2026

PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference

79% match1 repo52025

Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators

79% match2025

Normalizing Flow Regression for Bayesian Inference with Offline Likelihood Evaluations

78% match1 repo32025

Causal Posterior Estimation

78% match2025

Flow Matching for Robust Simulation-Based Inference under Model Misspecification

77% match2025

Cite this paper

@article{zhang2026practicality,
  title  = {The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models},
  author = {Junyao Zhang and Jinglai Li and Junqi Tang},
  year   = {2026},
  eprint = {2601.07413},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.07413v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.07413.svg)](https://codeofpaper.com/paper/2601.07413)

Discussion