Next Article in Journal
Accelerating Post-Quantum Cryptography: A High-Efficiency NTT for ML-KEM on RISC-V
Previous Article in Journal
Fast Algorithms for Small-Size Type VII Discrete Cosine Transform
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 15
Issue 1
10.3390/electronics15010099
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

AIDE: An Active Inference-Driven Framework for Dynamic Evaluation via Latent State Modeling and Generative Reasoning

by
Xi Chen
1,*,
Changwang Liu
2,
Chenyang Zhang
2,
Yuxuan Wang
2,
Jiayi Chang
2,
Shuqing He
3,
Wangyu Wu
4,
Wenjun Yu
5 and
Jia Guo
2
1
Personnel Department, Tianjin Normal University, Tianjin 300387, China
2
Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China
3
School of Information Science and Engineering, Linyi University, Linyi 276012, China
4
School of Computer Science, University of Liverpool, Liverpool L69 7ZX, UK
5
School of Computer Science, Shanghai University of International Business and Economics, Shanghai 201613, China
*
Author to whom correspondence should be addressed.
Electronics 2026, 15(1), 99; https://doi.org/10.3390/electronics15010099 (registering DOI)
Submission received: 28 November 2025 / Revised: 20 December 2025 / Accepted: 23 December 2025 / Published: 24 December 2025
(This article belongs to the Section Artificial Intelligence)
Versions Notes

Abstract

This paper introduces AIDE, an active inference-driven evaluation framework designed to provide a unified and theoretically grounded approach for analyzing sequential textual data. AIDE formulates the evaluation problem as variational inference in a latent dynamical system, enabling joint treatment of representation, temporal structure, and predictive reasoning. The framework integrates (i) a representation and augmentation module based on variational learning and contrastive semantic encoding, (ii) a parametric state–space model that captures the evolution of latent states and supports probabilistic forecasting, and (iii) a policy-selection mechanism that minimizes the expected free energy, guiding a latent diffusion generator to produce coherent and interpretable evaluation outputs. This formulation yields a principled pipeline linking evidence accumulation, latent-state inference, and policy-driven generative reporting. Experimental studies demonstrate that AIDE provides stable inference, coherent predictions, and consistent evaluation behavior across heterogeneous textual sequences. The proposed framework offers a general probabilistic foundation for dynamic evaluation tasks and contributes a structured methodology for integrating representation learning, dynamical modeling, and generative mechanisms within a single variational paradigm.
Keywords: active inference; latent dynamical models; variational representation learning; expected free energy; diffusion-based generation active inference; latent dynamical models; variational representation learning; expected free energy; diffusion-based generation

Share and Cite

MDPI and ACS Style

Chen, X.; Liu, C.; Zhang, C.; Wang, Y.; Chang, J.; He, S.; Wu, W.; Yu, W.; Guo, J. AIDE: An Active Inference-Driven Framework for Dynamic Evaluation via Latent State Modeling and Generative Reasoning. Electronics 2026, 15, 99. https://doi.org/10.3390/electronics15010099

AMA Style

Chen X, Liu C, Zhang C, Wang Y, Chang J, He S, Wu W, Yu W, Guo J. AIDE: An Active Inference-Driven Framework for Dynamic Evaluation via Latent State Modeling and Generative Reasoning. Electronics. 2026; 15(1):99. https://doi.org/10.3390/electronics15010099

Chicago/Turabian Style

Chen, Xi, Changwang Liu, Chenyang Zhang, Yuxuan Wang, Jiayi Chang, Shuqing He, Wangyu Wu, Wenjun Yu, and Jia Guo. 2026. "AIDE: An Active Inference-Driven Framework for Dynamic Evaluation via Latent State Modeling and Generative Reasoning" Electronics 15, no. 1: 99. https://doi.org/10.3390/electronics15010099

APA Style

Chen, X., Liu, C., Zhang, C., Wang, Y., Chang, J., He, S., Wu, W., Yu, W., & Guo, J. (2026). AIDE: An Active Inference-Driven Framework for Dynamic Evaluation via Latent State Modeling and Generative Reasoning. Electronics, 15(1), 99. https://doi.org/10.3390/electronics15010099

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop