Saved in:
Bibliographic Details
Main Authors: Jhajj, Gaganpreet, Lin, Fuhua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.01878
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911296505511936
author Jhajj, Gaganpreet
Lin, Fuhua
author_facet Jhajj, Gaganpreet
Lin, Fuhua
contents In this work, we propose that reasoning in knowledge graph (KG) networks can be guided by surprise minimization. Entities that are close in graph distance will have lower surprise than those farther apart. This connects the Free Energy Principle (FEP) from neuroscience to KG systems, where the KG serves as the agent's generative model. We formalize surprise using the shortest-path distance in directed graphs and provide a framework for KG-based agents. Graph distance appears in graph neural networks as message passing depth and in model-based reinforcement learning as world model trajectories. This work-in-progress study explores whether distance-based surprise can extend recent work showing that syntax minimizes surprise and free energy via tree structures.
format Preprint
id arxiv_https___arxiv_org_abs_2512_01878
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph Distance as Surprise: Free Energy Minimization in Knowledge Graph Reasoning
Jhajj, Gaganpreet
Lin, Fuhua
Artificial Intelligence
In this work, we propose that reasoning in knowledge graph (KG) networks can be guided by surprise minimization. Entities that are close in graph distance will have lower surprise than those farther apart. This connects the Free Energy Principle (FEP) from neuroscience to KG systems, where the KG serves as the agent's generative model. We formalize surprise using the shortest-path distance in directed graphs and provide a framework for KG-based agents. Graph distance appears in graph neural networks as message passing depth and in model-based reinforcement learning as world model trajectories. This work-in-progress study explores whether distance-based surprise can extend recent work showing that syntax minimizes surprise and free energy via tree structures.
title Graph Distance as Surprise: Free Energy Minimization in Knowledge Graph Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2512.01878