#active-inference News & Analysis

10 articles tagged with #active-inference. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

10 articles

AIBullisharXiv – CS AI · Jun 237/10

🧠

Active Inference as the Test-Time Scaling Law for Physical AI Agents

Researchers introduce a novel test-time scaling law for physical AI agents based on active inference principles, enabling agents to generalize to unforeseen scenarios by dynamically updating policies through reasoning about prediction errors. The approach outperforms existing reinforcement learning methods by 36% in inference efficiency on autonomous driving tasks and scales with real-world experience rather than just training data or model size.

AIBullisharXiv – CS AI · Jun 97/10

🧠

BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in Mobile Networks

Researchers propose BRAIN, a Bayesian reasoning AI agent for 6G mobile networks that uses active inference to improve decision-making transparency and adaptability. Unlike conventional deep reinforcement learning approaches, BRAIN demonstrates 28.3% better robustness to traffic shifts without retraining and provides human-interpretable explanations of its network resource allocation decisions.

AINeutralarXiv – CS AI · Jun 236/10

🧠

Expected Free Energy-based Planning as Variational Inference

Researchers demonstrate that Expected Free Energy (EFE)-based planning in artificial intelligence can be reformulated as Variational Free Energy minimization, unifying planning with perception and learning under the Free Energy Principle. The approach successfully scales active inference to complex environments while improving performance on stochastic problems compared to existing tabular methods.

AINeutralarXiv – CS AI · Jun 235/10

🧠

A Matter of Time: Towards a General Theory of Agency

A new arXiv paper proposes a unified theoretical framework for understanding agency by grounding it in temporal organization, relational biology, and process ontology. The framework distinguishes between autonomy, goal-directedness, agency, and open-endedness through formalized timescale analysis, with implications for understanding biological systems, synthetic life, and artificial intelligence.

AINeutralarXiv – CS AI · Jun 106/10

🧠

Belief-Space Control for Personalized Cancer Treatment via Active Inference

Researchers develop a belief-space control framework using active inference to optimize personalized cancer treatment as a sequential decision-making problem with incomplete information. The approach integrates goal-directed treatment control with strategic information gathering under realistic medical measurement constraints, validated using clinical data from the AACR Project GENIE dataset.

AINeutralarXiv – CS AI · Jun 95/10

🧠

Quantitative Promise Theory: Intentionality and Inference in Autonomous Agents

A research paper presents quantitative approaches to Promise Theory applied to autonomous agent systems, integrating Bayesian probability and Active Inference frameworks. The work explores how Promise Theory can address computational coordination challenges and enable agent alignment at scale, with applications across software, machine learning, biology, and engineering domains.

AINeutralarXiv – CS AI · Jun 46/10

🧠

What Type of Inference is Active Inference?

Researchers provide a rigorous mathematical framework showing how Active Inference and Expected Free Energy (EFE) minimization can be decomposed into Variational Free Energy (VFE) minimization with explicit entropy corrections. The work clarifies the theoretical foundations of EFE-based planning by identifying which corrections are necessary for different decision-making scenarios, demonstrated through grid-world experiments.

AINeutralarXiv – CS AI · May 116/10

🧠

Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference

Researchers introduce a neuro-symbolic framework combining Logic-Augmented Generation and Active Inference to extract and formalize tacit knowledge into machine-interpretable Knowledge Graphs. The approach addresses a critical gap in knowledge engineering by capturing implicit assumptions and contextual expertise from procedural domains like manufacturing, demonstrated through analysis of assembly repair videos.

AIBullisharXiv – CS AI · Mar 36/104

🧠

A Message Passing Realization of Expected Free Energy Minimization

Researchers developed a message passing approach for Expected Free Energy minimization that transforms complex combinatorial search problems into tractable inference problems. The method enables more efficient AI agent planning and exploration under uncertainty, outperforming conventional approaches in test environments.

AIBullisharXiv – CS AI · Mar 27/1016

🧠

ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference

Researchers propose ODAR-Expert, an adaptive routing framework for large language models that optimizes accuracy-efficiency trade-offs by dynamically routing queries between fast and slow processing agents. The system achieved 98.2% accuracy on MATH benchmarks while reducing computational costs by 82%, suggesting that optimal AI scaling requires adaptive resource allocation rather than simply increasing test-time compute.