mlsanityData to 14 Oct 2026

Predictive Minds: LLMs As Atypical Active Inference Agents

arXiv 2311.10215 ↗First posted 16 Nov 2023cs.CL cs.AIcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large language models (LLMs) like GPT are often conceptualized as passive predictors, simulators, or even stochastic parrots. We instead conceptualize LLMs by drawing on the theory of active inference originating in cognitive science and neuroscience. We examine similarities and differences between traditional active inference systems and LLMs, leading to the conclusion that, currently, LLMs lack a tight feedback loop between acting in the world and perceiving the impacts of their actions, but otherwise fit in the active inference paradigm. We list reasons why this loop may soon be closed, and possible consequences of this including enhanced model self-awareness and the drive to minimize prediction error by changing the world.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 19 of its 30 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

19 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022A Generalist Agent12 May

Other references · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  4. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  5. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  6. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 431
  7. 2020Performative Predictioncited by 327
  8. 2022Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizerscited by 204
  9. 2023Large Language Models as General Pattern Machinescited by 197
  10. 2023Taken out of context: On measuring situational awareness in LLMscited by 143
  11. 2022The Debate Over Understanding in AI's Large Language Modelscited by 142
  12. 2022Evaluating Human-Language Model Interactioncited by 92
6 more
  1. 2021Shaking the foundations: delusions in sequence models for interaction and controlcited by 62
  2. 2022Data Feedback Loops: Model-driven Amplification of Dataset Biasescited by 60
  3. 2020Is SGD a Bayesian sampler? Well, almostcited by 50
  4. 2019A free energy principle for a particular physicscited by 40
  5. 2023Conditioning Predictive Models: Risks and Strategiescited by 11
  6. 2023Learning to Plan with Natural Languagecited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  2. 2026Where is the Mind? Persona Vectors and LLM Individuationcited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2026Understanding Large Language Models
  2. 2025Language and Thought: The View from LLMs
  3. 2024GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?
  4. 2023Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models
  5. 2025Recognizing Artificial Minds: A Philosophical Defense of AI Cognition
  6. 2024Controlling Large Language Model Agents with Entropic Activation Steering
  7. 2024Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation
  8. 2024Mental Modeling of Reinforcement Learning Agents by Language Models