Axes of Planning (in AI Models) - by Nicky

Trying to somewhat decompose the term "planning"

Axes of Planning (in AI Models) Trying to somewhat decompose the term "planning" Nicky Apr 15, 2026 2 1 Share We give a model a prompt, it produces and output. How does it work? Do language models Plan? When people look at language models, and want to interpretability and evaluations to understand behavior, one natural question is to ask is whether the model is planning. However, “planning” is a relatively vague concept that points at a few different things. I try to walk though a bunch of examples that seem somehow related to aspects of “planning”, then try to divide planning into a few diffe

related reading

• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• A global workspace in language models \ Anthropicanthropic.com
• As Rocks May Think | Eric Jangevjang.com
• Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
• Agentshuyenchip.com
• A Functional Taxonomy of World Models - Dr. Fei-Fei Lidrfeifei.substack.com
• AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• [2201.07207] Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentsarxiv.org
• Neuronpedianeuronpedia.org
• Implicit planning in LLMs Paper | Manifundmanifund.org