# Affordances Enable Partial World Modeling with LLMs

arXiv: https://arxiv.org/abs/2602.10390 · HTML: https://mlsanity.com/paper/2602.10390/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 9 of 9)

- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [Large-Scale Study of Curiosity-Driven Learning](https://mlsanity.com/paper/1808.04355/) (2018)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [General agents contain world models](https://mlsanity.com/paper/2506.01622/) (2025)
- [Zero-shot Model-based Reinforcement Learning using Large Language Models](https://mlsanity.com/paper/2410.11711/) (2024)
- [Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning](https://mlsanity.com/paper/2212.03760/) (2022)
- [Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning](https://mlsanity.com/paper/2504.17282/) (2025)

## Built on by (most cited first, 2 of 2)

- [What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty](https://mlsanity.com/paper/2603.02491/) (2026)
- [RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions](https://mlsanity.com/paper/2610.13172/) (2026)

## Abstract (arXiv)

Full models of the world require complex knowledge of immense detail. While pre-trained large models have been hypothesized to contain similar knowledge due to extensive pre-training on vast amounts of internet scale data, using them directly in a search procedure is inefficient and inaccurate. Conversely, partial models focus on making high quality predictions for a subset of state and actions: those linked through affordances that achieve user intents~citepkhetarpal2020can. Can we posit large models as partial world models? We provide a formal answer to this question, proving that agents achieving task-agnostic, language-conditioned intents necessarily possess predictive partial-world models informed by affordances. In the multi-task setting, we introduce distribution-robust affordances and show that partial models can be extracted to significantly improve search efficiency. Empirical evaluations in tabletop robotics tasks demonstrate that our affordance-aware partial models reduce the search branching factor and achieve higher rewards compared to full world models.