Bridging the Agent-World Gap: Text World Models for LLM-based Agents
Summary
This paper systematically reviews text world models for LLM-based agents, covering foundations, construction paradigms, applications in planning and training, and evaluation methods.
View Cached Full Text
Cached at: 06/10/26, 05:45 AM
Paper page - Bridging the Agent-World Gap: Text World Models for LLM-based Agents
Source: https://huggingface.co/papers/2606.09032 Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
Text world models serve as transition models for LLM-based agents in interactive environments, enabling planning and efficient learning by predicting environmental changes from textual states and actions.
Large language model (LLM)-based agents are increasingly used in interactive textual environments, from web navigation and code editing to tool use and long-horizon dialogue. Yet many remain largely reactive, mapping observations to actions without an explicit model of how these environments are structured and evolve. This motivatestext world models(TWMs):transition modelsovertextual statesthat, given a state and a candidate action, predict the resulting webpage, terminal output, API response, or user reply, thereby supportingplanning, efficient learning, and principled evaluation. We systematically reviewtext world modelsforLLM-based agents, organized around a formal framework and the agent lifecycle: (1) Foundations, definingtext world modelsand characterizing them by state representation and grounding domain; (2) Construction, taxonomizing LLM-as-WM and code-as-WM paradigms and reviewing methods for building them; (3) Application, examining how world models support agents at training time throughexperience synthesisand at inference time throughplanning,verification, andadaptation; and (4) Evaluation, covering both evaluation of the world model itself and its use as an evaluation environment for agents. We aim to consolidate this rapidly developing area, clarify its design space, and highlight open challenges for future research.
View arXiv pageView PDFGitHub5Add to collection
Get this paper in your agent:
hf papers read 2606\.09032
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.09032 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.09032 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.09032 in a Space README.md to link it from this page.
Collections including this paper1
Similar Articles
Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
This paper argues that large language models struggle with causal reasoning and long-horizon planning due to a mismatch between sequence prediction and reasoning over latent environment dynamics, and introduces the Latent Dynamics Inference perspective along with the Flux environment to study these limitations.
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
This paper introduces World-Language-Action (WLA) models, embodied foundation models that jointly predict textual subtasks, subgoal images, and robot actions from text, images, and robot states, achieving state-of-the-art multi-task and long-horizon learning in simulated and real-world environments.
Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
Proposes Adwm, an autoregressive diffusion world model for off-policy evaluation of LLM agents, enabling reliable value estimates from pre-collected trajectories without online interaction.
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
A comprehensive survey on agentic environment engineering for LLMs, covering environment modeling, synthesis, evaluation, and application, with a focus on agent-environment co-evolution.
World Model for Robot Learning: A Comprehensive Survey
This comprehensive survey reviews the literature on world models for robot learning, covering their roles in policy learning, planning, and simulation. It highlights key paradigms, benchmarks, and future directions for predictive modeling in embodied agents.