Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model

• URL: http://arxiv.org/abs/2603.05438v1
• Date: Thu, 05 Mar 2026 18:00:02 GMT
• Title: Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
• Authors: Dongwon Kim, Gawon Seo, Jinsung Lee, Minsu Cho, Suha Kwak,
• Abstract summary: We propose CompACT, a tokenizer that compresses each observation into as few as 8 tokens, drastically reducing computational cost while preserving essential information for planning.<n>An action-conditioned world model occupies CompACT tokenizer achieves competitive planning performance with orders-of-magnitude faster planning, offering a practical step toward real-world deployment of world models.
• Score: 76.30055935418561
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World models provide a powerful framework for simulating environment dynamics conditioned on actions or instructions, enabling downstream tasks such as action planning or policy learning. Recent approaches leverage world models as learned simulators, but its application to decision-time planning remains computationally prohibitive for real-time control. A key bottleneck lies in latent representations: conventional tokenizers encode each observation into hundreds of tokens, making planning both slow and resource-intensive. To address this, we propose CompACT, a discrete tokenizer that compresses each observation into as few as 8 tokens, drastically reducing computational cost while preserving essential information for planning. An action-conditioned world model that occupies CompACT tokenizer achieves competitive planning performance with orders-of-magnitude faster planning, offering a practical step toward real-world deployment of world models.

Related papers

• An Empirical Study of World Model Quantization [34.94388089174202]
  We present a systematic empirical study of world model quantization using DINO-WM.<n>We conduct experiments on different visual planning tasks across a wide range of bit-widths, quantization granularities, and planning horizons up to 50 iterations.<n>Results show that quantization effects in world models extend beyond standard accuracy and bit-width trade-offs.
  arXiv  Detail & Related papers  (2026-02-02T13:54:03Z)
• From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction [57.56072009935036]
  We introduce a new driving paradigm named Policy World Model (PWM)<n>PWM integrates world modeling and trajectory planning within a unified architecture.<n>Our method matches or exceeds state-of-the-art approaches that rely on multi-view and multi-modal inputs.
  arXiv  Detail & Related papers  (2025-10-22T14:57:51Z)
• ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning [77.49815848173613]
  We propose a framework for abstract world models that jointly learns symbolic state representations and causal processes for both endogenous actions and mechanisms.<n>Across five simulated tabletop robotics environments, the learned models enable fast planning that generalizes to held-out tasks with more objects and more complex goals, outperforming a range of baselines.
  arXiv  Detail & Related papers  (2025-09-30T13:44:34Z)
• Sparse Imagination for Efficient Visual World Model Planning [4.379304291229695]
  World model based planning has significantly improved decision-making in complex environments by enabling agents to simulate future states and make informed choices.<n>However, ensuring the prediction accuracy of world models often demands substantial computational resources.<n>We propose a Sparse Imagination for Efficient Visual World Model Planning, which enhances computational efficiency by reducing the number of tokens processed during forward prediction.
  arXiv  Detail & Related papers  (2025-06-02T07:36:14Z)
• Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach [82.27842884709378]
  We propose a framework that prioritizes natural language understanding and structured reasoning to enhance the agent's global understanding of the environment.<n>Our method outperforms previous approaches, particularly achieving a 44.4% relative improvement in task success rate.
  arXiv  Detail & Related papers  (2025-05-22T09:08:47Z)
• Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling [21.45039811922009]
  We advocate a self-refining scheme that iteratively refines a draft plan until an equilibrium is reached.<n>A nested equilibrium sequence modeling procedure is devised for efficient closed-loop planning.<n>Our method is evaluated on the VirtualHome-Env benchmark, showing advanced performance with improved scaling w.r.t. inference-time computation.
  arXiv  Detail & Related papers  (2024-10-02T11:42:49Z)
• Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty [56.30846158280031]
  Task planning for embodied AI has been one of the most challenging problems. We propose a task-agnostic method named 'planning as in-painting' The proposed framework achieves promising performances in various embodied AI tasks.
  arXiv  Detail & Related papers  (2023-12-02T10:07:17Z)
• STRIPS Action Discovery [67.73368413278631]
  Recent approaches have shown the success of classical planning at synthesizing action models even when all intermediate states are missing. We propose a new algorithm to unsupervisedly synthesize STRIPS action models with a classical planner when action signatures are unknown.
  arXiv  Detail & Related papers  (2020-01-30T17:08:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.