Review possible WAM paper: World Tokens: Enhancing Embodied Policies with Training-Time World Modeling

[279object]

Paper

• Title: World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
• Short name: World Tokens
• arXiv ID: 2608.09730v1
• Paper: https://arxiv.org/pdf/2608.09730
• Authors: Qu Tang, Benhui Zhuang, Bo Yuan, Xue Yu, Longteng Guo, Junlan Feng
• Published: 2026-08-10
• arXiv categories: cs.CV, cs.RO
• Matched keywords: world-action model, world-action models

README Entry

- **World Tokens**: "World Tokens: Enhancing Embodied Policies with Training-Time World Modeling", arXiv 2026. ![](https://img.shields.io/badge/Needs--Taxonomy--Review-64748b)
  [[📄 Paper](https://arxiv.org/pdf/2608.09730)]

Robot Decision

• Decision: pending
• Confidence: unknown
• Taxonomy: None
• Taxonomy confidence: None
• README heading: ## World Action Model
• Badges: https://img.shields.io/badge/Needs--Taxonomy--Review-64748b

Reason

LLM WAM detection failed: LLM request failed: HTTP 404:

<title>404 Not Found</title>

404 Not Found

---

nginx

Evidence

• world-action model
• world-action models

Needs taxonomy review: fallback README heading/badge was used because taxonomy.toml has no README mapping for this classification.

Human Review Checklist

• This paper belongs in the WAM survey
• README section is correct
• Badges are correct
• Short name is correct
• Paper link is correct
• Merge this PR if accepted