---
id: 20260903-T0-09
title: "HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Models"
url: https://ai.daily.yangsir.net/daily/20260903-T0-09
issue_date: 2026-09-03
publish_date: 2026-09-02T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2609.00002
---

# HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Models

arXiv:2609.00002v1 Announce Type: new Abstract: World models enable language-model agents to predict environment dynamics and plan before acting. In text environments, the model must learn symbolic action effects from serialized state descriptions, but the role of serialization structure remains und

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2609.00002)

**详情页**：https://ai.daily.yangsir.net/daily/20260903-T0-09

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*