---
id: 20260630-T0-13
title: "Grounded Iterative Language Planning：通过参数化世界模型减少LLM Agent幻觉传播"
title_en: "Grounded Iterative Language Planning: Reducing Hallucination in LLM Agents"
url: https://ai.daily.yangsir.net/daily/20260630-T0-13
issue_date: 2026-06-30
publish_date: 2026-06-29T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2606.27806
---

# Grounded Iterative Language Planning：通过参数化世界模型减少LLM Agent幻觉传播

arXiv:2606.27806v1 发布。针对语言智能体中的幻觉传播问题，新研究提出了一种结合参数化世界模型与基于语言模型的迭代规划方案。该方案利用参数化模型来识别和纠正语言推理中的错误状态变化，有效减少了智能体在推理过程中的幻觉累积。这一发现为解决LLM Agent长期稳定运行中的事实一致性问题提供了新思路。

## English Version

**Grounded Iterative Language Planning: Reducing Hallucination in LLM Agents**

arXiv:2606.27806v1 released. Addressing hallucination propagation in language agents, this research proposes a method combining parametric world models with iterative language planning. The approach uses parametric models to identify and correct erroneous state changes during language reasoning, effectively reducing the accumulation of hallucinations. This finding offers a new solution for maintaining factual consistency in long-term LLM Agent operations.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2606.27806)

**详情页**：https://ai.daily.yangsir.net/daily/20260630-T0-13

---

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