---
id: 20260630-T0-17
title: "LLM规划新方案：基于符号反馈的迭代自优化框架"
title_en: "Symbolic Feedback-Driven Framework Improves LLM Planning Reliability"
url: https://ai.daily.yangsir.net/daily/20260630-T0-17
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/2606.27757
---

# LLM规划新方案：基于符号反馈的迭代自优化框架

针对大模型在长期规划中的鲁棒性问题，新研究提出了一种基于符号反馈的迭代自优化框架。该方法通过引入外部符号逻辑来校验 LLM 的输出，通过迭代修正显著提升了模型在复杂任务中的成功率和安全性。

## English Version

**Symbolic Feedback-Driven Framework Improves LLM Planning Reliability**

Addressing reliability issues in LLM planning, new research proposes a symbolic feedback-driven iterative self-refinement framework. It uses external symbolic logic to verify outputs, iteratively correcting errors to boost success rates in complex tasks.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2606.27757)

**详情页**：https://ai.daily.yangsir.net/daily/20260630-T0-17

---

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