让大模型推理更稳更快，通过外部图结构规划路径。
Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation
- 用外部有向无环图存储推理计划，避免记忆碎片化。
- 在多跳问答任务中表现优于RQ-RAG和Self-RAG。
- 适合需要可靠推理的复杂问答系统开发者。
我们提出Plan*RAG，一种在检索增强生成（RAG）中实现结构化多跳推理的新框架，通过测试时生成推理计划来提升性能。现有方法如ReAct将推理链限制在语言模型的上下文窗口内，常导致计划碎片化和执行失败。我们的核心洞察是：将推理计划以有向无环图（DAG）形式置于语言模型工作内存之外，可实现（1）系统性探索推理路径，（2）原子级子查询支持精准检索与事实对齐，（3）通过并行执行和受限上下文窗口利用提升效率。此外，Plan*RAG的模块化设计使其可无缝集成至现有RAG系统，提供实用升级方案。在标准多跳推理基准测试中，Plan*RAG持续优于近期提出的RQ-RAG和Self-RAG，同时保持相近计算开销。
原文摘要 · Abstract (English)
We introduce Plan*RAG, a novel framework that enables structured multi-hop reasoning in retrieval-augmented generation (RAG) through test-time reasoning plan generation. While existing approaches such as ReAct maintain reasoning chains within the language model's context window, we observe that this often leads to plan fragmentation and execution failures. Our key insight is that by isolating the reasoning plan as a directed acyclic graph (DAG) outside the LM's working memory, we can enable (1) systematic exploration of reasoning paths, (2) atomic subqueries enabling precise retrievals and grounding, and (3) efficiency through parallel execution and bounded context window utilization. Moreover, Plan*RAG's modular design allows it to be integrated with existing RAG methods, thus providing a practical solution to improve current RAG systems. On standard multi-hop reasoning benchmarks, Plan*RAG consistently achieves improvements over recently proposed methods such as RQ-RAG and Self-RAG, while maintaining comparable computational costs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。