让大模型自己设计复杂推理流程，提升准确率并减少人工调参。
Self-guided Knowledgeable Network of Thoughts: Amplifying Reasoning with Large Language Models
- 大模型自动生成可执行的多步推理网络，节点为操作，边为信息传递。
- 处理32个数排序任务时准确率达92%，远超其他方法。
- 适合需要高可靠长链推理的应用，如自动规划与复杂问题求解。
我们提出知识型思维网络（kNoT）：一种超越现有链式思维（CoT）、树状思维（ToT）和图状思维（GoT）范式的提示框架。其核心创新是大模型工作流模板（LWT），使大模型能为自身生成可执行计划。LWT将计划表示为任意网络结构，单步大模型操作作为节点，步骤间消息传递构成边。同时支持通过索引选择特定元素，使每一步仅执行基础操作，显著提升长序列任务的可靠性。实验表明，kNoT在六个应用场景中显著优于现有最先进方法，且大幅减少特定任务提示需求。例如，在排序32个数字的任务中，准确率达92%，远超ToT（12%）和GoT（31%），同时分别减少84.4%和87.3%的任务定制提示。
原文摘要 · Abstract (English)
We introduce Knowledgeable Network of Thoughts (kNoT): a prompt scheme that advances the capabilities of large language models (LLMs) beyond existing paradigms like Chain-of-Thought (CoT), Tree of Thoughts (ToT), and Graph of Thoughts (GoT). The key innovation of kNoT is the LLM Workflow Template (LWT), which allows for an executable plan to be specified by LLMs for LLMs. LWT allows these plans to be arbitrary networks, where single-step LLM operations are nodes, and edges correspond to message passing between these steps. Furthermore, LWT supports selection of individual elements through indexing, facilitating kNoT to produce intricate plans where each LLM operation can be limited to elementary operations, greatly enhancing reliability over extended task sequences. We demonstrate that kNoT significantly outperforms the state of the art on six use cases, while reducing the need for extensive prompt engineering. For instance, kNoT finds 92% accuracy for sorting 32 numbers over 12% and 31% for ToT and GoT, while utilizing up to 84.4% and 87.3% less task-specific prompts, respectively.
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。