用双系统模拟人类思考，让大模型更聪明地推理。
PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning
- 分快慢两步：先快速出答案，不确定时启动多代理深度推理
- 在多跳和知识依赖任务上媲美GPT-4等闭源模型
- 适合需要复杂推理的科研、问答与决策场景
受《思考，快与慢》中人类认知双过程理论启发，我们提出PRIME（Planning and Retrieval-Integrated Memory for Enhanced Reasoning），一种动态融合快速直觉思维（System 1）与慢速严谨思维（System 2）的多代理推理框架。PRIME首先由快速思维代理（System 1）生成初步答案；若检测到不确定性，则触发包含规划、假设生成、检索、信息整合与决策的结构化System 2推理流水线。该多代理设计忠实模拟人类认知过程，提升效率与准确率。在LLaMA 3模型上的实验表明，PRIME使开源大模型在需多跳推理和知识依赖的任务上表现媲美GPT-4与GPT-4o等闭源先进模型。本研究确立了PRIME作为提升大模型复杂知识推理能力的可扩展解决方案。
原文摘要 · Abstract (English)
Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates \textbf{System 1} (fast, intuitive thinking) and \textbf{System 2} (slow, deliberate thinking). PRIME first employs a Quick Thinking Agent (System 1) to generate a rapid answer; if uncertainty is detected, it then triggers a structured System 2 reasoning pipeline composed of specialized agents for \textit{planning}, \textit{hypothesis generation}, \textit{retrieval}, \textit{information integration}, and \textit{decision-making}. This multi-agent design faithfully mimics human cognitive processes and enhances both efficiency and accuracy. Experimental results with LLaMA 3 models demonstrate that PRIME enables open-source LLMs to perform competitively with state-of-the-art closed-source models like GPT-4 and GPT-4o on benchmarks requiring multi-hop and knowledge-grounded reasoning. This research establishes PRIME as a scalable solution for improving LLMs in domains requiring complex, knowledge-intensive reasoning.
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。