OlaGPT：賦予LLM具備類人問題解決能力

摘要

在大多數當前的研究中，大型語言模型（LLMs）能夠通過特定提示的引導，生成一系列思維鏈來執行推理任務。然而，它們在解決複雜推理問題方面的能力與人類之間仍存在顯著差距。目前，大多數方法著重於思維鏈（COT）和工具使用，而沒有考慮採用和應用人類認知框架。眾所周知，當人類面對複雜推理挑戰時，通常會運用各種認知能力，並需要與工具、知識和外部環境信息的各個方面進行互動，以完成複雜任務。本文介紹了一個新穎的智能框架，稱為OlaGPT。OlaGPT仔細研究了一個認知架構框架，並提出模擬人類認知的某些方面。該框架涉及近似不同的認知模塊，包括注意力、記憶、推理、學習以及相應的調度和決策機制。受人類主動學習機制的啟發，它提出了一個學習單元，記錄先前的錯誤和專家意見，並動態參考它們以增強解決類似問題的能力。該文還概述了人類解決問題的常見有效推理框架，並相應地設計了思維鏈（COT）模板。還提出了一個全面的決策機制，以最大程度地提高模型準確性。OlaGPT的有效性已在多個推理數據集上進行了嚴格評估，實驗結果顯示OlaGPT超越了最先進的基準，展示了其卓越性能。我們對OlaGPT的實現可在GitHub上找到：https://github.com/oladata-team/OlaGPT。

English

In most current research, large language models (LLMs) are able to perform reasoning tasks by generating chains of thought through the guidance of specific prompts. However, there still exists a significant discrepancy between their capability in solving complex reasoning problems and that of humans. At present, most approaches focus on chains of thought (COT) and tool use, without considering the adoption and application of human cognitive frameworks. It is well-known that when confronting complex reasoning challenges, humans typically employ various cognitive abilities, and necessitate interaction with all aspects of tools, knowledge, and the external environment information to accomplish intricate tasks. This paper introduces a novel intelligent framework, referred to as OlaGPT. OlaGPT carefully studied a cognitive architecture framework, and propose to simulate certain aspects of human cognition. The framework involves approximating different cognitive modules, including attention, memory, reasoning, learning, and corresponding scheduling and decision-making mechanisms. Inspired by the active learning mechanism of human beings, it proposes a learning unit to record previous mistakes and expert opinions, and dynamically refer to them to strengthen their ability to solve similar problems. The paper also outlines common effective reasoning frameworks for human problem-solving and designs Chain-of-Thought (COT) templates accordingly. A comprehensive decision-making mechanism is also proposed to maximize model accuracy. The efficacy of OlaGPT has been stringently evaluated on multiple reasoning datasets, and the experimental outcomes reveal that OlaGPT surpasses state-of-the-art benchmarks, demonstrating its superior performance. Our implementation of OlaGPT is available on GitHub: https://github.com/oladata-team/OlaGPT.

OlaGPT：賦予LLM具備類人問題解決能力

OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities

摘要

Support