Cogito, ergo sum:一种用于代码生成的神经生物学启发的认知-记忆-成长系统
Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
AI总结:
针对现有代码生成多智能体系统违背人类学习成长规律且计算成本高的问题,提出神经生物学启发的框架Cogito,采用调试-编码-规划的逆向序列并设计类海马体记忆模块,以更低成本积累知识并形成全能智能体,显著提升了代码生成性能。
摘要:
基于大语言模型的多智能体系统(MAS)在提升代码生成任务的效率和准确性方面展现出了良好的性能。然而,现有大多数方法遵循规划、编码和调试的传统序列,这与人类学习过程的成长驱动特性相矛盾。此外,多个智能体之间频繁的信息交互不可避免地带来高昂的计算成本。本文提出Cogito,一种神经生物学启发的多智能体框架,以更低成本增强代码生成任务中的问题解决能力。具体而言,Cogito采用逆向序列:首先进行调试,然后编码,最后规划。该方法模仿人类的学习与发展,知识是逐步获取的。因此,设计了一个具有不同功能的类海马体记忆模块与流水线协同工作,以便在类似任务中提供快速检索。通过这种基于成长的学习模型,Cogito在每个阶段积累知识和认知技能,最终形成超级角色——一个全能智能体来执行代码生成任务。针对代表性基线的广泛实验证明了Cogito的卓越性能和效率。代码已公开于https://anonymous.4open.science/r/Cogito-0083。
英文摘要:
Large language models based Multi Agent Systems (MAS) have demonstrated promising performance for enhancing the efficiency and accuracy of code generation tasks. However,most existing methods follow a conventional sequence of planning, coding, and debugging,which contradicts the growth-driven nature of human learning process. Additionally,the frequent information interaction between multiple agents inevitably involves high computational costs. In this paper,we propose Cogito,a neurobiologically inspired multi-agent framework to enhance the problem-solving capabilities in code generation tasks with lower cost. Specifically,Cogito adopts a reverse sequence: it first undergoes debugging, then coding,and finally planning. This approach mimics human learning and development,where knowledge is acquired progressively. Accordingly,a hippocampus-like memory module with different functions is designed to work with the pipeline to provide quick retrieval in similar tasks. Through this growth-based learning model,Cogito accumulates knowledge and cognitive skills at each stage,ultimately forming a Super Role an all capable agent to perform the code generation task. Extensive experiments against representative baselines demonstrate the superior performance and efficiency of Cogito. The code is publicly available at https://anonymous.4open.science/r/Cogito-0083.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。