Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
This work addresses computational cost and learning inefficiency in code generation for developers, though it appears incremental by adapting existing multi-agent systems with a novel sequence.
The authors tackled the inefficiency of conventional multi-agent code generation systems by proposing Cogito, a neurobiologically-inspired framework that reverses the typical planning-coding-debugging sequence to mimic human learning, resulting in superior performance and lower computational costs as demonstrated in experiments.
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.