Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
Yanlong Li, Jindong Li, Qi Wang, Menglin Yang, He Kong, Shengsheng, Wang

TL;DR
Cogito is a neurobiologically inspired multi-agent system that improves code generation by mimicking human learning, using a reverse process of debugging, coding, then planning, with a memory module for quick knowledge retrieval.
Contribution
The paper introduces Cogito, a novel growth-driven, reverse-sequence multi-agent framework inspired by human cognition, enhancing code generation efficiency and performance.
Findings
Outperforms baseline models in accuracy and efficiency
Reduces computational costs compared to traditional methods
Demonstrates effective knowledge accumulation and retrieval
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobotics and Automated Systems · Cognitive and developmental aspects of mathematical skills · AI-based Problem Solving and Planning
