Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation

• URL: http://arxiv.org/abs/2501.18653v1
• Date: Thu, 30 Jan 2025 01:41:44 GMT
• Title: Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
• Authors: Yanlong Li, Jindong Li, Qi Wang, Menglin Yang, He Kong, Shengsheng Wang,
• Abstract summary: Cogito is a neurobiologically inspired multi-agent framework to enhance the problem-solving capabilities in code generation tasks with lower cost. Cogito accumulates knowledge and cognitive skills at each stage,ultimately forming a Super Role an all capable agent to perform the code generation task.
• Score: 9.920563105290894
• License:
• 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 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.

Related papers

• UniGenCoder: Merging Seq2Seq and Seq2Tree Paradigms for Unified Code Generation [32.315975899771495]
  Existing approaches to code generation have focused on the Sequence-to-Sequence paradigm, which generates target code as a sequence of tokens, or the Sequence-to-Tree paradigm, which outputs code as a sequence of actions. We propose UniGenCoder for code-related generation tasks, which consists of a shared encoder, a shared decoder with a minimal set of additional parameters, and a selector that dynamically chooses optimal paradigm for each instance. Experimental results on the text-to-code and code-to-code generation tasks demonstrate the effectiveness of our proposed model.
  arXiv  Detail & Related papers  (2025-02-18T03:19:48Z)
• Scaling Large-Language-Model-based Multi-Agent Collaboration [75.5241464256688]
  Pioneering advancements in large language model-powered agents have underscored the design pattern of multi-agent collaboration. Inspired by the neural scaling law, this study investigates whether a similar principle applies to increasing agents in multi-agent collaboration.
  arXiv  Detail & Related papers  (2024-06-11T11:02:04Z)
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning [64.55001982176226]
  LIBERO is a novel benchmark of lifelong learning for robot manipulation. We focus on how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks.
  arXiv  Detail & Related papers  (2023-06-05T23:32:26Z)
• CONCORD: Clone-aware Contrastive Learning for Source Code [64.51161487524436]
  Self-supervised pre-training has gained traction for learning generic code representations valuable for many downstream SE tasks. We argue that it is also essential to factor in how developers code day-to-day for general-purpose representation learning. In particular, we propose CONCORD, a self-supervised, contrastive learning strategy to place benign clones closer in the representation space while moving deviants further apart.
  arXiv  Detail & Related papers  (2023-06-05T20:39:08Z)
• Artificial Neuropsychology: Are Large Language Models Developing Executive Functions? [0.0]
  We evaluate the planning function and working memory of GPT using the popular Towers of Hanoi method. Preliminary results show that LLMs generates near-optimal solutions in Towers of Hanoi related tasks. These abilities are quite limited and worse than well-trained humans when the tasks are not known.
  arXiv  Detail & Related papers  (2023-05-06T20:53:22Z)
• Incremental procedural and sensorimotor learning in cognitive humanoid robots [52.77024349608834]
  This work presents a cognitive agent that can learn procedures incrementally. We show the cognitive functions required in each substage and how adding new functions helps address tasks previously unsolved by the agent. Results show that this approach is capable of solving complex tasks incrementally.
  arXiv  Detail & Related papers  (2023-04-30T22:51:31Z)
• Enhancing Semantic Code Search with Multimodal Contrastive Learning and Soft Data Augmentation [50.14232079160476]
  We propose a new approach with multimodal contrastive learning and soft data augmentation for code search. We conduct extensive experiments to evaluate the effectiveness of our approach on a large-scale dataset with six programming languages.
  arXiv  Detail & Related papers  (2022-04-07T08:49:27Z)
• CogNGen: Constructing the Kernel of a Hyperdimensional Predictive Processing Cognitive Architecture [79.07468367923619]
  We present a new cognitive architecture that combines two neurobiologically plausible, computational models. We aim to develop a cognitive architecture that has the power of modern machine learning techniques.
  arXiv  Detail & Related papers  (2022-03-31T04:44:28Z)
• Planning with Biological Neurons and Synapses [4.2873412319680035]
  We revisit the planning problem in the blocks world, and we implement a known for this task. We believe that this is the first algorithm of its kind. The input is a sequence of symbols encoding an initial set of block stacks as well as a target set, and the output is a sequence of motion commands such as "put the top block in stack 1 on the table"
  arXiv  Detail & Related papers  (2021-12-15T15:09:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.