MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Mofei, Chen, Taozhi, Yang, Guowei, Li, Jia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911625895739392
author Li, Mofei
Chen, Taozhi
Yang, Guowei
Li, Jia
author_facet Li, Mofei
Chen, Taozhi
Yang, Guowei
Li, Jia
contents Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal private libraries absent from public pre-training corpora. While Retrieval-Augmented Generation (RAG) offers a training-free alternative by providing static API documentation, we find that such documentation typically provides only isolated definitions, leaving a fundamental knowledge gap. Specifically, LLMs struggle with a task-level lack of coordination patterns between APIs and an API-level misunderstanding of parameter constraints and boundary conditions. To address this, we propose MEMCoder, a novel framework that enables LLMs to autonomously accumulate and evolve Usage Guidelines across these two dimensions. MEMCoder introduces a Multi-dimensional Evolving Memory that captures distilled lessons from the model's own problem-solving trajectories. During inference, MEMCoder employs a dual-source retrieval mechanism to inject both static documentation and relevant historical guidelines into the context. The framework operates in an automated closed loop by using objective execution feedback to reflect on successes and failures, resolve knowledge conflicts, and dynamically update memory. Extensive evaluations on the NdonnxEval and NumbaEval benchmarks demonstrate that MEMCoder substantially enhances existing RAG systems, yielding an average absolute pass@1 gain of 16.31%. Furthermore, MEMCoder exhibits vastly superior domain-specific adaptation compared to existing memory-based continual learning methods.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24222
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation
Li, Mofei
Chen, Taozhi
Yang, Guowei
Li, Jia
Software Engineering
Artificial Intelligence
Computation and Language
Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal private libraries absent from public pre-training corpora. While Retrieval-Augmented Generation (RAG) offers a training-free alternative by providing static API documentation, we find that such documentation typically provides only isolated definitions, leaving a fundamental knowledge gap. Specifically, LLMs struggle with a task-level lack of coordination patterns between APIs and an API-level misunderstanding of parameter constraints and boundary conditions. To address this, we propose MEMCoder, a novel framework that enables LLMs to autonomously accumulate and evolve Usage Guidelines across these two dimensions. MEMCoder introduces a Multi-dimensional Evolving Memory that captures distilled lessons from the model's own problem-solving trajectories. During inference, MEMCoder employs a dual-source retrieval mechanism to inject both static documentation and relevant historical guidelines into the context. The framework operates in an automated closed loop by using objective execution feedback to reflect on successes and failures, resolve knowledge conflicts, and dynamically update memory. Extensive evaluations on the NdonnxEval and NumbaEval benchmarks demonstrate that MEMCoder substantially enhances existing RAG systems, yielding an average absolute pass@1 gain of 16.31%. Furthermore, MEMCoder exhibits vastly superior domain-specific adaptation compared to existing memory-based continual learning methods.
title MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation
topic Software Engineering
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.24222