用记忆增强的多级信心机制，解决Python依赖难题
MEMRES: A Memory-Augmented Resolver with Confidence Cascade for Agentic Python Dependency Resolution
- 构建记忆库与错误模式知识库，优先规则匹配而非直接调用大模型
- 在2890个代码片段中成功解析86.6%，远超现有方法
- 适合需要稳定依赖解析的开发工具链或自动化脚本系统
我们提出MEMRES，一种用于Python依赖解析的智能体系统，引入多级信心级联机制，将大语言模型作为最终求助手段。系统融合四项能力：(1) 自进化记忆库，通过提示和捷径积累可复用的解析模式；(2) 包含200+经筛选的导入-包映射的错误模式知识库；(3) 语义导入分析器；(4) 针对Python 2的启发式检测器，解决最大失败类别。在HG2.9K数据集上，使用Gemma-2 9B（10 GB VRAM），MEMRES成功解析2503/2890（86.6%，10次运行平均）代码片段，结合会话内记忆与信心级联处理剩余问题。该表现显著优于PLLM的54.7%整体成功率。
原文摘要 · Abstract (English)
We present MEMRES, an agentic system for Python dependency resolution that introduces a multi-level confidence cascade where the LLM serves as the last resort. Our system combines: (1) a Self-Evolving Memory that accumulates reusable resolution patterns via tips and shortcuts; (2) an Error Pattern Knowledge Base with 200+ curated import-to-package mappings; (3) a Semantic Import Analyzer; and (4) a Python 2 heuristic detector resolving the largest failure category. On HG2.9K using Gemma-2 9B (10 GB VRAM). MEMRES resolves 2503 of 2890 (86.6%, 10-run average) snippets, combining intra-session memory with our confidence cascade for the remainder. This already exceeds PLLM's 54.7% overall success rate by a wide margin.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。