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.
Cite
@article{arxiv.2604.16941,
title = {MEMRES: A Memory-Augmented Resolver with Confidence Cascade for Agentic Python Dependency Resolution},
author = {Dao Sy Duy Minh and Tran Chi Nguyen and Trung Kiet Huynh and Pham Phu Hoa and Nguyen Lam Phu Quy and Vu Nguyen},
journal= {arXiv preprint arXiv:2604.16941},
year = {2026}
}
Comments
4 pages, 1 figure, to appear in Proc. FSE Companion '26