# MEMRES: A Memory-Augmented Resolver with Confidence Cascade for Agentic Python Dependency Resolution

arXiv: https://arxiv.org/abs/2604.16941 · HTML: https://mlsanity.com/paper/2604.16941/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 8 of 8)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [Repo2Run: Automated Building Executable Environment for Code Repository at Scale](https://mlsanity.com/paper/2502.13681/) (2025)
- [DependEval: Benchmarking LLMs for Repository Dependency Understanding](https://mlsanity.com/paper/2503.06689/) (2025)
- [DockerizeMe: Automatic Inference of Environment Dependencies for Python Code Snippets](https://mlsanity.com/paper/1905.11127/) (2019)
- [The Last Dependency Crusade: Solving Python Dependency Conflicts with LLMs](https://mlsanity.com/paper/2501.16191/) (2025)
- [V2: Fast Detection of Configuration Drift in Python](https://mlsanity.com/paper/1909.06251/) (2019)

## Built on by (most cited first, 1 of 1)

- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

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.