Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving
Yue Pan, Zimin Chen, Siyu Lu, Zhaoyang Chu, Xiang Li, Han Li, Yang Feng, Claire Le Goues, Federica Sarro, Martin Monperrus, He Ye

TL;DR
Prometheus is a memory-centric coding agent framework that improves long-horizon codebase navigation and repository-level problem solving by maintaining contextual continuity and leveraging a knowledge graph, leading to state-of-the-art issue resolution performance.
Contribution
It introduces a memory-enhanced, knowledge graph-based approach for long-horizon code navigation, addressing the limitations of stateless agents and improving scalability in repository-level tasks.
Findings
Achieves 74.4% and 33.8% resolution rates on SWE-bench benchmarks.
Ranks Top-6 and Top-1 among open-source systems.
Demonstrates effective long-horizon reasoning with memory and knowledge graph integration.
Abstract
Large Language Models (LLMs) have shown remarkable capabilities in automating software engineering tasks, spurring the emergence of coding agents that scaffold LLMs with external tools to resolve repository-level problems. However, existing agents still struggle to navigate large-scale codebases, as the Needle-in-a-Haystack problem persists even with million-token context windows, where relevant evidence is often overwhelmed by large volumes of irrelevant code and documentation. Prior codebase navigation approaches, including embedding-based retrieval, file-system exploration, and graph-based retrieval, address parts of this challenge but fail to capture the temporal continuity of agent reasoning, rendering agents stateless and causing repeated repository traversals that hinder scalable planning and reasoning. To address these limitations, we present Prometheus, a memory-centric coding…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
