Saved in:
Bibliographic Details
Main Authors: Chaudhari, Shravan, Jacob, Rahul Thomas, Goswami, Mononito, Cao, Jiajun, Rashid, Shihab, Bock, Christian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.16956
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Retrieving code functions, classes or files that are relevant in order to solve a given user query, bug report or feature request from large codebases is a fundamental challenge for Large Language Model (LLM)-based coding agents. Agentic approaches typically employ sparse retrieval methods like BM25 or dense embedding strategies to identify semantically relevant units. While embedding-based approaches can outperform BM25 by large margins, they often don't take into consideration the underlying graph-structured characteristics of the codebase. To address this, we propose SpIDER (Spatially Informed Dense Embedding Retrieval), an enhanced dense retrieval approach that integrates LLM-based reasoning along with auxiliary information obtained from graph-based exploration of the codebase. We further introduce SpIDER-Bench, a graph-structured evaluation benchmark curated from SWE-PolyBench, SWEBench-Verified and Multi-SWEBench, spanning codebases from Python, Java, JavaScript and TypeScript programming languages. Empirical results show that SpIDER consistently improves dense retrieval performance by at least 13% across programming languages and benchmarks in SpIDER-Bench.