Spider: Spatially Informed Dense Embedding Retrieval For Software Issue Localization

Abstract

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 pr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychaudhari2025spider

Related papers

• On The Challenges And Opportunities Of Learned Sparse Retrieval For Code (2026)0.00
• Investigating The Scalability Of Approximate Sparse Retrieval Algorithms To Massive Datasets (2025)5.84
• Practical Code RAG At Scale: Task-aware Retrieval Design Choices Under Compute Budgets (2025)0.00
• Learning Deep Semantic Model For Code Search Using Codesearchnet Corpus (2022)3.16
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• Large Reasoning Embedding Models: Towards Next-generation Dense Retrieval Paradigm (2025)0.00
• Lexsembridge: Fine-grained Dense Representation Enhancement Through Token-aware Embedding Augmentation (2025)2.35
• Evaluating Embedding Apis For Information Retrieval (2023)8.09