Code Researcher: Deep Research Agent for Large Systems Code and Commit History

• URL: http://arxiv.org/abs/2506.11060v1
• Date: Tue, 27 May 2025 04:57:00 GMT
• Title: Code Researcher: Deep Research Agent for Large Systems Code and Commit History
• Authors: Ramneet Singh, Sathvik Joel, Abhav Mehrotra, Nalin Wadhwa, Ramakrishna B Bairi, Aditya Kanade, Nagarajan Natarajan,
• Abstract summary: Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored.<n>We design the first deep research agent for code, called Code Researcher, and apply it to the problem of generating patches for mitigating crashes reported in systems code.<n>Code Researcher performs multi-step reasoning about semantics, patterns, and commit history of code to gather sufficient context.
• Score: 6.13070170140402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored. Due to the size and complexities of systems code, making changes to a systems codebase is a daunting task, even for humans. It requires researching about many pieces of context, derived from the large codebase and its massive commit history, before making changes. Inspired by the recent progress on deep research agents, we design the first deep research agent for code, called Code Researcher, and apply it to the problem of generating patches for mitigating crashes reported in systems code. Code Researcher performs multi-step reasoning about semantics, patterns, and commit history of code to gather sufficient context. The context is stored in a structured memory which is used for synthesizing a patch. We evaluate Code Researcher on kBenchSyz, a benchmark of Linux kernel crashes, and show that it significantly outperforms strong baselines, achieving a crash-resolution rate of 58%, compared to 37.5% by SWE-agent. On an average, Code Researcher explores 10 files in each trajectory whereas SWE-agent explores only 1.33 files, highlighting Code Researcher's ability to deeply explore the codebase. Through another experiment on an open-source multimedia software, we show the generalizability of Code Researcher. Our experiments highlight the importance of global context gathering and multi-faceted reasoning for large codebases.

Related papers

• MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios [0.0]
  We introduce MultiAIGCD, a dataset for AI-generated code detection for Python, Java, and Go.<n>Overall, MultiAIGCD consists of 121,271 AI-generated and 32,148 human-written code snippets.
  arXiv  Detail & Related papers  (2025-07-29T11:16:55Z)
• MGS3: A Multi-Granularity Self-Supervised Code Search Framework [22.214324677526132]
  We introduce a novel Multi-Granularity Self-Supervised contrastive learning code Search framework (MGS$3$)<n>First, MGS$3$ features a Supervised Multi-Granularity Representation module (HMGR), which aggregates fine-grained information into coarser-grained representations.<n>We conduct extensive experiments on code search benchmarks across various granularities, demonstrating that the framework exhibits outstanding performance in code search tasks of multiple granularities.
  arXiv  Detail & Related papers  (2025-05-30T06:49:39Z)
• Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning [57.09163579304332]
  We introduce PaperCoder, a framework that transforms machine learning papers into functional code repositories.<n>PaperCoder operates in three stages: planning, designs the system architecture with diagrams, identifies file dependencies, and generates configuration files.<n>We then evaluate PaperCoder on generating code implementations from machine learning papers based on both model-based and human evaluations.
  arXiv  Detail & Related papers  (2025-04-24T01:57:01Z)
• CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval [103.116634967815]
  We introduce CodeXEmbed, a family of large-scale code embedding models ranging from 400M to 7B parameters. Our novel training pipeline unifies multiple programming languages and transforms various code-related tasks into a common retrieval framework. Our 7B model sets a new state-of-the-art (SOTA) in code retrieval, outperforming the previous leading model, Voyage-Code, by over 20% on CoIR benchmark.
  arXiv  Detail & Related papers  (2024-11-19T16:54:45Z)
• CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models [106.11371409170818]
  Large language models (LLMs) can act as agents with capabilities to self-refine and improve generated code autonomously. We propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions.
  arXiv  Detail & Related papers  (2024-11-07T00:09:54Z)
• CoIR: A Comprehensive Benchmark for Code Information Retrieval Models [52.61625841028781]
  COIR (Code Information Retrieval Benchmark) is a robust and comprehensive benchmark designed to assess code retrieval capabilities.<n>COIR comprises ten meticulously curated code datasets, spanning eight distinctive retrieval tasks across seven diverse domains.<n>We evaluate nine widely used retrieval models using COIR, uncovering significant difficulties in performing code retrieval tasks even with state-of-the-art systems.
  arXiv  Detail & Related papers  (2024-07-03T07:58:20Z)
• Enhancing Semantic Code Search with Multimodal Contrastive Learning and Soft Data Augmentation [50.14232079160476]
  We propose a new approach with multimodal contrastive learning and soft data augmentation for code search. We conduct extensive experiments to evaluate the effectiveness of our approach on a large-scale dataset with six programming languages.
  arXiv  Detail & Related papers  (2022-04-07T08:49:27Z)
• DeSkew-LSH based Code-to-Code Recommendation Engine [3.7011129410662558]
  We present emphSenatus, a new code-to-code recommendation engine for machine learning on source code. At the core of Senatus is emphDe-Skew LSH, a new locality sensitive hashing algorithm that indexes the data for fast (sub-linear time) retrieval. We show Senatus improves performance by 6.7% F1 and query time 16x is faster compared to Facebook Aroma on the task of code-to-code recommendation.
  arXiv  Detail & Related papers  (2021-11-05T16:56:28Z)
• COSEA: Convolutional Code Search with Layer-wise Attention [90.35777733464354]
  We propose a new deep learning architecture, COSEA, which leverages convolutional neural networks with layer-wise attention to capture the code's intrinsic structural logic. COSEA can achieve significant improvements over state-of-the-art methods on code search tasks.
  arXiv  Detail & Related papers  (2020-10-19T13:53:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.