Gistify! Codebase-Level Understanding via Runtime Execution

• URL: http://arxiv.org/abs/2510.26790v1
• Date: Thu, 30 Oct 2025 17:58:26 GMT
• Title: Gistify! Codebase-Level Understanding via Runtime Execution
• Authors: Hyunji Lee, Minseon Kim, Chinmay Singh, Matheus Pereira, Atharv Sonwane, Isadora White, Elias Stengel-Eskin, Mohit Bansal, Zhengyan Shi, Alessandro Sordoni, Marc-Alexandre Côté, Xingdi Yuan, Lucas Caccia,
• Abstract summary: We propose Gistify, a task where a coding LLM must create a single, minimal, self-contained file that can reproduce a specific functionality.<n>We show that current state-of-the-art models struggle to reliably solve Gistify tasks, especially ones with long executions.
• Score: 97.63528391679807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As coding agents are increasingly deployed in large codebases, the need to automatically design challenging, codebase-level evaluation is central. We propose Gistify, a task where a coding LLM must create a single, minimal, self-contained file that can reproduce a specific functionality of a codebase. The coding LLM is given full access to a codebase along with a specific entrypoint (e.g., a python command), and the generated file must replicate the output of the same command ran under the full codebase, while containing only the essential components necessary to execute the provided command. Success on Gistify requires both structural understanding of the codebase, accurate modeling of its execution flow as well as the ability to produce potentially large code patches. Our findings show that current state-of-the-art models struggle to reliably solve Gistify tasks, especially ones with long executions traces.

Related papers

• CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion [11.329578913209623]
  Repository-level code completion automatically predicts the unfinished code based on the broader information from the repository.<n>CodeRAG is a framework tailored to identify relevant and necessary knowledge for retrieval-augmented repository-level code completion.
  arXiv  Detail & Related papers  (2025-09-19T15:57:40Z)
• CodeRAG: Supportive Code Retrieval on Bigraph for Real-World Code Generation [69.684886175768]
  Large language models (LLMs) have shown promising performance in automated code generation.<n>In this paper, we propose CodeRAG, a retrieval-augmented code generation framework.<n> Experiments show that CodeRAG achieves significant improvements compared to no RAG scenarios.
  arXiv  Detail & Related papers  (2025-04-14T09:51:23Z)
• LocAgent: Graph-Guided LLM Agents for Code Localization [25.395102705800916]
  LocAgent is a framework that addresses code localization through graph-based representation.<n>Our method with the fine-tuned Qwen-2.5-Coder-Instruct-32B model achieves comparable results to SOTA proprietary models at greatly reduced cost.
  arXiv  Detail & Related papers  (2025-03-12T05:55:01Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs [24.00351065427465]
  We propose a strategy named Hierarchical Context Pruning (HCP) to construct completion prompts with high informational code content. The HCP models the code repository at the function level, maintaining the topological dependencies between code files while removing a large amount of irrelevant code content.
  arXiv  Detail & Related papers  (2024-06-26T12:26:16Z)
• VersiCode: Towards Version-controllable Code Generation [58.82709231906735]
  Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development. We propose two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM) We conduct an extensive evaluation on VersiCode, which reveals that version-controllable code generation is indeed a significant challenge.
  arXiv  Detail & Related papers  (2024-06-11T16:15:06Z)
• SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization [51.67317895094664]
  This paper studies file-level code summarization, which can assist programmers in understanding and maintaining large source code projects. We propose SparseCoder, an identifier-aware sparse transformer for effectively handling long code sequences.
  arXiv  Detail & Related papers  (2024-01-26T09:23:27Z)
• InstructCoder: Instruction Tuning Large Language Models for Code Editing [26.160498475809266]
  We explore the use of Large Language Models (LLMs) to edit code based on user instructions. InstructCoder is the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing. Our findings reveal that open-source LLMs fine-tuned on InstructCoder can significantly enhance the accuracy of code edits.
  arXiv  Detail & Related papers  (2023-10-31T10:15:35Z)
• CodeT5+: Open Code Large Language Models for Code Understanding and Generation [72.1638273937025]
  Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. CodeT5+ is a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning.
  arXiv  Detail & Related papers  (2023-05-13T14:23:07Z)
• Repository-Level Prompt Generation for Large Language Models of Code [28.98699307030983]
  We propose a framework that learns to generate example-specific prompts using prompt proposals. The prompt proposals take context from the entire repository. We conduct experiments on the task of single-line code-autocompletion using code repositories taken from Google Code archives.
  arXiv  Detail & Related papers  (2022-06-26T10:51:25Z)

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.