SpecRover: Code Intent Extraction via LLMs
- URL: http://arxiv.org/abs/2408.02232v3
- Date: Thu, 22 Aug 2024 11:54:20 GMT
- Title: SpecRover: Code Intent Extraction via LLMs
- Authors: Haifeng Ruan, Yuntong Zhang, Abhik Roychoudhury,
- Abstract summary: specification inference can be useful for producing high quality program patches.
Our approach SpecRover (AutoCodeRover-v2) is built on the open-source LLM agent AutoCodeRover.
In an evaluation on the full SWE-Bench consisting of 2294 GitHub issues, it shows more than 50% improvement in efficacy over AutoCodeRover.
- Score: 7.742980618437681
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Autonomous program improvement typically involves automatically producing bug fixes and feature additions. Such program improvement can be accomplished by a combination of large language model (LLM) and program analysis capabilities, in the form of an LLM agent. Since program repair or program improvement typically requires a specification of intended behavior - specification inference can be useful for producing high quality program patches. In this work, we examine efficient and low-cost workflows for iterative specification inference within an LLM agent. Given a GitHub issue to be resolved in a software project, our goal is to conduct iterative code search accompanied by specification inference - thereby inferring intent from both the project structure and behavior. The intent thus captured is examined by a reviewer agent with the goal of vetting the patches as well as providing a measure of confidence in the vetted patches. Our approach SpecRover (AutoCodeRover-v2) is built on the open-source LLM agent AutoCodeRover. In an evaluation on the full SWE-Bench consisting of 2294 GitHub issues, it shows more than 50% improvement in efficacy over AutoCodeRover. Compared to the open-source agents available, our work shows modest cost ($0.65 per issue) in resolving an average GitHub issue in SWE-Bench lite. The production of explanation by SpecRover allows for a better "signal" to be given to the developer, on when the suggested patches can be accepted with confidence. SpecRover also seeks to demonstrate the continued importance of specification inference in automated program repair, even as program repair technologies enter the LLM era.
Related papers
- Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios [13.949319911378826]
This study evaluated 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues.
No single agent dominated, with 170 issues unresolved, indicating room for improvement.
Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities.
Some agents increased code complexity, many reduced code duplication and minimized code smells.
arXiv Detail & Related papers (2024-10-16T11:33:57Z) - Agentless: Demystifying LLM-based Software Engineering Agents [12.19683999553113]
We build Agentless -- an agentless approach to automatically solve software development problems.
Compared to the verbose and complex setup of agent-based approaches, Agentless employs a simplistic three-phase process of localization, repair, and patch validation.
Our results on the popular SWE-bench Lite benchmark show that surprisingly the simplistic Agentless is able to achieve both the highest performance and low cost.
arXiv Detail & Related papers (2024-07-01T17:24:45Z) - Agent-Driven Automatic Software Improvement [55.2480439325792]
This research proposal aims to explore innovative solutions by focusing on the deployment of agents powered by Large Language Models (LLMs)
The iterative nature of agents, which allows for continuous learning and adaptation, can help surpass common challenges in code generation.
We aim to use the iterative feedback in these systems to further fine-tune the LLMs underlying the agents, becoming better aligned to the task of automated software improvement.
arXiv Detail & Related papers (2024-06-24T15:45:22Z) - 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) - AutoCodeRover: Autonomous Program Improvement [8.66280420062806]
We propose an automated approach for solving GitHub issues to autonomously achieve program improvement.
In our approach called AutoCodeRover, LLMs are combined with sophisticated code search capabilities, ultimately leading to a program modification or patch.
Experiments on SWE-bench-lite (300 real-life GitHub issues) show increased efficacy in solving GitHub issues (19% on SWE-bench-lite), which is higher than the efficacy of the recently reported SWE-agent.
arXiv Detail & Related papers (2024-04-08T11:55:09Z) - Assured LLM-Based Software Engineering [51.003878077888686]
This paper is an outline of the content of the keynote by Mark Harman at the International Workshop on Interpretability, Robustness, and Benchmarking in Neural Software Engineering, Monday 15th April 2024, Lisbon, Portugal.
arXiv Detail & Related papers (2024-02-06T20:38:46Z) - A Novel Approach for Automatic Program Repair using Round-Trip
Translation with Large Language Models [50.86686630756207]
Research shows that grammatical mistakes in a sentence can be corrected by translating it to another language and back.
Current generative models for Automatic Program Repair (APR) are pre-trained on source code and fine-tuned for repair.
This paper proposes bypassing the fine-tuning step and using Round-Trip Translation (RTT): translation of code from one programming language to another programming or natural language, and back.
arXiv Detail & Related papers (2024-01-15T22:36:31Z) - ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks.
To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
arXiv Detail & Related papers (2023-11-16T12:03:21Z) - RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic
Program Repair [75.40584530380589]
We propose a novel Retrieval-Augmented Patch Generation framework (RAP-Gen)
RAP-Gen explicitly leveraging relevant fix patterns retrieved from a list of previous bug-fix pairs.
We evaluate RAP-Gen on three benchmarks in two programming languages, including the TFix benchmark in JavaScript, and Code Refinement and Defects4J benchmarks in Java.
arXiv Detail & Related papers (2023-09-12T08:52:56Z) - Copiloting the Copilots: Fusing Large Language Models with Completion
Engines for Automated Program Repair [15.391586175711907]
Large Language Models (LLMs) have been shown to be helpful "copilots" in assisting developers with various coding tasks.
We propose Repilot, a general code generation framework to further copilot the AI "copilots" (i.e., LLMs) by synthesizing more valid patches during the repair process.
Our evaluation on a subset of the widely-used Defects4j 1.2 and 2.0 datasets shows that Repilot outperforms state-of-the-art techniques by fixing 27% and 47% more bugs, respectively.
arXiv Detail & Related papers (2023-09-01T17:54:14Z)
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.