HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909771008835584 |
|---|---|
| author | Phan, Huy Nhat Nguyen, Tien N. Nguyen, Phong X. Bui, Nghi D. Q. |
| author_facet | Phan, Huy Nhat Nguyen, Tien N. Nguyen, Phong X. Bui, Nghi D. Q. |
| contents | Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planning to final verification. HyperAgent sets new benchmarks in diverse SE tasks, including GitHub issue resolution on the renowned SWE-Bench benchmark, outperforming robust baselines. Furthermore, HyperAgent demonstrates exceptional performance in repository-level code generation (RepoExec) and fault localization and program repair (Defects4J), often surpassing state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16299 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale Phan, Huy Nhat Nguyen, Tien N. Nguyen, Phong X. Bui, Nghi D. Q. Software Engineering Artificial Intelligence Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planning to final verification. HyperAgent sets new benchmarks in diverse SE tasks, including GitHub issue resolution on the renowned SWE-Bench benchmark, outperforming robust baselines. Furthermore, HyperAgent demonstrates exceptional performance in repository-level code generation (RepoExec) and fault localization and program repair (Defects4J), often surpassing state-of-the-art baselines. |
| title | HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2409.16299 |