SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
by Princeton NLP / Princeton Language and Intelligence · open-source · Last verified 2026-03-17
Introduces SWE-agent, which defines Agent-Computer Interfaces (ACIs) to enable LLMs to autonomously solve real GitHub issues by browsing codebases, editing files, and running tests. On the SWE-bench benchmark, SWE-agent with GPT-4 Turbo resolves 12.5% of issues, significantly outperforming prior methods.
https://arxiv.org/abs/2405.15793 ↗B
B—Above Average
Adoption: AQuality: AFreshness: B+Citations: B+Engagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- software-engineering, bug-fixing, code-editing, repository-navigation, test-execution
- Integrations
- Use Cases
- automated-bug-fixing, software-development, research
- API Available
- No
- Tags
- agents, software-engineering, code, github, bug-fixing
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
69.3Adoption
80
Quality
89
Freshness
74
Citations
78
Engagement
0
Put AI to work for your business
Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.