SWE-Agent

Princeton · April 2024

activeOpen Sourcetext

Description

Princeton's autonomous software engineering agent that can independently navigate codebases, identify bugs, and submit fixes as pull requests. Introduced a custom agent-computer interface (ACI) optimized for language models to interact with code repositories effectively.

Key Innovations

Agentic
AgenticModels that can autonomously plan, execute multi-step tasks, use tools, and self-correct without human intervention.
Code Gen
Code GenAbility to write, debug, and understand programming code across multiple languages.
Tool Use
Tool UseAbility to call external tools, APIs, and functions — enabling web browsing, code execution, and real-world actions.

External Links