SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training
SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training explores SWE-Fuse enhances software agent performance by fusing issue-guided and issue-free learning, significantly improving solve rates on real-world software problems.. Commercial viability score: 8/10 in Software Engineering Agents.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $10K - $14K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisSWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code UnderstandingViability: 7.0
- Builds On ThisSWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering AgentsViability: 6.0
- Builds On ThisSWE-Replay: Efficient Test-Time Scaling for Software Engineering AgentsViability: 2.0
- Builds On ThisResolving Java Code Repository Issues with iSWE AgentViability: 3.0
- Builds On ThisLearning Adaptive Parallel Execution for Efficient Code Localization