Post
696
Latest work on SWE-Bench ๐
Our two new papers from the SJTU & Huawei: Powered by DeepSeek-V3, we've achieved a new SOTA on the SWE-Bench benchmark!
We introduce two innovative approaches:
โ๏ธ SWE-Debate: AI agents compete and "debate" to generate the best code fix.
๐ง SWE-Exp: An AI agent learns from past repair "experience" to solve new issues more efficiently.
๐ Explore the future of software development:
SWE-Debate
๐ Paper: https://arxiv.org/abs/2507.23348
๐ป Code: https://github.com/YerbaPage/SWE-Debate
SWE-Exp
๐ Paper: https://arxiv.org/abs/2507.23361
๐ป Code: https://github.com/YerbaPage/SWE-Exp
Our two new papers from the SJTU & Huawei: Powered by DeepSeek-V3, we've achieved a new SOTA on the SWE-Bench benchmark!
We introduce two innovative approaches:
โ๏ธ SWE-Debate: AI agents compete and "debate" to generate the best code fix.
๐ง SWE-Exp: An AI agent learns from past repair "experience" to solve new issues more efficiently.
๐ Explore the future of software development:
SWE-Debate
๐ Paper: https://arxiv.org/abs/2507.23348
๐ป Code: https://github.com/YerbaPage/SWE-Debate
SWE-Exp
๐ Paper: https://arxiv.org/abs/2507.23361
๐ป Code: https://github.com/YerbaPage/SWE-Exp