Search papers, labs, and topics across Lattice.
Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence Fudan University, The Corresponding Author. School of Mathematical Sciences, Key Laboratory of Intelligent Computing and Applications (Ministry of Education), Tongji University, Shanghai, China (wangw@tongji.edu.cn). W. Wang is supported by Natural Science Foundation of Shanghai (22ZR1465300)
2
0
2
0
Failure-driven post-training, combined with a meticulously curated 10M token STEM dataset, unlocks a 4.68% performance boost in LLM reasoning, proving that strategic data synthesis around model weaknesses is a powerful path to improvement.
An open-source ecosystem for agentic learning, complete with a trained agent and novel policy optimization, promises to accelerate research by providing a standardized, scalable platform.
