67 citations · 99 across the 13 of their papers we have counts for
4 papers · 1 filter
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
Yuxiang Wei, Zhiqing Sun, Emily McMilin +6
While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub i…
CWM: An Open-Weights LLM for Research on Code Generation with World Models
FAIR CodeGen team, Jade Copet, Quentin Carbonneaux +48
We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can…
PurpCode: Reasoning for Safer Code Generation
Jiawei Liu, Nirav Diwan, Zhe Wang +11
We introduce PurpCode, the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities. PurpCo…
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Yuxiang Wei, Olivier Duchenne, Jade Copet +6
The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs)…