SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution Paper • 2502.18449 • Published 1 day ago • 34
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution Paper • 2502.18449 • Published 1 day ago • 34
view article Article Blazing-Fast Code Editing via Multi-Layer Speculation By ganler and 3 others • 12 days ago • 15
view article Article Blazing-Fast Code Editing via Multi-Layer Speculation By ganler and 3 others • 12 days ago • 15
Agentless: Demystifying LLM-based Software Engineering Agents Paper • 2407.01489 • Published Jul 1, 2024 • 59
Agentless: Demystifying LLM-based Software Engineering Agents Paper • 2407.01489 • Published Jul 1, 2024 • 59
view article Article StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation Apr 29, 2024 • 76
view article Article StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation Apr 29, 2024 • 76