ParaTempo: Efficient Parallel Reasoning via Temporal Confidence Paper • 2608.16425 • Published Aug 17 • 41
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution Paper • 2608.18933 • Published Aug 19 • 14
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring Paper • 2608.09802 • Published Aug 10 • 85
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding Paper • 2602.01785 • Published Feb 2 • 55
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents Paper • 2601.16746 • Published Jan 23 • 74