ParaTempo: Efficient Parallel Reasoning via Temporal Confidence Paper • 2608.16425 • Published 13 days ago • 38
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring Paper • 2608.09802 • Published 20 days ago • 133
SWE-Explore: Benchmarking How Coding Agents Explore Repositories Paper • 2606.07297 • Published Jun 5 • 123