AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards Paper • 2610.18860 • Published 3 days ago • 80
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite Paper • 2610.02826 • Published 14 days ago • 104
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Paper • 2608.17800 • Published Aug 18 • 139
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement Paper • 2609.14857 • Published Sep 14 • 217
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published Sep 14 • 255