StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Paper • 2608.17800 • Published Aug 18 • 138
OmniEdu: Open Foundation Models for Learning and Teaching Paper • 2609.23088 • Published 17 days ago • 237
When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference Paper • 2609.04490 • Published Sep 3 • 7