Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence Paper • 2608.16590 • Published 4 days ago • 133
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published 2 days ago • 42
Looped Language Models Improve Compositional Tool Calling Paper • 2608.18171 • Published 4 days ago • 15
FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents Paper • 2608.18423 • Published 2 days ago • 15
ASI-Bench: At the Dawn of Artificial Superintelligence Paper • 2608.17271 • Published 3 days ago • 55
ASI-Bench: At the Dawn of Artificial Superintelligence Paper • 2608.17271 • Published 3 days ago • 55
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Paper • 2608.17800 • Published 3 days ago • 8
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Paper • 2608.17800 • Published 3 days ago • 8