RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents Paper • 2609.22000 • Published 5 days ago • 68
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? Paper • 2608.19799 • Published Aug 20 • 67
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Paper • 2604.11297 • Published Apr 13 • 144
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning Paper • 2603.21065 • Published Mar 22 • 80
FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation Paper • 2601.23182 • Published Jan 30 • 21
AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts Paper • 2601.20730 • Published Jan 28 • 22
TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization Paper • 2601.16480 • Published Jan 23 • 50
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published Jan 22 • 92
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published Jan 22 • 92
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published Jan 22 • 92
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published Jan 21 • 75