FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis Paper • 2608.18580 • Published Aug 19 • 96
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published Aug 4 • 54
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published Aug 4 • 54
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published Aug 4 • 54
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published Aug 4 • 54
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published Jul 29 • 75
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published Jul 29 • 75
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents Paper • 2607.23588 • Published Jul 26 • 127
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory Paper • 2606.08656 • Published Jun 7 • 3
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Paper • 2605.16079 • Published May 15 • 28
Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Paper • 2602.08324 • Published May 15
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents Paper • 2604.17308 • Published Apr 19 • 24
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Paper • 2605.16079 • Published May 15 • 28
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering Paper • 2605.17526 • Published May 17 • 7
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios Paper • 2605.27995 • Published May 27 • 12
ACC: Compiling Agent Trajectories for Long-Context Training Paper • 2605.21850 • Published May 21 • 62
ACC: Compiling Agent Trajectories for Long-Context Training Paper • 2605.21850 • Published May 21 • 62
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering Paper • 2605.17526 • Published May 17 • 7
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering Paper • 2605.17526 • Published May 17 • 7
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Paper • 2605.16079 • Published May 15 • 28