StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Paper • 2608.17800 • Published 5 days ago • 9
LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation Paper • 2608.00267 • Published 23 days ago • 3
AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities Paper • 2607.24821 • Published Jul 17 • 18
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks Paper • 2608.01964 • Published 20 days ago • 180
Beacon: Knowing When and How to Perform Agentic Visual Reasoning Paper • 2607.28595 • Published 24 days ago • 55
RefCaptioner: Multi-Reference Image-Grounded Video Captioning Paper • 2607.28509 • Published 24 days ago • 30
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders Paper • 2607.21217 • Published Jul 23 • 7
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Paper • 2607.10350 • Published Jul 15 • 85
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Paper • 2607.10350 • Published Jul 15 • 85
ABot-N1: Toward a General Visual Language Navigation Foundation Model Paper • 2607.10383 • Published Jul 14 • 102
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning Paper • 2607.07708 • Published Jul 8 • 88
Qwen-AgentWorld: Language World Models for General Agents Paper • 2606.24597 • Published Jun 23 • 159
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents Paper • 2606.22883 • Published Jun 22 • 37
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents Paper • 2606.22883 • Published Jun 22 • 37
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 210
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields Paper • 2606.11042 • Published Jun 9 • 22