RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild Paper • 2611.02497 • Published 4 days ago • 48
DreamX: Video Diffusion Model is a Universal Latent Action Learner Paper • 2611.05377 • Published 3 days ago • 55
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Paper • 2610.37666 • Published 10 days ago • 58
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory Paper • 2610.26860 • Published 18 days ago • 102
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence Paper • 2609.34563 • Published Sep 28 • 23
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 150
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published Sep 29 • 88
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery Paper • 2609.40340 • Published Sep 30 • 91
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published Sep 30 • 134
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Paper • 2609.39982 • Published Sep 30 • 95
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction Paper • 2609.04201 • Published Sep 3 • 39
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications Paper • 2606.25621 • Published Jun 24 • 20
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking Paper • 2606.22807 • Published Jun 22 • 50
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions Paper • 2606.23654 • Published Jun 22 • 81
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems Paper • 2606.22388 • Published Jun 21 • 93
SWE-Explore: Benchmarking How Coding Agents Explore Repositories Paper • 2606.07297 • Published Jun 5 • 123