Incremental Open-Ended Deep Research with Structured Harness Paper • 2610.11566 • Published 6 days ago • 7
Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym Paper • 2609.37267 • Published 15 days ago • 40
Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production Paper • 2609.39963 • Published 14 days ago • 21
Does Native 3D Texture Generation Necessarily Require 3D Assets for Training? Paper • 2609.34621 • Published 16 days ago • 10
SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation Paper • 2608.18565 • Published Aug 19 • 64
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published Aug 14 • 287
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 266
DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments? Paper • 2608.10366 • Published Aug 11 • 11
TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complex Paper • 2607.22143 • Published Aug 4 • 7
ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts Paper • 2607.28993 • Published Jul 31 • 8
3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering Paper • 2608.01185 • Published Aug 2 • 19