IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Paper • 2609.29444 • Published 6 days ago • 20
Emergent Collusion in Long-Horizon LLM Agent Interaction Paper • 2609.24967 • Published 9 days ago • 19
Paint-Anything: Unified Any-Color Control for Image Generation and Editing Paper • 2609.20816 • Published 13 days ago • 57
VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering Paper • 2609.19879 • Published 13 days ago • 33
An Empirical Study of Harness Design for Coding Agents Paper • 2609.20804 • Published 13 days ago • 91
JEPA-Anything: Learning Predictive Models across Different Worlds Paper • 2609.20800 • Published 13 days ago • 75
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published 15 days ago • 811
BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender Paper • 2609.15478 • Published 16 days ago • 34
Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs Paper • 2609.10355 • Published 21 days ago • 18
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Paper • 2609.07064 • Published 23 days ago • 147