MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents Paper • 2601.12346 • Published 6 days ago • 45
Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge Paper • 2601.08808 • Published 11 days ago • 37
ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models Paper • 2601.11404 • Published 8 days ago • 24
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5 Paper • 2601.10527 • Published 9 days ago • 23
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders Paper • 2601.10332 • Published 9 days ago • 28
Controlled Self-Evolution for Algorithmic Code Optimization Paper • 2601.07348 • Published 12 days ago • 110
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation Paper • 2601.09688 • Published 10 days ago • 123
Dr. Zero: Self-Evolving Search Agents without Training Data Paper • 2601.07055 • Published 13 days ago • 20
What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models Paper • 2601.06165 • Published 17 days ago • 16
MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era Paper • 2601.07526 • Published 12 days ago • 21