When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning Paper • 2602.10560 • Published 10 days ago • 28
BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation Paper • 2602.09849 • Published 11 days ago • 16
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning Paper • 2602.10090 • Published 10 days ago • 49
Chain of Mindset: Reasoning with Adaptive Cognitive Modes Paper • 2602.10063 • Published 10 days ago • 70
Code2World: A GUI World Model via Renderable Code Generation Paper • 2602.09856 • Published 11 days ago • 190
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published 16 days ago • 320
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper • 2602.10604 • Published 10 days ago • 178
Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments Paper • 2602.01244 • Published 20 days ago • 15
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent Paper • 2602.03955 • Published 17 days ago • 8
LatentMem: Customizing Latent Memory for Multi-Agent Systems Paper • 2602.03036 • Published 18 days ago • 14
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods Paper • 2601.21821 • Published 23 days ago • 59
DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding Paper • 2601.23161 • Published 22 days ago • 10
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing Paper • 2601.21957 • Published 23 days ago • 19
AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning Paper • 2601.18631 • Published 26 days ago • 47
DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints Paper • 2601.18137 • Published 26 days ago • 26
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs Paper • 2601.17058 • Published 30 days ago • 188
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents Paper • 2601.16746 • Published 29 days ago • 89
SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer Paper • 2601.16515 • Published 29 days ago • 15