DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published 8 days ago • 152
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory Paper • 2604.01007 • Published 3 days ago • 19
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Paper • 2603.24414 • Published 10 days ago • 173
MemRerank: Preference Memory for Personalized Product Reranking Paper • 2603.29247 • Published 5 days ago • 4
LongCat-Next: Lexicalizing Modalities as Discrete Tokens Paper • 2603.27538 • Published 6 days ago • 131
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Paper • 2603.19835 • Published 15 days ago • 312
EpochX: Building the Infrastructure for an Emergent Agent Civilization Paper • 2603.27304 • Published 7 days ago • 46
Emergent Social Intelligence Risks in Generative Multi-Agent Systems Paper • 2603.27771 • Published 6 days ago • 48
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution Paper • 2603.18718 • Published 16 days ago • 10
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens Paper • 2603.23516 • Published 30 days ago • 45
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models Paper • 2603.22212 • Published 12 days ago • 124
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? Paper • 2603.15401 • Published 19 days ago • 18
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent Paper • 2603.13875 • Published 21 days ago • 34
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation Paper • 2603.16871 • Published 18 days ago • 60