SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution Paper • 2607.26784 • Published 13 days ago • 28
Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability Paper • 2607.26637 • Published 13 days ago • 14
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them Paper • 2607.27703 • Published 12 days ago • 25
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published 12 days ago • 302
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents Paper • 2607.28229 • Published 11 days ago • 12
One Future, Every Robot: Label-Efficient Collective-State Prediction with Decentralized JEPA Paper • 2607.28443 • Published 12 days ago • 9
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction Paper • 2607.29677 • Published 11 days ago • 23
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Paper • 2608.00155 • Published 11 days ago • 13
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities? Paper • 2608.03874 • Published 7 days ago • 14
MaLA corpus Collection MaLA Corpus for Massive Language Adaptation of Large Language Models https://mala-lm.github.io • 9 items • Updated Jun 29 • 8
EgoCS-400K: An Egocentric Gameplay Dataset for World Models Paper • 2606.18180 • Published Jun 16 • 16
LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching Paper • 2606.16428 • Published Jun 15 • 40
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published Jun 11 • 111
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain Paper • 2605.23895 • Published May 22 • 54
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning Paper • 2606.03603 • Published Jun 2 • 30
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts Paper • 2606.02404 • Published Jun 1 • 59