LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents Paper • 2606.06087 • Published Jun 4 • 67
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published May 28 • 144
OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents Paper • 2605.28158 • Published May 27 • 6
Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents Paper • 2605.25971 • Published May 25 • 16
MMSkills: Towards Multimodal Skills for General Visual Agents Paper • 2605.13527 • Published May 14 • 122
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization Paper • 2604.09574 • Published Feb 24 • 30
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering Paper • 2604.08224 • Published Apr 9 • 53
MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios Paper • 2603.09983 • Published Feb 12 • 3
PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval Paper • 2603.01493 • Published Mar 2 • 21
MuonRec: Shifting the Optimizer Paradigm Beyond Adam in Scalable Generative Recommendation Paper • 2603.00416 • Published Feb 28 • 20