Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents Paper β’ 2602.16855 β’ Published Feb 15 β’ 51
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper β’ 2604.11784 β’ Published 9 days ago β’ 141
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing Paper β’ 2602.12205 β’ Published Feb 12 β’ 81
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper β’ 2604.08377 β’ Published 13 days ago β’ 282
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models Paper β’ 2603.22212 β’ Published 29 days ago β’ 126
Context-Value-Action Architecture for Value-Driven Large Language Model Agents Paper β’ 2604.05939 β’ Published 15 days ago β’ 9
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Paper β’ 2604.06132 β’ Published 15 days ago β’ 115
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper β’ 2604.04921 β’ Published 16 days ago β’ 109
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings Paper β’ 2603.13594 β’ Published Mar 13 β’ 148
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories Paper β’ 2602.10809 β’ Published Feb 11 β’ 59
PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost Paper β’ 2603.21383 β’ Published 30 days ago β’ 18
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper β’ 2603.16790 β’ Published Mar 17 β’ 308
AI2 Safety Toolkit Collection Safety data, moderation tools and safe LLMs. β’ 6 items β’ Updated Dec 23, 2025 β’ 9