ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper • 2604.11784 • Published 3 days ago • 125
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing Paper • 2602.12205 • Published Feb 12 • 81
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 7 days ago • 276
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models Paper • 2603.22212 • Published 24 days ago • 126
Context-Value-Action Architecture for Value-Driven Large Language Model Agents Paper • 2604.05939 • Published 9 days ago • 8
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Paper • 2604.06132 • Published 9 days ago • 114
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published 10 days ago • 107
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings Paper • 2603.13594 • Published Mar 13 • 148
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories Paper • 2602.10809 • Published Feb 11 • 59
PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost Paper • 2603.21383 • Published 25 days ago • 18
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published 30 days ago • 308
AI2 Safety Toolkit Collection Safety data, moderation tools and safe LLMs. • 6 items • Updated Dec 23, 2025 • 9