GUI-G^2: Gaussian Reward Modeling for GUI Grounding
Paper • 2507.15846 • Published • 135
Agents
-
-
WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
Paper • 2508.05748 • Published • 142 -
Mobile-Agent-v3: Foundamental Agents for GUI Automation
Paper • 2508.15144 • Published • 65 -
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 162 -
DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
Paper • 2509.01396 • Published • 58 -
Agentic Entropy-Balanced Policy Optimization
Paper • 2510.14545 • Published • 107 -
DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
Paper • 2510.16872 • Published • 112 -
DeepAgent: A General Reasoning Agent with Scalable Toolsets
Paper • 2510.21618 • Published • 102 -
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
Paper • 2510.23587 • Published • 67 -
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Paper • 2510.25726 • Published • 46 -
Scaling Latent Reasoning via Looped Language Models
Paper • 2510.25741 • Published • 229 -
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Paper • 2512.02395 • Published • 50 -
Adaptation of Agentic AI
Paper • 2512.16301 • Published • 108 -
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
Paper • 2601.05432 • Published • 169 -
Kimi K2.5: Visual Agentic Intelligence
Paper • 2602.02276 • Published • 259 -
Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
Paper • 2601.22060 • Published • 155 -
Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation
Paper • 2602.01756 • Published • 23 -
Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning
Paper • 2602.09439 • Published • 13 -
Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling
Paper • 2602.09084 • Published • 27 -
PyVision-RL: Forging Open Agentic Vision Models via RL
Paper • 2602.20739 • Published • 31 -
AI Can Learn Scientific Taste
Paper • 2603.14473 • Published • 261 -
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
Paper • 2603.13594 • Published • 139 -
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
Paper • 2603.15594 • Published • 137