-
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 156 -
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 103 -
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
Paper • 2607.15686 • Published • 12 -
DSWorld: A Data Science World Model for Efficient Autonomous Agents
Paper • 2607.15901 • Published • 7
Collections
Discover the best community collections!
Collections including paper arxiv:2603.20278
-
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 103 -
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
Paper • 2603.22847 • Published • 18 -
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
Paper • 2604.01007 • Published • 28
-
FlowRL: Matching Reward Distributions for LLM Reasoning
Paper • 2509.15207 • Published • 119 -
Kwaipilot/KAT-Dev-72B-Exp
Text Generation • 73B • Updated • 262 • • 158 -
Agentic Entropy-Balanced Policy Optimization
Paper • 2510.14545 • Published • 109 -
Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
Paper • 2511.13288 • Published • 20
-
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 52 -
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Paper • 2604.04804 • Published • 29 -
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Paper • 2604.14228 • Published • 24 -
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
Paper • 2604.15093 • Published • 30
-
Efficient Agents: Building Effective Agents While Reducing Cost
Paper • 2508.02694 • Published • 85 -
Agentic AI Frameworks: Architectures, Protocols, and Design Challenges
Paper • 2508.10146 • Published -
Kimi K2.5: Visual Agentic Intelligence
Paper • 2602.02276 • Published • 277 -
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Paper • 2601.21558 • Published • 61
-
openai/gpt-oss-120b
Text Generation • 117B • Updated • 2.41M • • 5.5k -
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
Paper • 2512.20605 • Published • 62 -
Nested Browser-Use Learning for Agentic Information Seeking
Paper • 2512.23647 • Published • 19 -
TimeBill: Time-Budgeted Inference for Large Language Models
Paper • 2512.21859 • Published • 25
-
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 156 -
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 103 -
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
Paper • 2607.15686 • Published • 12 -
DSWorld: A Data Science World Model for Efficient Autonomous Agents
Paper • 2607.15901 • Published • 7
-
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 52 -
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Paper • 2604.04804 • Published • 29 -
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Paper • 2604.14228 • Published • 24 -
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
Paper • 2604.15093 • Published • 30
-
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 103 -
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
Paper • 2603.22847 • Published • 18 -
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
Paper • 2604.01007 • Published • 28
-
Efficient Agents: Building Effective Agents While Reducing Cost
Paper • 2508.02694 • Published • 85 -
Agentic AI Frameworks: Architectures, Protocols, and Design Challenges
Paper • 2508.10146 • Published -
Kimi K2.5: Visual Agentic Intelligence
Paper • 2602.02276 • Published • 277 -
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Paper • 2601.21558 • Published • 61
-
FlowRL: Matching Reward Distributions for LLM Reasoning
Paper • 2509.15207 • Published • 119 -
Kwaipilot/KAT-Dev-72B-Exp
Text Generation • 73B • Updated • 262 • • 158 -
Agentic Entropy-Balanced Policy Optimization
Paper • 2510.14545 • Published • 109 -
Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
Paper • 2511.13288 • Published • 20
-
openai/gpt-oss-120b
Text Generation • 117B • Updated • 2.41M • • 5.5k -
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
Paper • 2512.20605 • Published • 62 -
Nested Browser-Use Learning for Agentic Information Seeking
Paper • 2512.23647 • Published • 19 -
TimeBill: Time-Budgeted Inference for Large Language Models
Paper • 2512.21859 • Published • 25