Collections
Discover the best community collections!
Collections including paper arxiv:2604.08377
-
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Paper • 2605.24117 • Published • 23 -
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Paper • 2605.27366 • Published • 31 -
SkillGrad: Optimizing Agent Skills Like Gradient Descent
Paper • 2605.27760 • Published • 28 -
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Paper • 2605.28424 • Published • 33
-
Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets
Paper • 2604.22294 • Published • 18 -
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 294 -
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
Paper • 2604.17091 • Published • 25
-
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
Paper • 2604.11548 • Published • 22 -
Do AI Coding Agents Log Like Humans? An Empirical Study
Paper • 2604.09409 • Published • 5 -
Spec Kit Agents: Context-Grounded Agentic Workflows
Paper • 2604.05278 • Published • 5 -
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
Paper • 2508.16279 • Published • 68
-
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 137 -
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Paper • 2606.03264 • Published • 28 -
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 265 -
VibeVoice Technical Report
Paper • 2508.19205 • Published • 179
-
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
Paper • 2604.22446 • Published • 126 -
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Paper • 2604.23781 • Published • 34 -
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 294 -
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 264
-
Continuous Adversarial Flow Models
Paper • 2604.11521 • Published • 13 -
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Paper • 2604.11544 • Published • 4 -
Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
Paper • 2604.10905 • Published • 29 -
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Paper • 2604.05333 • Published • 24
-
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 137 -
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Paper • 2606.03264 • Published • 28 -
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 265 -
VibeVoice Technical Report
Paper • 2508.19205 • Published • 179
-
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Paper • 2605.24117 • Published • 23 -
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Paper • 2605.27366 • Published • 31 -
SkillGrad: Optimizing Agent Skills Like Gradient Descent
Paper • 2605.27760 • Published • 28 -
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Paper • 2605.28424 • Published • 33
-
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
Paper • 2604.22446 • Published • 126 -
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Paper • 2604.23781 • Published • 34 -
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 294 -
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 264
-
Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets
Paper • 2604.22294 • Published • 18 -
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 294 -
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
Paper • 2604.17091 • Published • 25
-
Continuous Adversarial Flow Models
Paper • 2604.11521 • Published • 13 -
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Paper • 2604.11544 • Published • 4 -
Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
Paper • 2604.10905 • Published • 29 -
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Paper • 2604.05333 • Published • 24
-
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
Paper • 2604.11548 • Published • 22 -
Do AI Coding Agents Log Like Humans? An Empirical Study
Paper • 2604.09409 • Published • 5 -
Spec Kit Agents: Context-Grounded Agentic Workflows
Paper • 2604.05278 • Published • 5 -
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
Paper • 2508.16279 • Published • 68