Collection by 
about 10 hours ago
Collections
Discover the best community collections!
Collections including paper arxiv:2608.27454
Collection by 
14 days ago
Collection by 
21 days ago
Collection by 
3 days ago
-
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 79 -
Modular Cognitive Architecture Emerges in Large Language Models
Paper • 2608.13567 • Published • 16 -
Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition
Paper • 2607.26179 • Published • 1 -
Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept
Paper • 2607.20995 • Published • 1
Collection by 
1 day ago
-
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 89 -
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 67 -
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Paper • 2605.10912 • Published • 36 -
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
Paper • 2605.13941 • Published • 15
Collection by 
13 days ago
-
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Paper • 2608.27454 • Published • 34 -
SKILL-KD: Contrastive Skill Distillation for LLM Agents
Paper • 2607.28048 • Published • 14 -
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
Paper • 2608.15071 • Published -
Learning Globally Reusable Skills for Coding Agents
Paper • 2608.06153 • Published
Collection by 
18 days ago
Collection by 
about 20 hours ago
Collection by 
5 days ago
-
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Paper • 2606.29538 • Published • 143 -
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
Paper • 2608.02287 • Published • 31 -
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Paper • 2608.05139 • Published • 27 -
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
Paper • 2608.11079 • Published • 16
Collection by 
2 days ago
Collection by about 10 hours ago
Collection by 13 days ago
-
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Paper • 2608.27454 • Published • 34 -
SKILL-KD: Contrastive Skill Distillation for LLM Agents
Paper • 2607.28048 • Published • 14 -
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
Paper • 2608.15071 • Published -
Learning Globally Reusable Skills for Coding Agents
Paper • 2608.06153 • Published
Collection by 14 days ago
Collection by 18 days ago
Collection by 21 days ago
Collection by about 20 hours ago
Collection by 3 days ago
-
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 79 -
Modular Cognitive Architecture Emerges in Large Language Models
Paper • 2608.13567 • Published • 16 -
Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition
Paper • 2607.26179 • Published • 1 -
Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept
Paper • 2607.20995 • Published • 1
Collection by 5 days ago
-
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Paper • 2606.29538 • Published • 143 -
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
Paper • 2608.02287 • Published • 31 -
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Paper • 2608.05139 • Published • 27 -
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
Paper • 2608.11079 • Published • 16
Collection by 1 day ago
-
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 89 -
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 67 -
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Paper • 2605.10912 • Published • 36 -
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
Paper • 2605.13941 • Published • 15
Collection by 2 days ago