Collection by 
19 days ago
Collections
Discover the best community collections!
Collections including paper arxiv:2606.24937
Collection by 
21 days ago
Collection by 
23 days ago
Collection by 
11 days ago
-
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Paper • 2606.02373 • Published • 60 -
SIA: Self Improving AI with Harness & Weight Updates
Paper • 2605.27276 • Published • 16 -
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
Paper • 2606.06036 • Published • 75 -
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Paper • 2606.14249 • Published • 50
Collection by 
about 1 hour ago
Collection by 
21 days ago
Collection by 
22 days ago
Collection by 
23 days ago
Collection by 
3 days ago
-
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Paper • 2604.15574 • Published • 26 -
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 71 -
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Paper • 2604.24819 • Published • 91 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 112
Collection by 
5 days ago
-
AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
Paper • 2602.17100 • Published • 4 -
GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
Paper • 2603.01059 • Published • 1 -
Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models
Paper • 2603.00618 • Published -
Heterogeneous Agent Collaborative Reinforcement Learning
Paper • 2603.02604 • Published • 198
Collection by 19 days ago
Collection by 21 days ago
Collection by 21 days ago
Collection by 22 days ago
Collection by 23 days ago
Collection by 23 days ago
Collection by 11 days ago
-
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Paper • 2606.02373 • Published • 60 -
SIA: Self Improving AI with Harness & Weight Updates
Paper • 2605.27276 • Published • 16 -
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
Paper • 2606.06036 • Published • 75 -
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Paper • 2606.14249 • Published • 50
Collection by 3 days ago
-
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Paper • 2604.15574 • Published • 26 -
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 71 -
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Paper • 2604.24819 • Published • 91 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 112
Collection by about 1 hour ago
Collection by 5 days ago
-
AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
Paper • 2602.17100 • Published • 4 -
GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
Paper • 2603.01059 • Published • 1 -
Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models
Paper • 2603.00618 • Published -
Heterogeneous Agent Collaborative Reinforcement Learning
Paper • 2603.02604 • Published • 198