Collection by 
25 days ago
Collections
Discover the best community collections!
Collections including paper arxiv:2606.11926
Collection by 
15 days ago
-
Multi-Agent Computer Use
Paper • 2606.01533 • Published • 7 -
OpenSkill: Open-World Self-Evolution for LLM Agents
Paper • 2606.06741 • Published • 29 -
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Paper • 2606.07412 • Published • 12 -
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Paper • 2606.08348 • Published • 16
Collection by 
Jun 11
Collection by 
Jun 15
-
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 225 -
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
Paper • 2604.05091 • Published • 47 -
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 128
Collection by 
12 days ago
-
Open Deep Search: Democratizing Search with Open-source Reasoning Agents
Paper • 2503.20201 • Published • 48 -
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Paper • 2503.19470 • Published • 19 -
Spacer: Towards Engineered Scientific Inspiration
Paper • 2508.17661 • Published • 32 -
DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
Paper • 2509.01396 • Published • 58
Collection by 
9 days ago
-
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 29 -
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 128 -
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 70 -
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Paper • 2606.31551 • Published • 24
Collection by 
3 days ago
Collection by 
Jun 12
-
STEP3-VL-10B Technical Report
Paper • 2601.09668 • Published • 196 -
Advancing Open-source World Models
Paper • 2601.20540 • Published • 135 -
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
Paper • 2512.24615 • Published • 119 -
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Paper • 2602.08234 • Published • 76
Collection by 3 days ago
-
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
Paper • 2506.09790 • Published • 53 -
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance
Paper • 2506.06444 • Published • 73 -
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Paper • 2506.11763 • Published • 74 -
Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research
Paper • 2502.04644 • Published • 4
Collection by 25 days ago
Collection by 9 days ago
-
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 29 -
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 128 -
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 70 -
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Paper • 2606.31551 • Published • 24
Collection by 15 days ago
-
Multi-Agent Computer Use
Paper • 2606.01533 • Published • 7 -
OpenSkill: Open-World Self-Evolution for LLM Agents
Paper • 2606.06741 • Published • 29 -
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Paper • 2606.07412 • Published • 12 -
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Paper • 2606.08348 • Published • 16
Collection by 3 days ago
Collection by Jun 11
Collection by Jun 12
-
STEP3-VL-10B Technical Report
Paper • 2601.09668 • Published • 196 -
Advancing Open-source World Models
Paper • 2601.20540 • Published • 135 -
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
Paper • 2512.24615 • Published • 119 -
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Paper • 2602.08234 • Published • 76
Collection by Jun 15
-
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 225 -
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
Paper • 2604.05091 • Published • 47 -
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 128
Collection by 3 days ago
-
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
Paper • 2506.09790 • Published • 53 -
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance
Paper • 2506.06444 • Published • 73 -
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Paper • 2506.11763 • Published • 74 -
Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research
Paper • 2502.04644 • Published • 4
Collection by 12 days ago
-
Open Deep Search: Democratizing Search with Open-source Reasoning Agents
Paper • 2503.20201 • Published • 48 -
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Paper • 2503.19470 • Published • 19 -
Spacer: Towards Engineered Scientific Inspiration
Paper • 2508.17661 • Published • 32 -
DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
Paper • 2509.01396 • Published • 58