Roman Wellington
RomanAW
AI & ML interests
None yet
Recent Activity
updated a collection 2 days ago
Agentic Reinforcement Learning updated a collection 2 days ago
Agentic Research updated a collection 2 days ago
Agentic ResearchOrganizations
Agentic Reinforcement Learning
-
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 96 -
Self-Improvements in Modern Agentic Systems: A Survey
Paper • 2607.13104 • Published • 31 -
Loop the Loopies!
Paper • 2607.16051 • Published • 68 -
When Does Muon Help Agentic Reinforcement Learning?
Paper • 2607.16169 • Published • 13
AI Memory
Agent Skills
-
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 260 -
SkillEvolver: Skill Learning as a Meta-Skill
Paper • 2605.10500 • Published • 3 -
SkillGen: Verified Inference-Time Agent Skill Synthesis
Paper • 2605.10999 • Published -
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
Paper • 2605.09341 • Published
Agentic Research
-
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 143 -
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 101 -
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
Paper • 2607.15686 • Published • 15 -
DSWorld: A Data Science World Model for Efficient Autonomous Agents
Paper • 2607.15901 • Published • 10
GraphRAG
LLM Advancements
Agentic Development
Harness Engineering
Agentic Research
-
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 143 -
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 101 -
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
Paper • 2607.15686 • Published • 15 -
DSWorld: A Data Science World Model for Efficient Autonomous Agents
Paper • 2607.15901 • Published • 10
Agentic Reinforcement Learning
-
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 96 -
Self-Improvements in Modern Agentic Systems: A Survey
Paper • 2607.13104 • Published • 31 -
Loop the Loopies!
Paper • 2607.16051 • Published • 68 -
When Does Muon Help Agentic Reinforcement Learning?
Paper • 2607.16169 • Published • 13
GraphRAG
AI Memory
LLM Advancements
Agent Skills
-
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 260 -
SkillEvolver: Skill Learning as a Meta-Skill
Paper • 2605.10500 • Published • 3 -
SkillGen: Verified Inference-Time Agent Skill Synthesis
Paper • 2605.10999 • Published -
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
Paper • 2605.09341 • Published
Agentic Development