SEGAgentRL

non-profit

AI & ML interests

We target improved agent reinforcement learning in terms of stability (S), efficiency (E), and generalization (G).

Recent Activity

dwenlong authored a paper about 21 hours ago

DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models

dwenlong authored a paper about 21 hours ago

MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

dwenlong authored a paper about 21 hours ago

Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning

View all activity

Collections 1

models 10

SEGAgentRL/LLDS-A-GRPO-Llama3.2-3B-Base-MA

Reinforcement Learning • 4B • Updated 22 days ago • 9

SEGAgentRL/LLDS-A-GRPO-Qwen2.5-3B-Ins

Reinforcement Learning • 3B • Updated 23 days ago • 31

SEGAgentRL/LLDS-R-GRPO-Qwen2.5-3B-Base

Reinforcement Learning • 3B • Updated 23 days ago • 23 • 1

SEGAgentRL/LLDS-R-GSPO-Qwen2.5-3B-Ins

Reinforcement Learning • 3B • Updated 23 days ago • 28 • 1

SEGAgentRL/LLDS-A-GSPO-Qwen2.5-3B-Ins

Reinforcement Learning • 3B • Updated 23 days ago • 34 • 1

SEGAgentRL/LLDS-R-GRPO-Qwen2.5-3B-Ins

Reinforcement Learning • 3B • Updated 23 days ago • 30 • 1

SEGAgentRL/LLDS-A-GRPO-Qwen2.5-3B-Base

Reinforcement Learning • 3B • Updated 23 days ago • 26

SEGAgentRL/LLDS-A-GRPO-Qwen2.5-3B-Base-MA

Reinforcement Learning • 3B • Updated 23 days ago • 36 • 1

SEGAgentRL/LLDS-A-GRPO-Qwen2.5-7B-Base

Reinforcement Learning • 8B • Updated 23 days ago • 71 • 2

SEGAgentRL/LLDS-A-GRPO-Qwen2.5-7B-Ins

Reinforcement Learning • 8B • Updated 23 days ago • 93 • 2

datasets 0

None public yet