Ian Cole

codingiancole's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 4 papers about 21 hours ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published 6 days ago • 55

Region-Level Policy Optimization for Fine-grained MLLM Perception

Paper • 2609.19745 • Published 6 days ago • 41

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

Paper • 2609.20715 • Published 6 days ago • 42

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

Paper • 2609.17653 • Published 8 days ago • 44

upvoted 2 papers 2 days ago

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Paper • 2609.19134 • Published 7 days ago • 99

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published 8 days ago • 69

upvoted 3 papers 3 days ago

ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals

Paper • 2609.16816 • Published 8 days ago • 11

MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control

Paper • 2609.06251 • Published 18 days ago • 8

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 16 days ago • 372

upvoted 5 papers 4 days ago

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

Paper • 2609.06702 • Published 17 days ago • 26

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Paper • 2609.11042 • Published 13 days ago • 63

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

Paper • 2609.06107 • Published 18 days ago • 164

StepAudio 3 Music Technical Report

Paper • 2609.16034 • Published 12 days ago • 108

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 25 days ago • 475

upvoted 3 papers 5 days ago

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models

Paper • 2609.13680 • Published 11 days ago • 13

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

Paper • 2609.17523 • Published 8 days ago • 30

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 8 days ago • 146

upvoted 3 papers 6 days ago

Expert-Space Exploration in MoE Reinforcement Learning

Paper • 2609.13058 • Published 12 days ago • 7

MInTRL: Off-policy Intervention can boost On-policy RL

Paper • 2609.12419 • Published 12 days ago • 14

Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

Paper • 2609.15051 • Published 9 days ago • 14