Qiu

Qjbtiger

4

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 24 hours ago

Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces

upvoted a paper 1 day ago

Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens

upvoted a paper about 1 month ago

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

View all activity

Organizations

upvoted a paper about 24 hours ago

Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces

Paper • 2610.37255 • Published 2 days ago • 7

upvoted a paper 1 day ago

Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens

Paper • 2605.30960 • Published May 29 • 2

upvoted a paper about 1 month ago

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

Paper • 2609.11682 • Published Sep 10 • 47

upvoted a paper about 1 year ago

Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs

Paper • 2509.23166 • Published Sep 27, 2025 • 7

published a model over 1 year ago

Qjbtiger/Qwen2.5-1.5B-Open-R1-GRPO

Updated Jul 20, 2025