Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
Paper • 2604.17073 • Published • 9
zhaihaotian
zhaihaotian
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 19 hours ago
T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning upvoted a paper 17 days ago
The Amazing Agent Race: Strong Tool Users, Weak Navigators upvoted a paper 18 days ago
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RLOrganizations
submitted a
paper to Daily Papers 18 days ago