Hugging Face daily papers·6d agoScalable Weak-to-Strong Verifier Hardening for Agent Environments#reward-hacking#agent-security#verifiers
arXiv cs.CR·17d agoVStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers#verifiers#auditing#rlvrAI research
Hugging Face daily papers·Sep 2, 2026FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience#math-reasoning#qwen3#reasoning-models