Hugging Face daily papers·2d agoLEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents#leash#computer-use-agents#weak-to-strong1
Hugging Face daily papers·6d agoScalable Weak-to-Strong Verifier Hardening for Agent Environments#reward-hacking#agent-security#verifiers
Hugging Face daily papers·21d agoAllspark: Weak to Strong Transfer via Alternating Chain of Thought#allspark#weak-to-strong#chain-of-thought