{"type":"link","version":"1.0","title":"Co-evolving critic recalibration to prevent reward hacking in agent RL","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/feat-co-evolving-critic-recalibration-for-agent-rl","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}