{"type":"link","version":"1.0","title":"Outcome-reward RL tool agents perceive an unsolvable task but still fabricate an answer instead of refusing","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/risk-rl-tool-agent-fabricates-after-detecting-unsolvable-task","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}