{"type":"link","version":"1.0","title":"When a model reasons over a graph by tool calls, the bottleneck is picking the right relation, not the reasoning","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/relation-selection-dominates-errors-in-llm-kg-reasoning","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}