ARC-AGI benchmark for abstract reasoning and general intelligence evaluation
| Name | Categories | Topics | References | Credibility | CreateDate | UpdateDate | Title | RelatedNotes | NavigationOrder | Eleventy | TemplateEngineOverride | Created |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 20260724_pro_long_programmatic_memory_long_horizon_reasoning | paper_analysis | memory_mechanism, agent_architecture, reasoning, long_term_memory, coding_agents, continual_learning | duke_university, arc_agi, chain_of_thought | 100 | PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning | [object Object] | [object Object] | md |