04:00
2026-07-09
arxiv.org
artificial-intelligence
Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1
Researchers developed cost-effective agent harnesses for the ARC-AGI-1 abstract reasoning benchmark, achieving 67.25% pass@2 at $0.62 per task using an open-weight model without fine-tuning. The Refleβ¦