#ARC-AGI-3
2 articles with this tag
Artificial Intelligence
OpenAI Triples Benchmark Scores With Simple Settings
OpenAI found simple API setting tweaks tripled scores on the ARC-AGI-3 benchmark, proving harness design significantly impacts AI evaluation.
3 months ago
AI Research
PRO-LONG: Memory for LLM Agents
PRO-LONG revolutionizes LLM agent capabilities for long-horizon tasks, achieving SOTA performance with drastic token efficiency and cost reduction.
3 months ago
