PaperAgent

Jan 20, 2026 · Artificial Intelligence

How Intrinsic Self‑Critique Boosts LLM Planning Accuracy to 89% %​

Google DeepMind's new "Intrinsic Self‑Critique" method lets large language models iteratively self‑evaluate and rewrite their plans, raising Blocksworld planning accuracy from 49.8% to 89.3% and setting new records across multiple planning benchmarks.