AIBullisharXiv – CS AI · 10h ago7/10
🧠
When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
Researchers introduce a learnable approach to commitment depth—the number of primitive actions executed before replanning—in vision-language models for long-horizon reasoning. Their adaptive policy outperforms fixed-depth baselines and surpasses GPT-4.5 and Claude Sonnet on puzzle-solving tasks, achieving higher solve rates with fewer actions.
🧠 GPT-5🧠 Claude