AI RESEARCH
LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning
arXiv CS.AI
•
ArXi:2603.06870v1 Announce Type: new Long-horizon execution in Large Language Models (LLMs) remains unstable even when high-level strategies are provided. Evaluating on controlled algorithmic puzzles, we nstrate that while decomposition is essential for stability, extreme decomposition creates a "no-recovery bottleneck". We show that this bottleneck becomes critical due to highly non-uniform error distribution, where consistent errors on a few "hard" steps become irreversible. To address this, we propose Lookahead-Enhanced Atomic Decomposition.