1
When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
这篇论文深入诊断了大语言模型在遵循步骤执行过程式任务时的失败模式，揭示了关键缺陷与改进方向。
arXiv:2605.00817v2 Announce Type: replace Abstract: Large language models (LLMs) often achieve strong performance on reasoning benchmarks, but final-a…