When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
Large language models (LLMs) often achieve strong performance on reasoning benchmarks, but final-answer accuracy alone does not show whether they faithfully execute the procedure specified in a prompt. We introduce a controlled diagnostic benchmark for arithmetic procedural execution, where models are given a step-wise arithmetic procedure and two numeric inputs, and must return the final computed value. Complexity is varied through procedure length and look-back dependencies over intermediate variables. Average first-answer accuracy drops from 63% on 5-step procedures to 20\% on 95-step procedures. Generation-level analysis shows that failures often involve missing answers, premature ans...
| Authors | Sailesh Panda, Pritam Kadasi, Abhishek Upperwal et al. |
|---|---|
| Primary category | cs.CL |
| Published | 1 May 2026 |
| Last updated at source | 3 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.