Score: 2

Generating Verifiable CoT from Execution-Traces

Published: November 28, 2025 | arXiv ID: 2512.00127v1

By: Shailja Thakur , Vaibhav Saxena , Rohan Kulkarni and more

BigTech Affiliations: IBM

Potential Business Impact:

Teaches computers to understand code by watching it run.

Business Areas:
Simulation Software

Teaching language models to reason about code execution remains a fundamental challenge. While Chain-of-Thought (CoT) prompting has shown promise, current synthetic training data suffers from a critical weakness: the reasoning steps are often plausible-sounding explanations generated by teacher models, not verifiable accounts of what the code actually does. This creates a troubling failure mode where models learn to mimic superficially convincing but logically flawed reasoning patterns. We address this by grounding CoT generation directly in program execution traces. Our pipeline instruments code to capture its dynamic behavior, then narrates these verified execution traces into natural language rationales that are correct by construction. This execution-grounded approach ensures every reasoning step reflects what the program genuinely computes, eliminating logical hallucinations at the source. We evaluate our method on code reasoning tasks (forward reasoning on CruxEval and LiveCodeBench-Exec, backward reasoning on CruxEval-Input), as well as code generation and explanation tasks from HumanEval. Models trained on our bi-directional trace-grounded data achieve substantial improvements, with gains of up to 30 points on output prediction and 28 points on input prediction over base models, alongside improved explanation and code generation, demonstrating that verifiable reasoning fundamentally enhances model capabilities. https://github.ibm.com/IBM-Research-AI/Verified-Code-CoT

Country of Origin
🇺🇸 United States


Page Count
55 pages

Category
Computer Science:
Software Engineering