# The Path Not Taken: Duality in Reasoning about Program Execution

arXiv: https://arxiv.org/abs/2604.20917 · HTML: https://mlsanity.com/paper/2604.20917/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 11 of 11)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Llama-Nemotron: Efficient Reasoning Models](https://mlsanity.com/paper/2505.00949/) (2025)
- [Magistral](https://mlsanity.com/paper/2506.10910/) (2025)
- [CodeMind: Evaluating Large Language Models for Code Reasoning](https://mlsanity.com/paper/2402.09664/) (2024)
- [CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks](https://mlsanity.com/paper/2507.05269/) (2025)
- [From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting](https://mlsanity.com/paper/2401.05384/) (2023)
- [Assessing Coherency and Consistency of Code Execution Reasoning by Large Language Models](https://mlsanity.com/paper/2510.15079/) (2025)
- [Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation](https://mlsanity.com/paper/2512.00215/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks. However, their adoption requires a true understanding of program execution rather than relying on surface-level patterns. Existing benchmarks primarily focus on predicting program properties tied to specific inputs (e.g., code coverage, program outputs). As a result, they provide a narrow view of dynamic code reasoning and are prone to data contamination. We argue that understanding program execution requires evaluating its inherent duality through two complementary reasoning tasks: (i) predicting a program's observed behavior for a given input, and (ii) inferring how the input must be mutated toward a specific behavioral objective. Both tasks jointly probe a model's causal understanding of execution flow. We instantiate this duality in DexBench, a benchmark comprising 445 paired instances, and evaluate 13 LLMs. Our results demonstrate that dual-path reasoning provides a robust and discriminative proxy for dynamic code understanding.