# textttReMind: Understanding Deductive Code Reasoning in LLMs

arXiv: https://arxiv.org/abs/2511.00488 · HTML: https://mlsanity.com/paper/2511.00488/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## 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, 26 of 26)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [Chain of Code: Reasoning with a Language Model-Augmented Code Emulator](https://mlsanity.com/paper/2312.04474/) (2023)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://mlsanity.com/paper/2311.11797/) (2023)
- [Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification](https://mlsanity.com/paper/2404.00762/) (2024)
- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback](https://mlsanity.com/paper/2403.16792/) (2024)
- [CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification](https://mlsanity.com/paper/2405.00253/) (2024)
- [Mutation-Guided LLM-based Test Generation at Meta](https://mlsanity.com/paper/2501.12862/) (2025)
- [Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems](https://mlsanity.com/paper/2209.05948/) (2022)
- [SelfPiCo: Self-Guided Partial Code Execution with LLMs](https://mlsanity.com/paper/2407.16974/) (2024)
- [Mutation-based Consistency Testing for Evaluating the Code Understanding Capability of LLMs](https://mlsanity.com/paper/2401.05940/) (2024)
- [Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment](https://mlsanity.com/paper/2502.13170/) (2025)
- [Towards Trustworthy AI Software Development Assistance](https://mlsanity.com/paper/2312.09126/) (2023)
- [Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models](https://mlsanity.com/paper/2504.04372/) (2025)

## Built on by (most cited first, 2 of 2)

- [MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution](https://mlsanity.com/paper/2601.18847/) (2026)
- [CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction](https://mlsanity.com/paper/2604.25399/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have achieved remarkable progress in code-related tasks. Despite their advancement, empirical evidence reveals that they still struggle with deductive code reasoning, the ability to reason about the program execution process. While prior studies have recognized this limitation, the underlying causes remain largely underexplored. In this paper, we begin by presenting a comprehensive empirical study that reveals three key challenges undermining deductive code reasoning: (1) an intrinsic gap between generation and reasoning abilities, (2) a consistent bias towards code sources, and (3) weak zero-shot generalization on complex benchmarks. In light of these challenges, we propose textttReMind, a multi-agent framework composed of textttMutator, textttExecutor, and textttInspector. The textttMutator generates code variants to mitigate bias towards code sources, the textttExecutor traces variable states step-by-step to expose inconsistency, and the textttInspector identifies problematic reasoning steps and provides control-flow refinement to bridge the intrinsic reasoning gap. Through their coordinated collaboration, textttReMind systematically identifies and refines reasoning flaws, achieving outstanding performance and enabling robust zero-shot generalization. Extensive experiments on two benchmarks with five LLMs demonstrate the superior advantages of textttReMind compared to baseline approaches in deductive code reasoning.