# Agentic Code Reasoning

arXiv: https://arxiv.org/abs/2603.01896 · HTML: https://mlsanity.com/paper/2603.01896/

## Key facts

- Cited by 4 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 18 of its 31 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [Baldur: Whole-Proof Generation and Repair with Large Language Models](https://mlsanity.com/paper/2303.04910/) (2023)
- [Aristotle: IMO-level Automated Theorem Proving](https://mlsanity.com/paper/2510.01346/) (2025)
- [AgentFL: Scaling LLM-based Fault Localization to Project-Level Context](https://mlsanity.com/paper/2403.16362/) (2024)
- [CodeJudge: Evaluating Code Generation with Large Language Models](https://mlsanity.com/paper/2410.02184/) (2024)
- [VERINA: Benchmarking Verifiable Code Generation](https://mlsanity.com/paper/2505.23135/) (2025)
- [CLEVER: A Curated Benchmark for Formally Verified Code Generation](https://mlsanity.com/paper/2505.13938/) (2025)
- [SWE-RM: Execution-free Feedback For Software Engineering Agents](https://mlsanity.com/paper/2512.21919/) (2025)
- [Agentic Rubrics as Contextual Verifiers for SWE Agents](https://mlsanity.com/paper/2601.04171/) (2026)
- [Cobblestone: A Divide-and-Conquer Approach for Automating Formal Verification](https://mlsanity.com/paper/2410.19940/) (2024)
- [FlexFL: Flexible and Effective Fault Localization with Open-Source Large Language Models](https://mlsanity.com/paper/2411.10714/) (2024)
- [Towards Verified Code Reasoning by LLMs](https://mlsanity.com/paper/2509.26546/) (2025)
- [LLMs versus the Halting Problem: Characterizing Program Termination Reasoning](https://mlsanity.com/paper/2601.18987/) (2026)

## Built on by (most cited first, 4 of 4)

- [Auditing Reward Hackability in Code RL Training Environments](https://mlsanity.com/paper/2606.16062/) (2026)
- [RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists](https://mlsanity.com/paper/2608.04783/) (2026)
- [Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study](https://mlsanity.com/paper/2608.01507/) (2026)
- [Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis](https://mlsanity.com/paper/2605.12694/) (2026)

## Abstract (arXiv)

Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that requires agents to construct explicit premises, trace execution paths, and derive formal conclusions. Unlike unstructured chain-of-thought, semi-formal reasoning acts as a certificate: the agent cannot skip cases or make unsupported claims. We evaluate across three tasks (patch equivalence verification, fault localization, and code question answering) and show that semi-formal reasoning consistently improves accuracy on all of them. For patch equivalence, accuracy improves from 78% to 88% on curated examples and reaches 93% on real-world agent-generated patches, approaching the reliability needed for execution-free RL reward signals. For code question answering on RubberDuckBench Mohammad et al. (2026), semi-formal reasoning achieves 87% accuracy. For fault localization on Defects4J Just et al. (2014), semi-formal reasoning improves Top-5 accuracy by 5 percentage points over standard reasoning. These results demonstrate that structured agentic reasoning enables meaningful semantic code analysis without execution, opening practical applications in RL training pipelines, code review, and static program analysis.