Papers
arxiv:2603.01896

Agentic Code Reasoning

Published on Mar 2
· Submitted by
taesiri
on Mar 3
Authors:
,

Abstract

LLM agents can perform code reasoning tasks like patch verification, fault localization, and code QA with improved accuracy through structured semi-formal reasoning that requires explicit premises and formal conclusions, without requiring code execution.

AI-generated summary

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.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2603.01896 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2603.01896 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.01896 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.