Autonomous Issue Resolver: Towards Zero-Touch Code Maintenance

TL;DR

This paper introduces Autonomous Issue Resolver (AIR), a novel framework using Data Transformation Graphs and multi-agent neuro-symbolic reasoning to improve automated program repair at scale, achieving an 87.1% resolution rate.

Contribution

It proposes a paradigm shift from control-centric to data-centric modeling with DTGs and multi-agent systems for scalable, zero-touch code maintenance.

Findings

Achieved 87.1% resolution rate on SWE-Verified benchmark.

Resolved the 'Semantic Trap' in modern coding agents.

Demonstrated effectiveness through theoretical analysis and case studies.

Abstract

Recent advances in Large Language Models have revolutionized function-level code generation; however, repository-scale Automated Program Repair (APR) remains a significant challenge. Current approaches typically employ a control-centric paradigm, forcing agents to navigate complex directory structures and irrelevant control logic. In this paper, we propose a paradigm shift from the standard Code Property Graphs (CPGs) to the concept of Data Transformation Graph (DTG) that inverts the topology by modeling data states as nodes and functions as edges, enabling agents to trace logic defects through data lineage rather than control flow. We introduce a multi-agent framework that reconciles data integrity navigation with control flow logic. Our theoretical analysis and case studies demonstrate that this approach resolves the "Semantic Trap" inherent in standard RAG systems in modern coding agents. We provide a comprehensive implementation in the form of Autonomous Issue Resolver (AIR), a self-improvement system for zero-touch code maintenance that utilizes neuro-symbolic reasoning and uses the DTG structure for scalable logic repair. Our approach has demonstrated good results on several SWE benchmarks, reaching a resolution rate of 87.1% on SWE-Verified benchmark. Our approach directly addresses the core limitations of current AI code-assistant tools and tackles the critical need for a more robust foundation for our increasingly software-dependent world.