InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution

TL;DR

InfCode is an adversarial multi-agent framework that iteratively refines tests and patches for reliable software issue resolution, significantly improving success rates over existing methods.

Contribution

The paper introduces InfCode, a novel adversarial multi-agent system that enhances repository-level software issue fixing by iteratively refining tests and patches.

Findings

Achieves 79.4% performance on SWE-bench Verified

Outperforms strong baseline methods

Establishes new state-of-the-art in automated software fixing

Abstract

Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing agent-based and pipeline-based methods often rely on insufficient tests, which can lead to patches that satisfy verification but fail to fix the underlying defect. We present InfCode, an adversarial multi-agent framework for automated repository-level issue resolution. InfCode iteratively refines both tests and patches through adversarial interaction between a Test Patch Generator and a Code Patch Generator, while a Selector agent identifies the most reliable fix. The framework runs inside a containerized environment that supports realistic repository inspection, modification, and validation. Experiments on SWE-bench Lite and SWE-bench Verified using models such as DeepSeek-V3 and Claude 4.5 Sonnet show that InfCode consistently outperforms strong baselines. It achieves 79.4% performance on SWE-bench Verified, establishing a new state-of-the-art. We have released InfCode as an open-source project at https://github.com/Tokfinity/InfCode.