InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model (LLM…
InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution
Large language model (LLM) agents have recently shown strong performance on repository-level issue resolution, but existing systems are almost exclusively designed for Python and rely heavily on lexical retrieval and sha…
Semantic RetrievalMAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents
Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual perception models. However, developing such attacks remains challenging due to diverse real-world backgrounds and the requir…
object-detectionObject DetectionPrompt EngineeringScene UnderstandingHouse-GAN++: Generative Adversarial Layout Refinement Networks
This paper proposes a novel generative adversarial layout refinement network for automated floorplan generation. Our architecture is an integration of a graph-constrained relational GAN and a conditional GAN, where a pre…
Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established a…
Face Recognitionobject-detectionObject Detection