paper-with-me

Papers

Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?

2025-07-29 · Shuqing Li, Qiang Chen, Xiaoxue Ren, Michael R. Lyu arxiv

Physics Engines (PEs) are fundamental software frameworks that simulate physical interactions in applications ranging from entertainment to safety-critical systems. Despite their importance, PEs suffer from physics failures, deviations from expected physical behaviors that can compromise software reliability, degrade user experience, and potentially cause critical failures in autonomous vehicles or medical robotics. Current testing approaches for PE-based software are inadequate, typically requiring white-box access and focusing on crash detection rather than semantically complex physics failures. This paper presents the first large-scale empirical study characterizing physics failures in PE-based software. We investigate three research questions addressing the manifestations of physics failures, the effectiveness of detection techniques, and developer perceptions of current detection practices. Our contributions include: (1) a taxonomy of physics failure manifestations; (2) a comprehensive evaluation of detection methods including deep learning, prompt-based techniques, and large multimodal models; and (3) actionable insights from developer experiences for improving detection approaches. To support future research, we release PhysiXFails, code, and other materials at https://sites.google.com/view/physics-failure-detection.

📄 PDF Abstract BibTeX arXiv:2507.22099

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Vehicles

Similar Papers 제목 키워드 기반

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

2026-05-26 · Hwiwon Lee, Jiawei Liu, Dongjun Kim, Ziqi Zhang 외 arxiv

Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug h…

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents

2026-05-13 · Hailin Zhong, Shengxin Zhu arxiv

Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability.…

Code Generation

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

2026-05-09 · Chenyu Zhao, Shenglin Zhang, Yihang Lin, Wenwei Gu 외 arxiv

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, bu…

Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem

2023-03-30 · Purvish Jajal, Wenxin Jiang, Arav Tewari, Erik Kocinare 외

Software engineers develop, fine-tune, and deploy deep learning (DL) models using a variety of development frameworks and runtime environments. DL model converters move models between frameworks and to runtime environmen…

Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems

2026-05-26 · Yipeng Ouyang, Xin Huang, Bingjie Liu, Zhongchun Zheng 외 arxiv

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks th…