Software Engineering Papers

New Software Engineering papers from design tools, software metrics. Thank you to arXiv for use of its open access interoperability.

[Software Engineering Papers @ComputerPapers]

A Case Study in Assuring AI-Written Software

Lindsey Ferris, Sierra Bonilla
https://t.co/vsiG4cOfH1 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙼𝙰]
💬Accepted to the NeurIPS 2026 Meta-Agents Workshop

[Software Engineering Papers @ComputerPapers]

RAPO-Sol: Retrieval-Augmented Preference Optimization for Repository-Level Solidity Code Generation

Rongcun Wang, Shi Chen
https://t.co/flkxKnthxa [𝚌𝚜.𝚂𝙴]

[Software Engineering Papers @ComputerPapers]

Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis

Mandana Ghadamian, David Mohaisen
https://t.co/VmFNcGJB6r [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁]
💬Accepted at CSoNet 2026

[Software Engineering Papers @ComputerPapers]

Newer and Bigger, but Safer? A Longitudinal Study of the Functionality-Security Gap in LLM-Generated Code

Thiago Santos de Moura, Fynn Matuschek, Flavio Toffalini, Yannic Noller
https://t.co/hFlnkkI3O6 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝚁]

[Software Engineering Papers @ComputerPapers]

Beyond the Leaderboard: Multi-Dimensional Evaluation of Dense and Mixture-of-Experts Models for Automated Program Repair

Anvi Kalpesh Shah, Umamaheswara Sharma B
https://t.co/9Rlkfa0eOE [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙻𝙶]

[Software Engineering Papers @ComputerPapers]

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

Haibo Jin, Xinjie Li, Peng Kuang, Haohan Wang
https://t.co/eyDexItmZl [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙼𝙰]

[Software Engineering Papers @ComputerPapers]

ES-Trace: Auditing Ethical-Sourcing Disclosure of Code Generation Models Beyond Model Cards

Zhuolin Xu, Haibo Wang, Shin Hwei Tan
https://t.co/C336s4WQx9 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝚈]

[Software Engineering Papers @ComputerPapers]

Acquiring and Verifying Repository Norms for Coding Agents

Kaifeng He, Xiaojun Zhang, Zhenxi Chen, Christoph Treude, Mingwei Liu
https://t.co/7xq3WFlNP8 [𝚌𝚜.𝚂𝙴]

[Software Engineering Papers @ComputerPapers]

When Old Facts Return: Re-Reads, Reverts, and the Limits of Temporal Memory

Neeraj Yadav
https://t.co/4ntZP4wjp3 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝙻]

[Software Engineering Papers @ComputerPapers]

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?

Hang He, Li Wang, Hao Chen, Yuchen Shao, Yuling Shi, Lisheng Wang, Peiyang Liu, Goose Lin, Zaiyuan Wang, Haiying Sun, Ting Su, Chengcheng Wan
https://t.co/JQUseQ5Bla [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁]

[Software Engineering Papers @ComputerPapers]

The EPIC Framework for Spec-Driven Development

Bruno Claudino, Ruizhe Xing, Yuanhao Zuo, Tyler Menezes, Anita Sarma, Kostadin Damevski, Zixuan Feng
https://t.co/ehFsUyUlB6 [𝚌𝚜.𝚂𝙴]

[Software Engineering Papers @ComputerPapers]

CogAdapt: Cognition-informed Sparse Adaptation of Code LLMs

Yueke Zhang, Zihan Fang, Kevin Leach, Yu Huang
https://t.co/hfs9SRHXf5 [𝚌𝚜.𝚂𝙴]

[Software Engineering Papers @ComputerPapers]

A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models

Ardalan Aryashad, Yan Jin
https://t.co/ulUaNDgTTW [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

[Software Engineering Papers @ComputerPapers]

Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale

Celal Ziftci, Spencer Greene, Ray Liu, …
https://t.co/jTz0Iiyt9C [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]
💬Accepted at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)

[Software Engineering Papers @ComputerPapers]

SAFESHIELD: A Decision-Organization Framework for Deployment-Time Safety of Small Language Models

Xingru Zhou, Luis Sentis, Aarti Choudhary
https://t.co/RJMjd3x1aO [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁]
💬Accepted to the Application Track of IEEE TPS 2026

[Software Engineering Papers @ComputerPapers]

Choosing an energy-efficient software architecture for building system diagnostic support

Roxane Koitz-Hristov, Franz Wotawa
https://t.co/Tsz9v6HE0k [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

[Software Engineering Papers @ComputerPapers]

LLM Non-Determinism in Deterministic Processes: A Controlled Variation Space for Constraining the Propagation of Non-Determinism

Paul Darius Mandl, Peter Mandl, Martin Häusl
https://t.co/vMOc64HDJ9 [𝚌𝚜.𝚂𝙴]

[Software Engineering Papers @ComputerPapers]

Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents

Hai Dang Truong, Rayner Goh, Thanh Le-Cong, Yintong Huo
https://t.co/W1GsSMt0Tq [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]
💬Code: https://t.co/RUXtdyxufO

[Software Engineering Papers @ComputerPapers]

Where Does the Budget Go? Structural Concentration in Learning-Based Mutant Selection

Taha Rostami, Jeongju Sohn, Mike Papadakis
https://t.co/3g3EpPJzjt [𝚌𝚜.𝚂𝙴]

[Software Engineering Papers @ComputerPapers]

Let the Agent Do It? How Software Practitioners Understand and Make Permission Decisions in Agentic AI Assistants

Larissa Salerno, Haoyu Gao, Gregory Gay, Alexander Serebrenik, Philipp Leitner
https://t.co/SfSpMqvoWA [𝚌𝚜.𝚂𝙴]