iiinova — where your digital self keeps evolving

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Zhenyu Qi, Haotang Li, Jinfu Chen, Huashan Chen, Yutong Zhao, Derui Zhu, Tomas Cerny, Bo Liu, Sen He: Merged, Not Measured: An Empirical Study of Performance Issues Fixed by Coding Agents arxiv.org/abs/2609.37985 arxiv.org/pdf/2609.37985 arxiv.org/html/2609.37985

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Yiming Cheng, Alfin Wijaya Rahardja, Mengshi Zhang, Zihao Chen, Zhenpeng Chen, Yiling Lou: AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems arxiv.org/abs/2609.37864 arxiv.org/pdf/2609.37864 arxiv.org/html/2609.37864

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Pavlin G. Poli\v{c}ar, Martin \v{S}pendl, Toma\v{z} Ho\v{c}evar: Is manual software optimization a thing of the past? arxiv.org/abs/2609.37849 arxiv.org/pdf/2609.37849 arxiv.org/html/2609.37849

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Sabrina Kaniewski, Tim Kr\"amer, Julius B\"achle, Markus Enzweiler, Michael Menth, Tobias Heer: Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection arxiv.org/abs/2609.37669 arxiv.org/pdf/2609.37669 arxiv.org/html/2609.37669

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Charlotte Brandebusemeyer, Daniela Gasser, Tobias Schimmer, Bert Arnrich: Beyond Productivity: Measuring Developers' Cognitive Load During GenAI-Supported Software Development arxiv.org/abs/2609.37645 arxiv.org/pdf/2609.37645 arxiv.org/html/2609.37645

010

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Fabio Rovai: Independent Verification Paths Are Not Independent: A Case Study of Common-Mode Failure in a Satellite Catalogue Pipeline arxiv.org/abs/2609.37603 arxiv.org/pdf/2609.37603 arxiv.org/html/2609.37603

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Woirhaye, Gibier, Da Silva, Faticanti, Ledoux, Rouvoy: Profiling the Energy Consumption of Serverless Functions with Joule Profiler arxiv.org/abs/2609.37531 arxiv.org/pdf/2609.37531 arxiv.org/html/2609.37531

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Cristina Martinez Montes, Pushpamalar Rajendran, Grace Karuri, Felix Dobslaw: Exploring Emotional Intelligence in Software Testing arxiv.org/abs/2609.37526 arxiv.org/pdf/2609.37526 arxiv.org/html/2609.37526

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Ali Mohammadi Esfahani, Nafiseh Kahani, Samuel A. Ajila: Complexity-Aware Evaluation of LLM Comprehension arxiv.org/abs/2609.37405 arxiv.org/pdf/2609.37405 arxiv.org/html/2609.37405

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Rohith Reddy Bellibatlu, Zichong Wang, Wenbin Zhang: Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments arxiv.org/abs/2609.37315 arxiv.org/pdf/2609.37315 arxiv.org/html/2609.37315

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Francisco Ortin: SafeLLM4SE: Statistical Evaluation and Reporting for LLM-based Software Engineering Systems arxiv.org/abs/2609.37294 arxiv.org/pdf/2609.37294 arxiv.org/html/2609.37294

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Yue Pan, Jiawei Li, Ziyuan Zhang, Xiangxin Zhao, He Ye: CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews? arxiv.org/abs/2609.37216 arxiv.org/pdf/2609.37216 arxiv.org/html/2609.37216

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Yun Peng, Zihan Wu, Zeyang Zhuang, Xin Zhou, Rui Shu, Xu Han, Chun Yong Chong, Yuan Wang, Jiakun Liu: LoLBench: Evaluating Coding Agents with Long-Horizon Proposals on Large Software Systems arxiv.org/abs/2609.37143 arxiv.org/pdf/2609.37143 arxiv.org/html/2609.37143

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Yuto Kitabayashi, Takashi Kobayashi: GitCF: Reducing Incomplete Changes by Exploiting Multiple Similarities Among Commits arxiv.org/abs/2609.37045 arxiv.org/pdf/2609.37045 arxiv.org/html/2609.37045

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Zirui Li, Torsten Brix, Stephan Husung: Cross-Organizational SysML Model Integration: A Survey of Challenges and AI-Supported Tasks arxiv.org/abs/2609.37000 arxiv.org/pdf/2609.37000 arxiv.org/html/2609.37000

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Guo, Zhou, Zhang, Zhang, Liu, Chen, Lin, Dong, Zhang, Chen: XRepoSkill: Learning Transferable Skills for Software Engineering Agents arxiv.org/abs/2609.36807 arxiv.org/pdf/2609.36807 arxiv.org/html/2609.36807

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Angad Miglani, Samrath Singh Chadha, Kevin Li, Manas Venkata Sai Ravulapalli: The Editor Has Read-Only Access: Correctness Signals in Diffusion Language Models arxiv.org/abs/2609.36783 arxiv.org/pdf/2609.36783 arxiv.org/html/2609.36783

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Xinran Zhang: CTE-Bench: Counterfactual Trace Evaluation for Stateful Software Simulators arxiv.org/abs/2609.36647 arxiv.org/pdf/2609.36647 arxiv.org/html/2609.36647

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Haomin Qi, Xiangzhe Xu, Yiming Huang, Jingbo Shang, Chengpeng Wang: WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses arxiv.org/abs/2609.36635 arxiv.org/pdf/2609.36635 arxiv.org/html/2609.36635

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Yuning Han, Yangchenchen Jin, Tyler Jandreau, Jingwei Sun: LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents arxiv.org/abs/2609.36371 arxiv.org/pdf/2609.36371 arxiv.org/html/2609.36371

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Ming Du, et al.: Strategies for Deploying AI Agents in Production at Scientific User Facilities arxiv.org/abs/2609.36362 arxiv.org/pdf/2609.36362 arxiv.org/html/2609.36362

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Ali Alfageeh, Rahul Gopinath, Amin Alipour: How Much Prompt Is Enough? A Blackbox Minimization of Few-Shots in LLMs arxiv.org/abs/2609.36289 arxiv.org/pdf/2609.36289 arxiv.org/html/2609.36289

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Om Shankar Tiwari, Tangi Vass, Gagan Deep Singh: Assay: Claims That Decay With the Code. Content-Addressed Evidence Graphs for Accountable AI-Assisted Software Delivery arxiv.org/abs/2609.36170 arxiv.org/pdf/2609.36170 arxiv.org/html/2609.36170

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Tianyu Liu, Dingyuan Dai, Yufan Du, Zhen Yang: From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents arxiv.org/abs/2609.36161 arxiv.org/pdf/2609.36161 arxiv.org/html/2609.36161

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Xinyue Feng, Hanyuan Shi, Yuan Si: The Invisible Throttle: Running on Borrowed Time in Scratch arxiv.org/abs/2609.36152 arxiv.org/pdf/2609.36152 arxiv.org/html/2609.36152

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Denis Mamatin, Andrey Salov: Live Architecture Models for Cloud-Native Architecture-as-Code: Early Results from Kubernetes Conformance Checking arxiv.org/abs/2609.36148 arxiv.org/pdf/2609.36148 arxiv.org/html/2609.36148

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Xinyue Feng, Hanyuan Shi, Yuan Si: The Invisible Scheduler: Dragging a Sprite Can Change What a Scratch Program Does arxiv.org/abs/2609.36147 arxiv.org/pdf/2609.36147 arxiv.org/html/2609.36147

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Myokyung Han, Taegyoon Kim, Jinhyuk Yun, Lanu Kim: The Uneven Decline of Collective Knowledge Production: Evidence from Stack Overflow After Generative AI arxiv.org/abs/2609.36069 arxiv.org/pdf/2609.36069 arxiv.org/html/2609.36069

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Zhengyang Shan, Jiayun Xin, Yanjun Lin, Xu Qian, Zhiang Liu, Minghui Xu, Yue Zhang, Qin Hu, Kun Li, Xiuzhen Cheng: UNBIND: UNlearning By INference-time Directional Steering for Code LLMs arxiv.org/abs/2609.35913 arxiv.org/pdf/2609.35913 arxiv.org/html/2609.35913

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Vasili Gavrilov, Enkli Ylli: The Artifact Promotion Control Model: An Implementation Case Study. Build on Target Machines vs. Build Once and Promote Artifacts arxiv.org/abs/2609.35891 arxiv.org/pdf/2609.35891 arxiv.org/html/2609.35891

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Paulo Akira F. Enabe, Rodrigo Provasi: PoliVEM: a Python-driven virtual element framework for computational solid mechanics arxiv.org/abs/2609.35878 arxiv.org/pdf/2609.35878 arxiv.org/html/2609.35878

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Nils Kiele, Zainab Saad, Zirui Wang, Steve Drew, Samira Ebrahimi Kahou: Beyond Rule-Based Mutation Testing: Test-Aware Mutant Generation Using Large Language Models arxiv.org/abs/2609.35841 arxiv.org/pdf/2609.35841 arxiv.org/html/2609.35841

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Furqan Nasir, Muhammad Arif Shah, Ifitkhar Alam: A Leakage-Safe, Cost-Aware Regression Testing Methodology for the Quantum Transpiler arxiv.org/abs/2609.35834 arxiv.org/pdf/2609.35834 arxiv.org/html/2609.35834

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

Zedong Peng: Agent-Callable Feature Coverage: Measuring Software Readiness for AI Agents arxiv.org/abs/2609.35789 arxiv.org/pdf/2609.35789 arxiv.org/html/2609.35789

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 23h

[2026-09-30 Wed (UTC), 35 new articles found for csSE Software Engineering]

001

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Xiaonan Xu, Wenjing Wu: MCP Error Messages Written for Developers Hurt the Most Capable Agents Most arxiv.org/abs/2609.35381 arxiv.org/pdf/2609.35381 arxiv.org/html/2609.35381

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Dongsheng Ma, Sizhe Wang, Xinyi Huang, Zhengren Wang, Yuhan Wang, Luyang Si, Xincheng Wei, Wentao Zhang: Do Coding Agents Reuse Existing Code or Reinvent the Wheel? arxiv.org/abs/2609.35357 arxiv.org/pdf/2609.35357 arxiv.org/html/2609.35357

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Marco Calamo, Massimo Mecella, Monique Snoeck: Is there a future for models in the LLM era? arxiv.org/abs/2609.35281 arxiv.org/pdf/2609.35281 arxiv.org/html/2609.35281

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Wang, Liu, Cui, Ji, Ni, Lu, Cui, Qin: Research-Native by Construction: Minimal Nodes, Re-verifiable Workflows, and Compounding Memory for Long-Horizon Scientific Agents arxiv.org/abs/2609.35182 arxiv.org/pdf/2609.35182 arxiv.org/html/2609.35182

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Gary Myler, James Holmes, Manish Patel, Amel Bennaceur: Graph-Based Learning for Multi-Horizon Martian Atmospheric Forecasting arxiv.org/abs/2609.35042 arxiv.org/pdf/2609.35042 arxiv.org/html/2609.35042

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Ali Shakiba, Thomas Chaffey: Making the Invisible Visible: A Framework for Reflective AI Use in Software Engineering Education arxiv.org/abs/2609.34997 arxiv.org/pdf/2609.34997 arxiv.org/html/2609.34997

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Liao, Nan, Liang, Gao, Hu, Sun, Zhong, Ma, Zheng, Liu: SmartMemory: Detecting On-chain-off-chain Communication Inconsistency for Smart Contract via Memory-based Agent arxiv.org/abs/2609.34983 arxiv.org/pdf/2609.34983 arxiv.org/html/2609.34983

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Andrei Aldea (Bitdefender), Dumitru-Bogdan Prelipcean (Bitdefender): Verifying Graceful Degradation in a Distributed Malware-Detection System with SPIN arxiv.org/abs/2609.34873 arxiv.org/pdf/2609.34873 arxiv.org/html/2609.34873

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Alexandre Berard (Framatome SAS Grenoble), Richard B. Kreckel (Framatome GmbH): Certified Compilation in the TELEPERM XS Nuclear Safety I&C Platform arxiv.org/abs/2609.34871 arxiv.org/pdf/2609.34871 arxiv.org/html/2609.34871

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

I Putu Arya Dharmaadi, Elias Athanasopoulos, Fatih Turkmen: TraceLib: System-Call Bitmap Feedback Mechanism for Language-Agnostic Web Fuzzing arxiv.org/abs/2609.34778 arxiv.org/pdf/2609.34778 arxiv.org/html/2609.34778

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Kazuki Kusama, Sota Nakashima, Haruka Tokumasu, Masanari Kondo, Lingming Zhang, Yasutaka Kamei: Multi-SWT-Bench: A Multilingual Benchmark for Reproduction Test Generation arxiv.org/abs/2609.34752 arxiv.org/pdf/2609.34752 arxiv.org/html/2609.34752

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Haoran Li, Shihai Wang, Bin Liu, Jialuo Chen, Wenjing Zhu, Yu Liu, Tengfei Shi, Shudi Guo: When Ambiguity Meets Atypicality: Dual-Perspective Test Input Prioritization for DNNs arxiv.org/abs/2609.34703 arxiv.org/pdf/2609.34703 arxiv.org/html/2609.34703

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Cong Li, Hao Sun, Zenan Li, Zhendong Su: Codoku: Renewable Program-Reasoning Challenges for Frontier Coding Agents arxiv.org/abs/2609.34661 arxiv.org/pdf/2609.34661 arxiv.org/html/2609.34661

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 29/09/2026

Hai Duong, Thanh Le, ThanhVu Nguyen: CLAD: Constrained Abstract Domain for Neural Network Verification arxiv.org/abs/2609.34628 arxiv.org/pdf/2609.34628 arxiv.org/html/2609.34628

000