Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle Happy Bhati Published: 2026-09-04Area: cs.SECitations: 26 Tags: ai-safety, csse, preprint | 2026-09-04 | cs.SE | ai-safety, csse, preprint | E10 / R9 (92%) | 26 |
| Building a research-software catalog with a coding agent: from hackathon prototype to public deployment Gotai Yamada, Kazuyoshi Yoshimi, Satoshi Terasaki Published: 2026-09-04Area: cs.SECitations: 22 Tags: ai-safety, csse, preprint | 2026-09-04 | cs.SE | ai-safety, csse, preprint | E12 / R10 (93%) | 22 |
| Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models Andrej Andrejev Published: 2026-09-05Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-05 | cs.SE | ai-safety, csse, preprint | E8 / R6 (95%) | - |
| SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness Bo Kang, Shunkun Yang, Yi Yang, Yizhuo Zhang Published: 2026-09-05Area: cs.SECitations: 25 Tags: ai-safety, csse, preprint | 2026-09-05 | cs.SE | ai-safety, csse, preprint | E7 / R6 (91%) | 25 |
| SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction Bing Zhao, Chenxiong Qian, Jiayi Lin, Liangcai Su Published: 2026-09-05Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-05 | cs.SE | ai-safety, csse, preprint | E11 / R8 (91%) | - |
| CodeTD: Topology of Attention Detects Hallucinations in Code LLMs Anton Dmitriev, Daria Voronkova, Eduard Tulchinskii, Evgeny Burnaev Published: 2026-09-07Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-07 | cs.SE | ai-safety, csse, preprint | E14 / R11 (94%) | - |
| Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evaluation Approach Elena Zentgraf, Janek Gro脽, Jens Heidrich Published: 2026-09-07Area: cs.SECitations: - Tags: ai-safety, csse, preprint, safety-evaluation | 2026-09-07 | cs.SE | ai-safety, csse, preprint, safety-evaluation | E9 / R7 (92%) | - |
| Recompilation Is Not Enough: Test-Guided Decompiled-C Repair Jianlei Chi, Puzhuo Liu, Yuhan Huang Published: 2026-09-07Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-07 | cs.SE | ai-safety, csse, preprint | E8 / R6 (95%) | - |
| AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents Rui Xie, Shikun Zhang, Wei Ye, Yixin Li Published: 2026-09-08Area: cs.SECitations: 45 Tags: ai-safety, csse, preprint | 2026-09-08 | cs.SE | ai-safety, csse, preprint | E9 / R8 (91%) | 45 |
| It Is Not My Code Anymore Augusto Camargo Published: 2026-09-08Area: cs.SECitations: 15 Tags: ai-safety, csse, preprint | 2026-09-08 | cs.SE | ai-safety, csse, preprint | E8 / R7 (91%) | 15 |
| Talking to Itself While Coding: What Makes Comments Help Code Generation? Cenyuan Zhang, Dangfeng Pan, David Lo, Xiaoning Du Published: 2026-09-08Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-08 | cs.SE | ai-safety, csse, preprint | E11 / R6 (92%) | - |
| The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution? Boyang Wang, Yalun Wu, Yunhan Wang Published: 2026-09-08Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-08 | cs.SE | ai-safety, csse, preprint | E7 / R6 (93%) | - |
| A-JIT: Agentic Just-In-Time Software Construction Earl T. Barr, Mark Marron Published: 2026-09-09Area: cs.SECitations: 12 Tags: ai-safety, csse, preprint | 2026-09-09 | cs.SE | ai-safety, csse, preprint | E10 / R7 (96%) | 12 |
| Introducing Consort: A Spec-First Agent Framework for Enforced, Test-Driven Development on Live Database Branches Kevin Hartman Published: 2026-09-09Area: cs.SECitations: 22 Tags: ai-safety, csse, preprint | 2026-09-09 | cs.SE | ai-safety, csse, preprint | E10 / R11 (92%) | 22 |
| The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, and Responsible Adoption Louie Jay S. Labastida, Sales G. Aribe Published: 2026-09-09Area: cs.SECitations: 53 Tags: ai-safety, csse, preprint | 2026-09-09 | cs.SE | ai-safety, csse, preprint | E8 / R8 (93%) | 53 |
| A decision-basis contract for auditable LLM-assisted medical billing verification: deterministic rules, verbatim evidence, and fail-closed abstention Benjamin Raab, Boris Bauke, Jan H枚lter, Kevin Geis Published: 2026-09-10Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E12 / R10 (93%) | - |
| Agent-Integrated Software: Interaction Contracts and Continuous Assurance Chunrong Fang, Shengcheng Yu, Zhenyu Chen Published: 2026-09-10Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E8 / R7 (96%) | - |
| Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents Baohan Huang, Cong Zuo, Haibin Zhang, Ruiqing Yue Published: 2026-09-10Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E14 / R11 (93%) | - |
| Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents Alejandro Gutierrez Munoz, Barry Wang, Chhaya Methani, Hazel Mak Published: 2026-09-10Area: cs.SECitations: 15 Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E9 / R8 (96%) | 15 |
| Learning to adapt GR(1) specifications through degradation Dalal Alrajeh, Sebastian Uchitel, Tiberiu-Andrei Georgescu Published: 2026-09-10Area: cs.SECitations: 15 Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E7 / R5 (92%) | 15 |
| PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews Baihan Lin, Miguel Zabaleta Published: 2026-09-10Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E8 / R5 (91%) | - |
| Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering Alexander Krentsel, Ion Stoica, Matei Zaharia, Mert Cemri Published: 2026-09-10Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E10 / R11 (94%) | - |
| Retrieval-Augmented Generation for Scientific Code Understanding Aaron Nobile, Andreas Adelmann, Mohsen Sadr Published: 2026-09-10Area: cs.SECitations: 15 Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E12 / R10 (93%) | 15 |
| What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead Haseeb Mohammed Afsar Published: 2026-09-10Area: cs.SECitations: 11 Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E7 / R7 (93%) | 11 |
| When Agent Metrics Measure Different Things: An Evidence-Grounded Audit of the Praxa AI Pipeline Peyton Woakz, Stefan G. Creadore Published: 2026-09-10Area: cs.SECitations: 11 Tags: ai-safety, csse, preprint | 2026-09-10 | cs.SE | ai-safety, csse, preprint | E10 / R8 (90%) | 11 |
| Comparative Framework Analysis for Enterprise Generative AI Applications: Chatbot, Automation, and Oracle-to-PostgreSQL Migration Alona Seletska, Daryna Tukalo, Dmytro Kostetskyi, Ivan Fedorchuk Published: 2026-09-11Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-11 | cs.SE | ai-safety, csse, preprint | E8 / R6 (93%) | - |
| GraphAHA: Graph-Based Adaptive Search with Heterogeneous Actions for Test-Time Code Generation Gege Yuan, Haijun Wang, Jiali Wei, Ming Fan Published: 2026-09-11Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-11 | cs.SE | ai-safety, csse, preprint | E9 / R9 (93%) | - |
| Involving before Evolving: A Vision for Trustworthy Enterprise Digital Twin Engineering Adil Lagrou, Bentley Oakes, Franck Dervault, K茅rian Fiter Published: 2026-09-11Area: cs.SECitations: 36 Tags: ai-safety, csse, preprint | 2026-09-11 | cs.SE | ai-safety, csse, preprint | E16 / R11 (95%) | 36 |
| Separating Engineering Reasoning from DEXPI Serialization in LLM-Based Greenfield Surface-Process Design: A Three-Case Study for Underground Gas Storage Pengju Ren, Qingchuan Zhu, Shuyue Tong Published: 2026-09-11Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-11 | cs.SE | ai-safety, csse, preprint | E8 / R8 (98%) | - |
| The Agentic Company OS: Substrate Inversion for Sustained Enterprise Agent Deployment Mahyar T. Moghaddam, Oliver Aleksander Larsen Published: 2026-09-11Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-09-11 | cs.SE | ai-safety, csse, preprint | E12 / R13 (95%) | - |