Latest Research in Software Engineering

Top Research Topics in Software Engineering

• Software Engineering — 86 papers
• Cryptography and Security — 56 papers
• Computation and Language — 46 papers
• Artificial Intelligence — 30 papers
• Machine Learning — 14 papers
• Software Engineering Research — 11 papers
• Adversarial Robustness in Machine Learning — 9 papers
• Topic Modeling — 6 papers
• Software Testing and Debugging Techniques — 4 papers
• Natural Language Processing Techniques — 4 papers

Highest-Cited Papers

1. A Survey on Foundation Models for Personalized Federated Intelligence (1 citations)
2. Token-level defect feedback and alternating optimization for coupled code generation and defect detection with large language models
3. Stress-Testing Byzantine Robustness in Multi-Agent LLM Systems: Adaptive Adversaries and an Alternative Filtering Anchor
4. Can Adversarial Attacks Target Cutting‐Edge Language Models Fine‐Tuned for Hate Speech and Toxicity Detection?—A State‐of‐the‐Art Evaluation and Analysis
5. Specification Before Generation: A Pre-Registered, Five-Model Paired Evaluation of a Specification Frame for LLM-Generated Code in Money, Time, Idempotency, and Access Tasks
6. Specification Before Generation: A Pre-Registered, Five-Model Paired Evaluation of a Specification Frame for LLM-Generated Code in Money, Time, Idempotency, and Access Tasks
7. CodeAssay: A Multi-Metric Benchmark with Audited Ground Truth for LLM Code Generation
8. Characterizing and Classifying Self-Admitted Technical Debt in Infrastructure-as-Code
9. The More It Says, the More You Pay: A Black-Box Audit of Provider-Side Token Inflation in LLM Services
10. Spotlights: Discovering Improvement Opportunities in Software Repositories
11. Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning
12. From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
13. Distributed and Private Textual Data Synthesis from Embeddings
14. The Complexity Kink: A Prompt-Side Structural Complexity Index for Code-Generation Reliability
15. LLM-as-an-Improver: Turning Verification into Better Candidates
16. Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models
17. Closed-World Resolution Against Tool Hallucination in LLM Agents
18. Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
19. Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
20. An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks