Latest Research in Software Engineering

Top Research Topics in Software Engineering

• Artificial Intelligence — 96 papers
• Computation and Language — 92 papers
• Machine Learning — 38 papers
• Software Engineering — 17 papers
• Topic Modeling — 14 papers
• Information Retrieval — 7 papers
• Cryptography and Security — 6 papers
• Computer Vision and Pattern Recognition — 4 papers
• Scientific Computing and Data Management — 4 papers
• Ferroelectric and Negative Capacitance Devices — 3 papers

Highest-Cited Papers

1. The Agent Harness Playground: A ReAct-Style Agent Harness with Budgeted Multi-Agent Delegation and Embedded Quantitative Equity Research
2. The Agent Harness Playground: A ReAct-Style Agent Harness with Budgeted Multi-Agent Delegation and Embedded Quantitative Equity Research
3. Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models
4. From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models
5. Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance
6. VideoResearcher: Self-Improving Tool Design for Long-Video Understanding
7. Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data
8. AutoData: Agentic Search for Pre-training Data Selection
9. Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics
10. DeltaSelect: Affordable A/B Testing for Coding Agents
11. An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS
12. MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
13. Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition
14. Compass-v3: Scaling Domain-Specific LLMs for Multilingual E-Commerce in Southeast Asia
15. BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs
16. Benchmarking locally hosted language models for journal editorial work on a compact desktop workstation
17. Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
18. Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs
19. Do Large Language Models Correct False Technical Premises? An Empirical Case Study in Computer Science Question Answering
20. Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record