Applied & Human-Centered · Computer Science & AI
Software Engineering
The newest papers in Software Engineering that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
1,466 papers, from 31 August 2026 to 5 November 2026: 1,451 arXiv preprints and 15 OpenAlex records.
Get the few papers worth your time in Software Engineering every morning.
Follow Software Engineering and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 32
JevCoder: When Does Decision Delegation Pay Off in Code Repair?
A coding agent repeatedly makes decisions as it repairs code.When Does the Dependency Graph Help Code-to-Architecture Mapping?
Architectural technical debt arises when a system's implementation drifts from its inten ded modular decomposition, while the mapping between source files and architectural modu les is missing…Systematic Detection of Energy Regressions in Software Version Histories
Green software engineering is emerging as a crucial response to the rising energy impact of information technology, especially in continuous development.Taming the Online Software Engineering Tongue: Detecting and Reducing Offensive Language in Software Communities
Online Software Engineering (SE) communities such as Stack Overflow have become unwelcoming and hostile spaces, as evidenced by the presence of rude and offensive comments that are detrimental to…Temporal Adaptive Fine-Tuning for Code Comprehension
Repository-level code comprehension question answering (QA) supports developer reasoning over functionality and usage distributed across codebases.LintEval: Benchmarking LLMs on Linter-Guided File Refactoring
Linters are widely used in code maintenance and real-time IDE editing to surface lint alerts related to performance, style, error-prone, and other patterns in source files.SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution
Historical code changes provide convenient task boundaries, but do not identify which production functions selected tests exercise or support composing validated behaviors beyond a single change.The Code of Theseus: Can Agents Rebuild Software from Recovered Design Documents?
LLM agents increasingly design a system before implementing it, yet the data to train and evaluate them centres on implementation and testing: requirements and design artefacts are often missing…SWE-Stream: Scaling Executable Training Data for SWE Agents via Progressive Construction and Elastic Streaming
Software engineering agents have advanced rapidly, but scaling their training remains constrained by the limited availability of high-quality executable tasks.P2Patch: Exploit-Guided Vulnerability Repair
Large language models are increasingly deployed as autonomous agents for automated program repair, patching software vulnerabilities through multi-step reasoning and tool use.Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Agents driven by large language models are increasingly deployed on long-horizon tasks, where they use tools and modify real workspaces.What Should a Software Team Spend on Agents? Simulation-Based Cost Optimization of Mixed AI-Human Teams
AI agents are rapidly adopted in software development, but their token costs are rising and it is unclear how much a team should spend on agents, and on which tasks.PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates.HPCAgent-Bench: A Framework for Sound Benchmarking of Code-Optimizing Agents, Harnesses, and Skills
Coding agents are increasingly used to optimize code, but existing benchmarks fix one accelerator, programming model or harness, so they cannot isolate what each component contributes or show…Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised
Code models write Python when the prompt does not say which language to use.Robotic-supported Data Loss Detection in Android Applications
Smartphones have become integral to modern life due to their diverse applications.EnterpriseSynth: Zero-Execution SFT and Evaluation Data from OpenAPI Specs
Tool-using large language model agents require substantial training and evaluation data, yet collecting execution traces from enterprise APIs is often unsafe, expensive, or infeasible because of…Learning from Past Mistakes: AI-Assisted Analytics of Software Defects and Their Fixes for Future Defect Prevention - An Industrial Case Study
Despite advances in software testing and quality assurance, defects continue to recur in industrial software systems.Cross-Project Bug Localization: What Works, What Doesn't, and Why
Bug localization models require substantial within-project training data that newly active or small open-source projects rarely have.StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents
Long-horizon coding requires agents to maintain an evolving view of the project they are changing: what problem is currently being solved, what has already been learned or modified, which other…