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 45
A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models
Systems engineers use several diagrams to describe the structure and behavior of systems.CogAdapt: Cognition-informed Sparse Adaptation of Code LLMs
Large language models (LLMs) have become increasingly capable of generating code.Agent Skill Evolution: How Revisions Affect Coding Agents
Agent Skills, the SKILL.md files that tell an LLM coding agent how a project works, are revised like code, yet what a revision does to the agent is unknown.CARET: Training-Free Test-Time Scaling for Repository-Level Code Completion
Retrieval-augmented generation (RAG) dominates repository-level code completion: it retrieves cross-file context (R), then decodes one greedy completion (G).Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild
LLM-based agentic systems are emerging as a new software paradigm.Assembling Insights for Agentic Machine Learning Engineering Systems
Agentic machine learning engineering (MLE) is an emerging AI4SE application for complex ML tasks and a step toward recursive self-improvement of AI systems.Software World Models: From Consequence Prediction to Decision Value
A coding agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it.TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry
Large language models can generate runnable web applications from natural-language requirements, but many generated applications still fail interactive tasks.LLM-Based Test Generation: Information Sources, Generation Strategies, and Quality Evidence
Large language models are increasingly used to generate test scenarios, executable test suites, assertions, interaction sequences, and fuzzing infrastructure.Rethinking Tool Design for Agentic RCA: A Controlled Empirical Study
Large language model (LLM) agents are increasingly explored for root cause analysis (RCA) in microservice systems, yet empirical guidance on how to design and combine their tools remains limited.Characterizing Security Effects of OSS Vulnerabilities in Agent Systems
Software agents increasingly depend on open-source components when executing tools and interacting with external systems.Beyond Task Completion: Measuring Interaction Cost in Terminal User Interfaces
Large language models (LLMs) are increasingly used through terminal user interfaces (TUIs), yet task completion alone does not capture how difficult an interface is to understand and operate.VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence
Reliable learning-based vulnerability detection requires high-quality labels, yet datasets built from vulnerability-fixing commits may label functions as vulnerable simply because they were changed…SpecAgent: Empowering Program Verification with Agentic Synthesis of Formal Program Specifications
Formal specifications are essential for deductive program verification, providing semantic abstractions for compositional verification of complex software.StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions
LLM agents combine reasoning, tool use, and persistent memory to support work across tasks by reusing stored operational records as premises for later actions.Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models
Code language models must be maintained like the software around them: when a library evolves, a model keeps writing the interface that it saw during training.Understanding the Hierarchical Structure and Functional Landscape of the Model Context Protocol Ecosystem
AI agents increasingly rely on tools exposed through the Model Context Protocol (MCP) to complete user tasks.GNN-CB: A Graph Neural Network Competition Benchmark for Human and LLM Evaluation
Large language models (LLMs) have demonstrated strong performance on coding and reasoning benchmarks; however, their ability to solve graph-structured machine learning problems remains largely…Adaptive Code Revision Attacks on AI Pull Request Reviewers
Pull-request review protects software before new code reaches users, helping prevent vulnerabilities that could expose users to attacks.Scenario-Based Compositional Statistical Model Checking for Safety Specifications
In safety-critical domains such as autonomous driving, systems must be evaluated across a large number of environment conditions, often represented as composite scenarios built from primitive…