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 63
One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be uneven: gains in some categories coincide with…Omni2Web: Benchmarking Audiovisual Website Development
Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor trajectories, page state, and edit history.VSpector: Specification-Driven Bug Detection for RISC-V CPUs
Detecting RTL design bugs in open-source RISC-V CPU implementations is critical for ensuring system reliability.VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks
Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks.Packaged, But Not Portable: Why Conforming to the Agent Plugin Standard Is Rare, and Why Conforming Would Not Be Enough
Coding agents are extended by plugins: installable bundles that ship skills, sub-agents, commands, hooks, and tool servers.MCPGen: Benchmarking LLMs on Executable MCPWorkflow Development
We study whether LLMs can produce executable workflow artifacts that remain consistent across graph structure, tool implementation, schema bindings, and runtime wiring.TRACTOR Benchmark for Evaluating C to Rust Translators
Memory-safety vulnerabilities remain a persistent source of security risk in critical software, much of which is implemented in memory-unsafe languages such as C and C++.From Code to Requirements: Agentic Reverse Engineering of Business Rules at Enterprise Scale
Business requirements for enterprise software systems are rarely captured in structured form; the logic resides instead in source code, configuration files, and institutional memory.Towards the Generalizability of Leveraging ChatGPT in APR via Self-enhancing: An Empirical Study
Automated Program Repair (APR) increasingly relies on Large Language Models (LLMs)."It Comes in Notebooks": Changes and Challenges when Operationalizing ML Prototypes
Machine learning practitioners commonly prototype models in computational notebooks before transitioning them to automated production systems.Characterizing Feedback Statements in Machine Learning Jupyter Notebooks
Machine learning development in Jupyter notebooks is iterative and feedback-driven.NostrAgent: A Decentralized Identity and Delegation Architecture for Sovereign Agentic Systems
Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subtasks to other agents, and pay for metered resources.Diversity-Guided Search-Based Testing of Large Language Model Applications
Large Language Model (LLM)-based applications are increasingly deployed across domains including customer service, education, and mobility.SoK: From Finding to Deployment: Systematizing the OS Kernel Bug Lifecycle
Automated kernel bug discovery has advanced rapidly.Security of Agent-Integrated Software: When Human Operations and Agent Actions Coexist
Agent-Integrated Software (AIS) embeds an intelligent agent in a conventional application, supporting both human operations and agent actions.SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering.Embedding Drift in Code Vulnerability Models Under Intended Behaviour-Preserving Transformations
Code edits that preserve program behaviour can shift frozen code embeddings across classifier decision boundaries, causing correctly detected vulnerabilities to be predicted as benign.License Compliance in Open Source Cybersecurity Projects
Developers of cybersecurity software often include and rely upon open source software packages in their commercial software products.Two's a Crowd: Human and AI-Based Copresence for Developers with ADHD
Effective collaboration and communication are vital to developer productivity and well-being, yet remain constrained by human factors such as attention, intrinsic motivation, and interpersonal…Efficient Benchmarking in Production: A Study of an Evolving LLM Agent
Production LLM agents are evaluated repeatedly as they evolve, but full agent benchmarks are costly to rerun.