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 16
UnityBench-Mini3D: Evaluating LLM Agents for 3D Game Development in Unity
Game development stresses coding agents in ways general software engineering does not: correctness depends on how engine APIs, serialized scene state, and runtime behavior interact, not on source…Small agents should know what their tools do
Small open language models can call tools, but they do not reason about what a call does: they delete without asking, repeat writes, re-read state they already hold, and issue one call per turn…Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering
Research on coding agents mainly focuses on generation quality.PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix
Proactive bug discovery is an important software-engineering problem.Before the First Edit? Measuring When Coding-Agent Guidance Actually Arrives
When a coding-agent harness promises guidance before the first source edit, what event does it actually intercept?CIVER: Causal Intervention Verification for Reliable Code Review
Code review is essential for maintaining software repositories by identifying defects, improving code quality, and supporting reliable software evolution.Do Coding Agents Still Need a Debugger? Frontier-Model-Based Fault Localization at the Accuracy Ceiling
To localize a fault, a coding agent can reason from source code alone or use debugger assistance by running the program and stepping through it in an interactive debugger.AGDecode: Semantic Attribute Grammar Derivatives for Safety-Constrained Decoding of Large Language Models
Large language models (LLMs) are increasingly used for code generation, motivating techniques that guarantee the structural and semantic correctness of generated programs.Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses
LLM agents are judged by two numbers: the size of the context window, and how often the final answer is correct.Stratum: Repository Memory for Coding Agents Beyond the Context Window
Context windows have grown a thousand-fold, yet coding agents still start every session with no memory of their past work.Can AI Guide Testing Without Generating Tests? A Comparative Study of AI-Assisted Unit Testing
Recent advances in generative AI have enabled assistants to generate increasingly sophisticated executable unit tests.Skill Dreaming: Evolving Repository Skills through Pull Request Streams
Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance.Agent or Human? Detecting Commits by AI Coding Agents in the Absence of Authorship Signatures
AI coding agents such as Claude Code, GitHub Copilot coding agent, and Cursor now commit directly to open-source repositories.MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge
Requirements engineering (RE) is foundational to systems engineering (SE), as requirement defects can propagate downstream and adversely affect development outcomes.Instant Software Factories
Coding agents can quickly build prototypes, but a long tail of fixes, optimizations, tests, and releases separates a prototype from a product.Building Mathematical Software -- Lessons from the Development of GAP
Mathematical software has particular needs that are not all covered by the existing literature on software engineering or algorithm design.How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation
Benchmarks for verifiable code generation usually test a proof against one fixed implementation.Your Wish Is My Commit: Over-Compliant Refactoring in AI Coding Agents
Large language models are known to be sycophantic, over-complying with users even when doing so is unproductive.kw-bench: Breaking Frontier Harnesses on Real-World Tasks
Each new generation of frontier model pushes the edge of what is possible.When AI Can Build It, What Should We Assess? Rethinking Evidence of Engineering Competence
Generative AI can produce code, tests, documentation, and technical explanations that resemble artefacts traditionally used as evidence of student competence, weakening the inference from artefact…