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 31
The Role of Agentic Instruction Categories for Code Generation: A Study of Five Python Libraries
Agentic coding systems increasingly rely on repository-level agent files, such as AGENTS.md, to communicate project knowledge and developer intent.Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair
When code-repair agents fail, final tests reveal that a patch is wrong but not which earlier commitment caused it or which software obligation failed.Independent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware Design
LLM agents can write directed tests that close functional coverage, but coverage only shows that a state was reached, not that the data on the way there was correct.Realization Divergence in Multi-Provider Quantum Computing: A Pre-Registered Study of What Survives Measurement
Quantum programs pass through compilers, transpilers and vendor services before execution.CodeHealth Predicts the Token Cost of Agentic Code Review: A Pre-Registered Study of 465 Agent-Authored Pull Requests
Organizations increasingly delegate code review to multi-agent large language model (LLM) pipelines billed per token.Benchmarking and Enhancing Design-Aware Code Review in the Linux Kernel
Code review often requires reasoning beyond local correctness.Stateful Testing for Deep Learning Compilers
Modern deep learning compilers compile models lazily and cache artifacts across invocations.WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents
Real-world software engineering rarely consists of isolated changes.Are We Testing the Wrong Quantum Bugs? A Study of Fault Representation Gaps in Quantum Software Testing
Quantum software relies on compilers, intermediate representations, and execution frameworks that transform programs before execution.FDE-Gym: The Last Mile of AI Delivery
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets.From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems
Large language models (LLMs) provide a convenient interface for translating natural language commands into task plans for cyber-physical systems (CPSs).AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems
Evaluating language models and agents requires combining benchmark accuracy, judge-based assessment, runtime performance, tool-use behavior, and retrieval quality.Understanding LLM Hallucinations Caused by Soft Errors
While hallucinations in Large Language Models (LLMs) have been extensively studied from a software perspective, limited attention has been paid to hardware-level factors.ForTress: Bringing Assurance and Determinism for LLM-Driven Fortran-to-Python Translation
Modernizing mature scientific software from Fortran to Python can improve accessibility and integration with modern computing tools, but manual rewriting is expensive.SIEVE: A Parameterized GitHub Corpus Builder for Software Engineering Research
Software engineering research increasingly relies on large, richly annotated corpora of real-world code.Enjoying the Product but Not Joining the Builders: Investigating Why Students Don't Contribute to OSS
Open-source software (OSS) participation provides students with authentic exposure to collaborative, real-world software development, yet active contributions remain limited.Agentic Interpretation: Harness-Governed Evidence Construction for Software Agents
Software agents answer behavioral questions about code, such as whether a patch passes tests or which lines caused a failure.OS-Bench: Evaluating SWE Agents on Cross-OS Code Migration
Language-model (LM) agents are increasingly evaluated on repository-level software engineering (SWE) benchmarks derived from GitHub issues and pull requests.BenchChecker: Assessing the Credibility of Bug-Fixing Benchmarks for LLMs
While Large Language Models (LLMs) show promise for Automatic Program Repair (APR), existing benchmarks suffer from data contamination, in which test samples appear in training sets, artificially…Mission (Im)Possible: Towards Autonomous Discovery of Autopilot Logic Flaws in Open-Source Drone Frameworks
Autonomous drones are increasingly deployed in safety-critical tasks, yet their autopilot software can still contain subtle logic flaws that lead to unsafe behaviors.