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 19
The Computational Assessment Stack: An Architecture for AI-Native Measurement
Test development is shifting toward automation and agentic artificial intelligence (AI), in which autonomous systems draft items at scale, assemble test forms, administer adaptive assessments, score…DRILS: Dependency-based Requirement Change Impact Analysis Using LLMs
Change is inevitable in software systems, where requirements must continuously adapt to evolving stakeholder needs, regulations, and project scopes.Why Does Structured Output Fail? An Empirical Study of Prompt-Enforced Pydantic Schemas Across Nine LLMs
Pipelines that require structured outputs from hosted language models often specify a Pydantic schema in the prompt, validate the response, and retry when validation fails.PASS Is a Claim, Not an Observation: Mechanical Re-verification of 10 Self-Asserted Fix Claims in a Live Multi-Agent Audit Layer
When agents claim to have fixed their own defects, how do we know the fix is real?Are LLM-Generated Formal Specifications Faithful to Their Requirements? A Study on Bimodal Formal Specification Generation
Formal specification generation is a critical step towards formal verification and correctness assurance of software.CrowdStrike Channel File 291: An Engineering Analysis of a Global Endpoint Outage
On July 19, 2024, a CrowdStrike Falcon content update caused Windows systems to crash, affecting about 8.5 million devices according to a Microsoft estimate.Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers
Agents and verifiers often rely on the text a tool prints, and that text can misrepresent what the tool actually did, even when the tool's computation is correct.Beyond Correctness: How Novice Software Engineering Students Exercise Oversight of Generative AI
Generative AI (GenAI) is shifting software engineering students' work from producing artefacts towards evaluating and supervising AI-generated outputs.Shorter Is Not Cheaper: A Controlled Comparison of Declarative Animation Specifications and Free-Form Code for LLM-Generated Explanations
Chat assistants increasingly answer conceptual questions with interactive, animated explanations, generated either as free-form HTML/JavaScript or as declarative specifications that a fixed runtime…Pairing Matters: Performance, Failures, and Efficiency in Lightweight Coding Agents
Self-hosting coding agents is often necessary for software-engineering teams that must keep proprietary code and development traces within controlled infrastructure.Large-Scale Study of GitHub Copilot Trajectories
AI coding agents are increasingly integrated into software development workflows.From Faulty Claims to Incorrect Patches: An Empirical Study of Task-Grounded Reasoning in Coding Agents
Large language model (LLM)-based coding agents increasingly resolve real-world software engineering tasks, yet still fail on many of them.DeepAVR: Deep Analysis via Multi-Agent Collaboration for Automated Vulnerability Repair
Automated Vulnerability Repair (AVR) has emerged as a critical defense against software security flaws, aiming to triage and fix bugs autonomously.Search-Based Testing of Modality Sensitivity in Vision Language Models
Vision-language models (VLMs) process images and text jointly, yet robustness evaluations often perturb these inputs separately or assess only predefined corruption levels.Complexity concentration as a god-class and god-method detector: a pre-registered test of a scale-free outlier rule against tool definitions and human labels
God-class and god-method detectors mark concentrated complexity with a raw-scale threshold, a constant fitted on a corpus and re-fitted when the population moves.OPTARI: An open-source software framework for clinical translation of optoacoustic imaging
Combined optoacoustic (OptA) and ultrasound imaging is a promising modality across a wide range of pathologies.WaitLens: Temporal VLM-Based Adaptive Waiting for Industrial GUI Testing Agents
Improving the efficiency of GUI testing agents is important for industrial deployment.When Agents Fail: Model or Harness--Who's to Blame?
LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior.Beyond Coverage and Mutation: A Blind-Spot Analysis of LLM-Generated Unit Tests
Existing evaluation protocols for unit tests rely on aggregate metrics such as branch coverage and mutation score.Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance
LLM agents increasingly rely on external tools exposed via the Model Context Protocol (MCP), yet current benchmarks assume tools respond correctly and on time, leaving agent resilience to realistic…