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 6
TACT: A Pragmatic Approach to Qualitative Analysis with an AI Council
Qualitative data can tell software teams what their stakeholders need, yet rigorously analyzing thousands of qualitative responses takes expert time that few teams can afford or justify.How Much Do Modern Embeddings Reveal? Inversion Attacks on Commercial Embedding Models
Text embedding inversion reconstructs source text from fixed-dimensional vectors, posing a privacy risk to systems that store embeddings instead of raw text.Beyond the Agent Harness: Boundary Criteria for Software-Factory Orchestration - A Single-Operator Case Study
Several recent systems add a layer above the coding-agent harness that organises many agent runs into continuous delivery.How Python Audio Libraries Change Across Releases: Module Structure and Documentation
Developers who upgrade a Python audio library need to know what changed in the code they import and whether the release notes say so.When Does Combining Software-Effort Estimates Help? Evidence from Four Public Project Datasets
Combining estimates can reduce individual prediction errors, but an ensemble may also dilute an unusually accurate estimator or repeat errors shared by its members.KG-AST for Cheaper CI/CD: Budgeted Test Selection and AI Bug Review
Continuous integration and AI-assisted review spend the same budget on every commit, although few commits introduce bugs.Recursively Testing and Vibe Debugging a Google AI Studio Generated Vibe-Coded Database Software Application
This research paper proposes a broader definition of vibe coding, extending the original one with non-developers and natural languages other than English, and introduces the notion of vibe…APG: Agentic Static-Analysis Infrastructure on LLVM-IR Graph Databases
LLM-based coding agents increasingly rely on external program knowledge, yet access to static-analysis graphs alone does not ensure appropriate operation selection or evidence interpretation.Toward an Evidence-Based Template for Agent Instruction Files: An Empirical Study of Adoption, Consistency, and Maintenance
AI coding agents rely on repository-level instruction files to understand project conventions, development workflows, and constraints.Fault-Free Profiles and Decision-Level Training for Root Cause Analysis via Small Language Models
Root cause analysis (RCA) in microservice systems requires distinguishing failure sources from routine fluctuations and propagated symptoms.Harvesting SWE Benchmarks from Wild Vibe Coding Sessions
Development teams need reproducible tasks from their own repositories and workflows to evaluate coding agents.When Neither Side Confirms: Destructive Tool Approval Across MCP Servers and Hosts
LLM agents call tools that delete data or move money through the Model Context Protocol (MCP).CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents
The rapid growth of automated code generation has created a pressing need for automated code review.Does the Judge See What the Evaluation Requires? Input Assurance for LLM Agent Evaluation
An LLM judge assesses agent steps from text packets.IssueLighter: An Issue Type-Aware LLM Agent for Issue Report Validity Assessment
Invalid issue reports are prevalent in open source software (OSS) projects, imposing substantial burdens on maintainers who already face a high risk of burnout.HLSClaw: Bringing Vibe Coding to High-Level Synthesis through Skill-Based Agentic Harness
LLM agents are rapidly shifting software development toward intent-driven \emph{vibe coding}, yet their effectiveness drops sharply in high-level synthesis (HLS), where code optimization must…TLAPS-Bench: Formally Proving Correctness of Real-World System Specifications with TLA+ Proof System
TLAPS-Bench is a benchmark and execution harness for constructing machine-checked proofs for real-world system specifications in TLA+ with agentic AI.CAREFUL-Bench: Effect-Aware, Judge-Free Evaluation of Multi-Turn LLM Function Calling
The multi-turn checker of the Berkeley Function Calling Leaderboard (BFCL) checks only the final state of a simulated service, never the calls that produced it.COVE: A Task-Adaptive, Code-Based Ensemble for Proactive Verification of LLM Outputs
Large Language Models (LLMs) are now embedded in enterprise workflows, yet their outputs remain prone to hallucinations: plausible-sounding but factually incorrect or malformed content.Beyond Surface Metrics: Multi-Condition Requirements in Enterprise Maintenance and AI Coding Benchmarks
Repository-level AI coding benchmarks measure task success but do not directly capture the conditions required for software maintenance completion.