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 27
Better Specifications, Better Code: Fine-Tuning LLMs for Behavioral Contract Generation
Large language models (LLMs) demonstrate strong code-generation capabilities but often struggle with functional correctness due to implicit or ambiguous behavioral requirements.Selecting and Composing Agent Design Patterns: Industrial Case Evidence and Controlled Reference-System Experiments
Agent pattern catalogs describe architectural alternatives, but engineers also need evidence for selecting and composing them.Beyond Leaderboards: A Method for Application-Specific Capability Profiling of Large Language Models
Public leaderboards rank large language models (LLMs) in general, but an engineer has to choose a model for a specific application, architecture and cost.How Effectively Do Security Skills Guide Coding Agents in Vulnerability Detection in Linux Kernel?
Large language model (LLM) coding agents, such as Claude Code, are increasingly used for security auditing, with task-specific skills providing reusable vulnerability-analysis procedures.What Is Under the Hood? A Cross-Ecosystem Study of Vulnerable Dependencies in Construction Software
The construction industry increasingly relies on software built from third-party components, yet the dependency composition and known-vulnerability exposure of construction-related software remain…From Finding to Fixing: How Useful is Fault Localization for Agentic Program Repair?
Fault localization (FL) aims to identify code locations responsible for software failures and is commonly evaluated by how accurately it ranks known fault locations.SWE-Residual: Evaluating Starting-State Robustness of Coding Agents
Software engineering (SWE) benchmarks are the primary way to measure the capabilities of coding agents: an agent is placed in a code repository or machine environment, given a request, and judged by…SPLASH: Contrastive Audit Pressure for Detecting and Localizing Security Hallucinations in Generated Code
Code generated by large language models often passes every functional test while remaining insecure.Function Contracts for Bounded Model Checking of C Programs
Bounded model checking unrolls a program into a single formula, so a function holding a loop costs the solver a fresh copy of that loop at every call site.The EBC Proportionality Law: A Recurring Architectural-Role Pattern Across Java Software
Architectural roles describe how responsibilities are distributed within software systems.When Coding Agents Outpace Review: Evaluating PRD-Driven Development in Mature Enterprise Repositories
Coding agents increasingly undertake development tasks in mature enterprise repositories, yet existing benchmarks offer limited insight into whether they fulfill complete Product Requirement…Co-Evolving Policy and Reward for Code Generation: A Mechanistic Study of Single-Adapter Drift
Reinforcement learning with verifiable rewards (RLVR) is particularly well suited to code generation because generated programs can be objectively evaluated through execution.VerusEval: Evaluating LLM-Generated Verus Specifications Beyond Verifier Acceptance
Large language models (LLMs) are increasingly used to generate Verus contracts for Rust programs together with the proofs that establish them.Certifying Repeatable Entry-Replay Witnesses for COBOL-to-Java Migration
Producing synthetic data for comparison testing a migrated COBOL application is a major challenge that agentic migrations face today.A Hybrid Information Flow Analysis Framework for Android Hybrid Apps
The WebView interface in Android (hybrid) applications enables the native side (e.g., Java) to exchange data with the Web (e.g., JavaScript).XRust: Detecting Logical Races in Rust Linux Drivers
Rust is increasingly used in Linux to improve memory safety, but its guarantees do not prevent logical races: individually synchronized operations can still interleave in ways that violate…Stop Paying by the Letter: Accelerating Full-Chip RTL Simulation with Host-Side Tokenized Logging
Firmware diagnostic logging (printf) is an essential debug instrument in full-chip SoC design verification, yet it imposes a heavy tax on cycle-accurate RTL simulation: formatting a 30-character…Characterizing Post-Incident Software Evolution
After a software incident, organizations attempt to improve the reliability of their software systems by conducting post-incident analysis and identifying actions to prevent or mitigate similar…Documentation Drift in AI-Generated Pull Requests
AI coding agents now contribute to software repositories at scale, yet their documentation practices remain uncharacterised.AgenticVulHunter: Bringing Local Agentic Vulnerability Hunting to Your Terminal
Finding vulnerabilities early, before they can affect the production system, is important for reducing the risk of any software attacks.