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 53
LLM-Assisted Automatic Security Proofs for Cryptographic Protocols: How Far Are We?
Large language models (LLMs) have shown strong potential for assisting software and security analysis tasks, yet their effectiveness in cryptographic symbolic protocol verification remains…The Compiler May Read It, the Agent May Not: Keeping Part of a Research Code Away from a Coding Agent
The compiler must read modules a physics-based solver cannot build without; the coding agent must not read that intellectual property.TokenCast: Forecasting Token Consumption During LLM Agent Execution
When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs.UNBIND: UNlearning By INference-time Directional Steering for Code LLMs
Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal.Evaluating Name-Only Directory Routing for One-Shot Code Search
Finding the right files is an early challenge for coding agents.Irene: Equivalence Checking of Hybrid Quantum Programs via Structure-Preserving Symbolic Reduction
Equivalence checking is essential for validating compiler transformations of hybrid quantum programs, which combine quantum operations, measurements, and classical control.The Uneven Decline of Collective Knowledge Production: Evidence from Stack Overflow After Generative AI
Generative AI (Gen AI) is reshaping how individuals learn and work, but its consequences for collective knowledge, the shared body of knowledge that online communities produce together, remain…When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
Before invoking external tools, an agentic LLM must select among a K-way action space: executing a call, seeking clarification, answering directly, or declining.The Invisible Scheduler: Dragging a Sprite Can Change What a Scratch Program Does
Tens of millions of children program in Scratch, whose programs are concurrent: when the green flag is clicked, every sprite's scripts start together and share the project's state.Live Architecture Models for Cloud-Native Architecture-as-Code: Early Results from Kubernetes Conformance Checking
Infrastructure drift can separate a running Kubernetes system from its documented architectural intent.The Invisible Throttle: Running on Borrowed Time in Scratch
Scratch has 135 million registered users, most of them children, and 164 million shared projects.From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents
Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open specifications?Assay: Claims That Decay With the Code. Content-Addressed Evidence Graphs for Accountable AI-Assisted Software Delivery
AI coding agents fail in two coupled ways.SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety
Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under benign instructions and environments.How Much Prompt Is Enough? A Blackbox Minimization of Few-Shots in LLMs
Prompts are the primary mechanism for directing the behavior of large language models (LLMs).Towards an AI Software Factory for Data Systems
AI-assisted coding tools deliver significant acceleration of coding, but only limited impact across the end-to-end software development lifecycle (SDLC)--an Amdahl's law effect!Strategies for Deploying AI Agents in Production at Scientific User Facilities
Agentic artificial intelligence (AI) is moving beyond research demonstrations toward production use at scientific user facilities, including light sources, neutron sources, nanoscience centers, and…LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents
Test-time scaling improves software engineering agents by generating multiple candidate trajectories and selecting the best one.KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation
High-performance GPU kernels are essential to modern machine learning systems, yet automatically generating kernels that are both correct and efficient remains challenging.Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring
Self-evolving agent harnesses continually update persistent components such as memory, prompts, skills, and tools.