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 15
Behavioral Regression Detection for Pull Requests via Structured Oracles
Software regressions are unintended behavioral changes introduced by code modifications and are hard to detect at pull-request (PR) level.Chart the Invisible: Interactive Perception for Hidden-Target Exploration in GUI Agents
Despite rapid progress in command-line interface (CLI) tasks, recent LLM-based agents still struggle with reliable task execution through graphical user interfaces (GUIs).Testing with Coding Agents: A Large-Scale Comparison of Agent-Supported and Human-Authored Pull Requests
Coding agents increasingly contribute tests through pull requests that developers then maintain, so how testing work is divided affects long-term maintainability.RepoTrace: Improving Requirement Tracing in Multi-Round Agent Interactions
Code agents have become increasingly capable of performing software engineering tasks through interaction with software environments.Toward Evidence-Based Agentic Software Engineering
Task success rates and execution costs of agentic coding tools depend on both model and harness.Then there is prompt injection, a malicious email, ...: The Wild Wide West of OpenClaw Agentic System Security
AI-powered personal assistant frameworks such as OpenClaw combine LLM reasoning, persistent memory, tool invocation, local execution, and web-based workflows.Making Small Code LLMs More Efficient for Secure Code Review with Neuro-Symbolic Fine-Tuning
As AI coding assistants generate more code, the need to review it for security flaws grows.Understanding Python Linters through a Comprehensive and Systematic Empirical Study
Code linters, tools that automatically detect code issues, help developers accelerate development and improve code quality by identifying errors early.Benchmarking Coding Agents under Evolving Requirements
Software development with coding agents often begins with a rough request that users refine after trying the implementation.The Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents
Software engineering agents resend their entire trajectory to an LLM at every turn, motivating online trajectory reduction.Governing Enterprise AI Traffic at Scale: Design and Operation of a Policy-Driven, Multi-Vendor LLM Gateway on Envoy
Large organizations consume large language models (LLMs) from several vendors at once, each with its own API dialect, credential model, streaming protocol and pricing.Ranking Function Generation with LLMs for Termination
Ranking functions are a fundamental technique for proving loop termination, but constructing them manually is challenging and requires substantial expertise.JANUS: Synthesizing Cross-Layer Defenses Against Web Deserialization Attacks
Unsafe deserialization turns untrusted data into attacker-controlled execution, and a single vulnerability can admit diverse exploit variants that evade defenses tailored to a known exploit.The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
Web services increasingly expose backend interfaces that let users delegate tasks to AI agents, which invoke service operations directly without navigating websites.Making the Telemetry Pipeline Measurable: An Edge IoT Testbed and Dataset for End-to-End Latency, Provenance, and Energy-Aware Benchmarking
Edge-centric IoT systems are increasingly evaluated through sensor values or platform features, yet the telemetry pipeline itself, the sequence of sensing, serialization, message mediation…GEAR: Feature-Based Configuration and Code Generation for Agentic Systems
Engineering multi-agent systems (MAS) requires choosing agents, orchestration strategies, communication mechanisms, reasoning approaches, and memory configurations.FLOWSTEP: A Framework for Learning to Predict GitHub Actions Workflow STEPs
Continuous Integration and Delivery (CI/CD) are fundamental to modern software development, yet configuring pipelines such as GitHub Actions (GHA) workflows remains complex and error-prone.Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents
Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages and role agents.Continue or Restart? The Limits of Early Failure Prediction in Coding Agents
Early stopping promises to reduce compute costs for autonomous coding agents by terminating unpromising runs early.Testing Agentic Service Systems: An Agentic Living Lab Methodology Across the Physical-Digital Continuum
Task success is insufficient for testing agents that act for principals, change persistent business state, and affect physical processes: a useful result may be unauthorized, leave obligations…