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 59
FairTest: Search-Based Fairness Testing for Multi-Agent Reinforcement Learning Systems
Multi-agent Reinforcement Learning (MARL) trains a team of agents that share one environment and learn their policies together.Constraint-Driven Context Engineering: Designing Domain Interfaces for AI Systems
Generative AI systems are increasingly deployed to address domain problems.Issuer-Sovereign Agentic Payments
AI agents are beginning to make real payments.FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration
Deployment requires an agent to turn application code into a running system whose services connect, become ready, and remain observable.Unity Insight: A Production Code--Asset Index for LLM Coding Agents in Unity Projects
LLM coding agents increasingly operate inside game-engine repositories, where application logic is inseparable from serialized assets: a single gameplay change may span C\# scripts, prefabs, scenes…AST-Based Automated Elimination of break and continue Statements in Java Code
This work presents the development of an automatic refactoring tool for Java code built on top of the Eclipse JDT API.Foundations of Algebraic Architecture Theory: A Rising Sea of Geometry, Transport, Comparison, and Reconstruction
AI-generated software changes make it increasingly important to determine what a change preserves, where local consistency fails to extend globally, and which alternatives remain.A ready-to-deploy MLOps software platform for satellite and NEO detection at meter-class ground-based observatories
Ground-based astronomical observations frequently contain streaks produced by artificial satellites, space debris, and potentially Near-Earth Objects (NEOs).Satisfaction Is Not Explanation: Auditing Vacuity and Training Influence in Temporal-Logic-Guided Reinforcement Learning
A reinforcement learning policy that satisfies its temporal-logic specification has passed a test, not an assurance argument.LLM-Assisted Workflow for Structural Difference Visualization in Evolving Software Requirements
This paper presents an LLM-assisted workflow for visualizing structural differences in evolving software require- ments.Can LLMs Catch a Rigged Backtest? A Clean-Control Calibration Benchmark
Backtest auditing is a calibration problem: high flaw recall is not useful when the model falsely flags matched clean strategies.Scenario-Driven Neuroevolution: Using Models to Guide Test Generation for Games
Automatically generating test inputs for games is challenging, as test generators must master the game to reach advanced program states while also ensuring robustness against the heavy program…From Agent Output to Authorized Transition
Agentic engineering systems can edit repositories, run tools and tests, build firmware, synthesize schematics, and prepare deployable or manufacturable artifacts.Entangle: Uncovering Collaboration in the GitHub Quantum Software Ecosystem
Quantum computing is moving from research laboratories towards early commercialization and broader socio-technical adoption, supported by sustained hardware progress and a rapidly expanding…Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark
Large language models (LLMs) are increasingly used in coding tasks, but their ability to reason about code execution remains unclear.Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior
LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files.Pretraining and adapting a language model on a dependency-free stack: GPT-2 124M from random weights, reproduced against llm.c, and a clinical adapter for Qwen3-0.6B
Almost every language model in service was trained by one family of software.Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents
Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution evidence.Time-Series Foundation Models That Understand Data Revisions
Historical observations are not always fixed: statistical agencies revise previously published values as new evidence arrives.Agent Approval Laundering: Transitive Effects Beyond the Approved Invocation
Coding-agent approval interfaces bind a human decision to a command or tool call, while developer tools execute the transitive workflow that invocation activates.