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 46
Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction
Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution.UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents
Tool-using AI agents are increasingly deployed across enterprise software systems, yet widely used benchmarks primarily evaluate nominal task completion, conflating baseline planning competence with…Functionally Equivalent or Not? Graph-Grounded Differential Surrogate Execution for Code Equivalence
Determining whether two programs are functionally equivalent is central to code modernization, patch validation, refactoring, and code-generation evaluation.Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents
Agents built on large language models (LLMs) build and run software through tool calls.What Does a Harness Buy? Tokens, Mostly
A coding agent is a language model wrapped in a harness: the system prompt, the tool set, and the context management that turn a chat model into something that can work inside a repository.World Requirement Model: Learning Requirement-Change Consequences from Typed Artifact Graphs
Requirement changes can affect connected stakeholders, constraints, components, and tests.Noise-Resilient Testing of Quantum Programs Based on Output Dominance
Quantum software testing (QST) is a central quality-assurance activity for checking whether quantum programs conform to their specifications.DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents
Testing deep reinforcement learning (DRL) agents in cyber-physical systems aims to uncover diverse failures before deployment, but each execution can be expensive.Practical Runtime Enforcement of First-Order Temporal Requirements
Runtime enforcers observe a system's behavior and exert control over it to ensure that the system always adheres to its requirements.When Talk Isn't Code: Comparing LLM Agents That Simulate and Develop Software
LLMs are used both to simulate network protocol implementations, as honeypots do, and to write them.Back to the Future: Regressing Readability Features from LLMs
Code readability supports software understanding, review, and maintenance.RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair
Large language model (LLM) agents increasingly reuse prior experience, but most approaches assume that problems and solutions are already aligned.Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?
Logging code supports debugging, monitoring, and software maintenance, but excessive logging can add noise, impose runtime overhead, and obscure diagnostic information.Asymmetric Repository Lineage Modeling and Verifier-Guided Coordination in Concurrent AI Coding Agents
Concurrent AI coding agents create a coordination problem in which cheap signals may prioritize work, but only an executable checker can establish the property being claimed.Pattern-Guided Graph Synthesis for Suppressing Known Defects in DL Compiler Fuzzing
Fuzzing is effective at finding bugs in deep learning (DL) compilers, but existing fuzzers repeatedly trigger faults they have already uncovered.WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness
Evaluating WebUI code generation at scale is difficult: outputs may compile and look plausible yet fail under user interaction, and prior benchmarks largely rely on free-form prompts with static…Self-Supervised Scaling of Terminal Environments for Scientific Domains
Terminal agents are increasingly deployed beyond software engineering in science and other specialized domains.VeriPy Source-Preserving Verification and Compatibility Checking for Python Components
Keeping a Python program and its formal guarantees aligned is a continuing maintenance problem.Discriminating Fixture Coverage in Agent-Infrastructure Verification Suites
Invariant suites and runtime monitors increasingly gate agent deployment decisions, and the evidence offered for any particular suite is almost always a single observation: it passes an…GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial Testing
Test-driven development gives AI coding agents executable requirements for implementing software.