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 51
How Should Diffusion Language Models Edit Code?
Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else.Zero2Repo: Can Coding Agents Build Repositories from Scratch?
Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a single language and depend on manually…E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch
Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories.OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration.From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning
We introduce C2C (From Codebase to Culprit), a framework for precise bug localization that progressively reduces the debugging search space across multiple levels of granularity: files, functions…MallocSan: A Memory Safety Tool for Native Closed-Source Applications
Memory-corruption errors remain a leading cause of high-impact vulnerabilities in C and C++ software.An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers
Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice.Rules to Tools: Executable Checks for LLM Agents in Scientific Computing
Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise.Towards Certificate-Driven Software Porting: A Self-Improving Agentic Harness for Scientific Program Optimization
The upgrade and rewriting of large scientific codebases has traditionally been a major challenge.Faultless: A Program Equivalence Technique for Validating and Evaluating Neural Decompilers
Neural decompilers are machine learning models which perform the process of decompilation, lifting code from a lower-level language to a higher one.JET: Judge-Guided Evolution at Test Time for Agent Programs
An agent's executable program governs how it uses tools, processes observations, and responds to failures.Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes
Agentic benchmarks guide model selection and training.ControlScope: Workflow Revision and Reliability in LLM Agents
How much of a running workflow should a language model agent revise?The Construction of an Empirical Dataset of Incomplete Software Changes from Open Source Projects
During software development, a modification to a software component may propagate across the system, requiring precise identification and correct revision of all affected components.DPS: Dual-Mode Precision LLM Serving with Semi-Unified Memory
Existing LLM serving systems virtualize and optimize KV-cache memory, but treat model-weight memory as fixed throughout execution.ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models
Transformer-based models are widely used for reasoning, coding, and multimodal agentic tasks.The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing
A small Office edit creates two obligations: propagate every required update and leave protected state untouched.From Noisy Telemetry to Actionable Warnings: GPU Failure Prediction in Industrial Clusters
GPU clusters are critical infrastructure for AI services, but accurate and actionable GPU failure prediction remains a problem in production settings.Verifying Neural Networks with Reinforcement Learning
Formal verification can play a key role in ensuring the reliability of Deep Neural Networks (DNNs) deployed in safety-critical systems.After the Fix: Transfer of Corrected Agent Experience
Does repairing an episode make its experience a better memory for the next task?