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 72
Vectorizer: Vectorizing NumPy Programs with Shape-Guided Rewrite
NumPy is a widely used Python library for numerical scientific computing, known for its declarative APIs and its optimized implementations.SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents on challenging repository-level tasks.Qiushi Engine on AstaBench E2E-Bench-Hard
This report analyzes Qiushi Engine v0.8 across all 40 test tasks in AstaBench E2E-Bench-Hard, a benchmark that requires autonomous agents to carry a research question through experimental design…AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents
The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks.Tool Retrievers Are Underestimated: Annotation Expansion Reveals True Capability
In open-world scenarios with massive and evolving tool repositories, tool-augmented large language models rely on a retriever to surface relevant tools for a given query.RepoNav: From Snippet Retrieval to File-Centered Repository Navigation for Code Agents
Solving repository-level code tasks requires LLM-based agents to use code search tools to navigate large codebases and identify a small set of relevant files and functions.EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language Rendering
In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier information, changing what remains valid and what…Beyond Agent Harnesses: Cross-Substrate Authority for Multi-Agent Systems
Agentic systems persist model-visible memory while mutating workspaces, while a runtime, registry, or approval service may hold authority state outside both.The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?
Recent large language models can emit task-progress signals that agent frameworks use to decide whether a task should continue or stop, yet whether a model can reliably report its task progress at…Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers
Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous.API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy.It Is Not My Code Anymore
AI-assisted programming raises distinct questions about who produces code, who feels ownership of it, and who is responsible when it fails.MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions.ExecCritic: Learn to Test, Test to Improve for Coding Agents
Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue.Talking to Itself While Coding: What Makes Comments Help Code Generation?
Large Language Models (LLMs) often generate natural-language comments while writing code, and these comments become part of the context used to generate the code that follows.On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study
Computational notebooks are the standard environment for machine learning (ML) development.Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software engineer.LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text
Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipelines.Recompilation Is Not Enough: Test-Guided Decompiled-C Repair
Decompiled C often becomes recompilable only after repair, but recompilation alone does not establish test-observed behavior.Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evaluation Approach
The rapid digital transformation of manufacturing, often referred to as Industry 4.0, relies on seamless interoperability between physical and software assets.