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 35
When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems
LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks.Security in LLM-Assisted Coding: A Systematic Literature Review
Large Language Models accelerate software development but introduce severe security vulnerabilities.Reviewing Beyond the Change: Repository Size and Existing Code Across Agent and Human Pull Requests
Reviewers sometimes name existing repository items outside the change under review.SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications
Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weights.To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse
Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generated by a related sender model.LLM-based Code Auditing by Inferring and Evaluating Developer Assumptions
When we see a null pointer check, we know that the developer believes that the pointer may not be initialized.A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
Large language model agents are emerging as an important new class of users of desktop applications.Passing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation
Planning and revision are intended to bring generated code closer to the task specification.Grounding Deep Learning Framework Testing in Data Flow
Data flow underlies deep learning (DL) framework execution, including automatic differentiation and operator-fusion optimization.Separating Statistical Inference from Experimental Runtime: An Architecture for Sequential Scientific Analysis
Sequential statistical procedures are increasingly embedded in scientific systems in which observations arrive incrementally from heterogeneous sources.Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair
Large language model (LLM) code-repair systems fix faulty programs by repeatedly generating and testing revisions.BRQGen: Towards Adaptive Completeness Assessment and Follow-Up Question Generation for Bug Reports
Many bug reports lack the necessary information required to reproduce issues.Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents
A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass.HoldSpec: A Machine-Checked Model and Conformance Suite for the Payment Authorization Hold Lifecycle
When a merchant authorizes a card and captures the funds later, the money sits in a state that neither party fully controls: held on the cardholder's account, not yet taken, and due to lapse on a…Specification-Based Testing of Large Language Models
Model cards, system cards, and safety reports increasingly document LLM safety behaviors, yet safety evaluations typically start from predefined benchmarks rather than asking which documented claims…Taylor-Approximation-Based Repair of High Floating-Point Errors
Numerical libraries can still lose many bits of accuracy on localized ill-conditioned inputs, such as roots, poles, cancellation points, and branch boundaries.SecReason: Vulnerability Detection and In-Stream Self-Repair for LLM Code Generation
Large language models (LLMs) may introduce security vulnerabilities into generated code, which can persist into production when verification focuses on functional correctness.Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk
Executable tests grade large language model (LLM) coding-agent patches for leaderboards, rewards and self-improvement.Rethinking SZZ Search Strategies: Lessons from Claude Code
Identifying bug-inducing commits (BICs) is important for studying software bugs and maintaining software, yet the accuracy of existing SZZ methods remains limited.When Is a Reconciliation Break Real? A Temporal Correctness Contract for Streaming Financial Reconciliation
Reconciliation systems decide, continuously, whether money the ledger expected has arrived at the bank.