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 26
Foreword: Pre-Generation Prediction and Characterisation of LLM Test Failures using the Jacobian Lens
Testing LLM-based software is expensive: each input needs several sampled responses, each judged by a costly oracle.ExeBench-FHD: Addressing Fidelity Issues in Decompiler Evaluation
ExeBench is one of the most widely used benchmarks for evaluating LLM-based decompilers.A Multimodal Engineering GraphRAG Framework for Post-Wind-Event Building Assessment and Recovery Inference
Post-event building assessment requires linking observed physical damage to its consequences for safety, habitability, functionality, and recovery.Quantum Broker: QoS-Aware Distribution of Quantum Computations
Cloud-accessible quantum computing has made heterogeneous Quantum Processing Units (QPUs) available through provider platforms that differ in qubit technology, calibration state, queueing behavior…Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model.InterWebCoder: Learning Interactive Webpage Generation from Executable Tests via Reinforcement Learning
Interactive webpages underpin modern applications, but reproducing both their visual appearance and multi-step behavior remains challenging for multimodal large language models (MLLMs).TraceLite: Efficient Trace Reduction for SWE Agents via Optical Compression and Redundancy Removal
Software engineering agents solve repository-level tasks through iterative tool use, but their continuously growing interaction traces incur substantial token consumption and inference overhead.Industrial ReMEmbR: Scaling Spatiotemporal Memory to Robot Fleets
Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs.PCLA-Bridge: A Framework for Cross-Domain Deployment of CARLA Agents
Most high-performing end-to-end autonomous driving agents (ADAs) are developed for the CARLA Leaderboard, tightly coupling them to CARLA's APIs, sensor layouts, coordinate systems, and internal clock.Multi-agent LLMs on the Cloud-Edge-IoT Continuum: A Systematic Mapping Study on Architectures, Deployment, and Evaluation
LLM applications are increasingly built as systems of cooperating components rather than as single prompt-response pipelines.Sign Here: Attributing a Source for a More Trustworthy Software Supply Chain
Software supply chain attacks continue to be on the rise, exploiting the trust that helps open source ecosystems thrive.How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery
How much does an agent harness affect vulnerability discovery, and does its value depend on the model?Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback.SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges
LLM judges increasingly mediate benchmark evaluation, model selection, data curation, and training.Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents
Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way.Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents
While large language models are increasingly deployed as tool-calling agents, their safety evaluations still focus primarily on their ability to refuse harmful requests in text.When EVM Defaults Break: Three SDK Patterns for UTXO-Family Wallets
Mainstream Web3 SDKs (e.g., ethers.js, viem) bundle three coupled assumptions: an account-based ledger, a single secp256k1 signer, and input-selection-free transaction construction.Self-Evolving Static Analysis via LLM Pseudo-Labeling
Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules have not yet been written for the code in front of us.Agentic Verified Optimization of Real-World Software
Program optimization aims to improve performance while preserving behavior.Step-Aligned Script Generation with Verification and Recovery for Web Automation Testing
Automated generation of end-to-end web tests remains costly: developers must identify stable selectors, encode multi-step workflows, attach assertions, and maintain scripts as interfaces evolve.