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.
1,448 papers, from 31 August 2026 to 5 November 2026: 1,444 arXiv preprints and 4 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
How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering
LLM agents are increasingly used for repository-level software engineering tasks.Code, Commits, and Complexity in the GenAI Era: A Longitudinal Study of Team-Based Capstone Projects
Generative AI tools are now widely available to students, but little is known about how team-based project codebases have changed since they appeared.Take It From Here: Evaluating Coding Agents On Project Takeover
Coding agents increasingly collaborate on long-term projects.Rule-Guided and Trajectory-Aware Repair for LLM-Based HLS Generation
Large language models (LLMs) offer a promising path for directly generating functionally correct and synthesizable HLS-C from natural-language specifications.Req2Rust: A Requirements-Guided Agent Harness for Project-Level C++-to-Rust Migration
Memory-safety concerns make Rust an attractive target for modernizing legacy C/C++ systems, yet project-level C++ migration must balance semantic fidelity with Rust-oriented reconstruction.The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
How can an agent handle a real-world task end to end?Evolver: Turning Agent Exploration into Evolving Capabilities
Agent exploration produces valuable procedural knowledge, yet much of this experience remains confined to transient execution traces and is not systematically reused.What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays
Third-party application programming interface (API) relays offer access to large language models (LLMs), often at lower prices.Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems
Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write code, guess API payloads, and memorize operational constraints through prompt…ReConMem: A Graph-Based Dual Memory System for Repository-Oriented Conversations
LLM-based code assistants are increasingly used in iterative repository-level development, where effective assistance requires jointly leveraging evolving conversational history and repository…Fast Unsupervised Anomaly Detection Methods on Software Logs - An Empirical Study
Anomaly detection on software logs ensures system reliability through failure identification, root cause analysis and fault localization.Adapt the Object to the Subject: Representative Study Material for Empirical Software Engineering
External validity is a central concern in empirical software engineering, yet the debate has largely focused on whether study participants are representative.Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness
Large language models increasingly judge code, yet without external feedback such judgments are unreliable, and verifying them by executing tests or by extended reasoning is costly.Compositional Loop Invariant Inference for Multiphase Programs via Structured Neurosymbolic Reasoning
Loop invariants are essential for deductive program verification, yet automatically inferring them for {multiphase programs}, whose loops contain conditional branches that induce multiple execution…A Low Similarity Score Does Not Show Independence after Source-Conditioned Repository Rewriting
Maintainers sometimes cite a low token-similarity score as evidence that an LLM-assisted rewrite of a copyleft project is independent of the original.tok: a textual concrete syntax of BPMN and DMN for humans and AI agents
tok is a plain-text notation for Business Process Model and Notation (BPMN) 2.0.2 process models and Decision Model and Notation (DMN) 1.5 decisions.Requirements Nobody Wrote Down: Emergence in a Public-Sector ML Pipeline
Governments increasingly use machine learning (ML) to handle data volumes beyond their analytical capacity, yet little is known about how requirements arise and evolve as an ML experiment moves…Symmetry-Aware Surrogate-Assisted Testing of UAVs
We investigate a symmetry-aware surrogate-assisted testing approach for UAV autopilots.Detecting Silent Faults at the Environment-Trainer Boundary in Reinforcement Learning
Robot reinforcement learning increasingly runs environments outside the trainer: in another process, on another machine, in another language.RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection
LLM service selection requires performance evidence that reflects the demands of the current task.