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, page 3
Beyond Infraction Scores: Failure-Boundary Profiles for Closed-Loop Evaluation of Driving and Robot Navigation Agents
Closed-loop driving benchmarks in CARLA rank agents by a driving score that multiplies route completion by an infraction penalty.Trace2Eval: Contextualized Evaluation of Coding Agents from Real-World Traces
Coding agents are increasingly used in real-world workflows across diverse domains, motivating evaluation grounded in real user tasks.HELIX: HEterogeneous LLM Inference with FleXible and Fine-Grained Partitioning
LLM inference is inherently heterogeneous, with performance bottlenecks shifting throughout inference phases down to individual operators.Scythe: Semantic-Aware Rewriting for Fast,Effective Program Reduction
Automated program reduction shrinks a program into a smaller one that preserves a property of interest.Construction Contracts for Generated Embedded Domain-Specific Language Programs: A Measurement Protocol and a Conditional Effect
A generated domain-specific program can be accepted by its host and still miss the reference construction.EPISTEME: Trustworthy Coding Agents Through Tool Call Intent
Coding agents change software through tool calls.PatchCon: Patch-aware Weighted Supervised Contrastive Learning for Vulnerability Detection
Automated vulnerability detection is critical for securing modern software systems, yet existing learning-based approaches often treat functions as independent samples and underuse the supervision…AgentTrustCI: Build-Time Policy, Grounding, and Trajectory Tests for Java LLM Agents
Infrastructure security does not establish whether an LLM agent selected an allowed tool, grounded its answer in tool output, or followed a required workflow.Rethinking Access Control for AI Agents: Recent Advances and Open Challenges
Large language model agents access data, invoke tools, and act on users' behalf.GH-AWTrace: A Large-Scale Dataset of GitHub Agentic Workflow Execution Logs
Agentic workflows enable AI agents to perform recurring repository tasks on schedules or in response to repository events.MCP-Eco: A Linked Dataset of MCP Servers, Consumers, and Development Activity
The Model Context Protocol (MCP) enables LLM agents to access external tools and data.Operationalizing Responsible AI in MLOps and ML Production: A Systematic Literature Review
Artificial intelligence (AI)-enabled systems are increasingly deployed in operational environments where machine learning (ML) models interact with changing data, users, infrastructure, and…When Can Self-Play Fix a False Belief? Answer Keys, Pass Bands and Replacement Rules in an Execution-Grounded Loop
Self-play loops in which a model writes tasks, derives an answer key and trains on its own matching solutions are often called grounded when the key comes from executing code.Call-Level Revision Contracts for LLM-Authored Workflows
Durable execution engines replay a recorded history and do not compare activity payloads.An LLM-Orchestrated Neuro-Symbolic Framework for Verifying Diagnostic Signal Reachability in Electronic Systems
Diagnostic Signal Reachability (DSR) captures whether board-level health signals are observable by management controllers, including baseboard management controllers (BMCs), complex programmable…Follow the Policy, Fail the Benchmark: Auditing and Revising Policy-Based Decision Benchmarks
Policy-based decision benchmarks evaluate whether systems apply written rules to financial and operational cases.Automatic Assistance to Reduce Information Overload during Software Issue Report Understanding
Modern issue tracking systems are used to log an issue and track it from its inception to closure.Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons?
Developers rarely give a coding agent a single request: they ask it to build a component and then to extend, upgrade, and optimize it, each time on code the agent itself wrote.Global Surveillance Under the Lens: Reconstructing Passive Dolev-Yao Intruders
Global surveillance systems record large volumes of network traffic for retrospective analysis, but packet captures alone reveal little about protocol-level semantics.SeVerus: Context-Aware, Gamified Benchmarking for Rust Verification
Coding agents achieve high success rates on existing benchmarks for Verus, a verifier for Rust programs.