arXiv AI

Spec-Driven PBT: Deriving Semantic Invariants from Code Specifications for Agentic Property-based Testing

Spec-Driven PBT is a testing approach that derives invariant properties from a natural‑language specification before inspecting the implementation to generate concrete tests. In a study of 25 ViBench applications, it uncovered a unique set of bugs that Code‑driven PBT missed, using 2.4× fewer property tests and finding roughly the same total number of bugs with little overlap between the two methods. The approach highlights how specifications can reveal bugs related to documented product workflows, complementing implementation‑focused testing.

arXiv AI
Oct 31

Skeleton Coding: Program Structure as a Specification for Agents

The paper introduces Skeleton Coding, a method where developers jointly specify a program’s structure—its data types, modules, and functions—alongside behavioral tests. This approach allows the agent to first commit to a structure, narrowing the search space of possible programs, and then use tests to select the correct implementation. Empirical results across multiple models and benchmarks show that skeletons can dramatically reduce the number of required tests, improve accuracy, and lower implementation costs.

By Aditya Golatkar, Alessandro Achille, Renos Zabounidis, Vlad Sobal, Yangruibo Ding, Baishakhi Ray, Jonathan Buck, Guy Van den Broeck, Maryam Fazel, Pietro Perona, Wei Xia, Stefano Soatto
Hugging Face Trending Papers
Jul 29

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fundamentally harder. Recent benchmarks such as ProgramBench quantify this gap: given only natural-language documentation and an execute-only binary as a behavioral oracle, even frontier models solve fewer than 1% of instances.

arXiv AI
Oct 28

Benchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements

The paper introduces Req2Test-Bench, a benchmark of 5,086 instances linking natural‑language Gherkin requirements to developer‑written test implementations across five languages and four BDD frameworks. It evaluates eight agent–model–reasoning setups, finding that while the best configuration (Codex with DeepSeek‑V4.1‑Flash) produces passing tests for 82.8% of cases, only 33.8% are behaviorally adequate, as measured by kill‑completeness. The study highlights diminishing returns from scaling agents, the impact of under‑specified requirements, and the potential of requirement‑grounded harnesses to improve test generation.

By Binhang Qi, Yiming Liu, Yun Lin, Yangjie Zhou, Hailong Sun, Jin Song Dong
arXiv AI
Oct 23

Who Verifies the Builder? Toward Independent Assurance for Agent-Produced Software

The paper discusses the need for independent assurance when coding agents produce both software and its correctness evidence. It identifies four gaps—requirement, conformance, evaluation, and model—between stakeholder intent and production, and proposes a verification framework that separates building from verifying. The framework introduces a Verification Contract, a specification-first phase, and an implementation-aware phase using mutation analysis, property-based testing, and fuzzing, and is evaluated in a study showing that an external verifier detected more seeded faults than the builder’s own tests.

By Sion Israel Sion, Alain April
arXiv AI
Oct 28

FeatureArc: Benchmarking Coding Agents on Evolving Features

FeatureArc is a new benchmark that evaluates coding agents on the evolution of software features, requiring agents to extend a feature across multiple stages while preserving earlier functionality. The benchmark uses a pipeline that constructs tasks from real repository histories, validates fail‑to‑pass and pass‑to‑pass tests, and covers four programming languages. In tests on 73 tasks, agents performed well on the first stage (62.7% success) but dropped to 28.5% when the entire feature was evaluated, with inherited defects causing most failures.

By Yunlong Wang, Alyssa Wu, Cuiyun Gao, Jia Feng, Songyuanyi Lu, Zhichao Hu
arXiv AI
Oct 2

Code That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software

The paper investigates how well large language models specify the software environments needed to run AI-generated code. Using a new agent protocol and a three‑layer dependency framework, the authors evaluate three coding agents across four languages and fifty tasks, finding that dependency specifications are often inconsistent, redundant, or incomplete. Agreement on dependency sets is as low as 7% for identical tasks, and newer agents show no improvement, indicating that environment specification remains a significant, unaddressed challenge in code generation.

By Bhanu Prakash Vangala, Tanu Malik