Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills

• URL: http://arxiv.org/abs/2609.12012v1
• Date: Thu, 10 Sep 2026 06:20:22 GMT
• Title: Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills
• Abstract summary: Tests increasingly participate in the decisions made by large language models and software engineering agents.<n>They specify intended behavior, guide program construction and repair, select candidates, constrain transformations, and provide execution evidence for software analysis.<n>These uses draw on test-driven development, yet differ substantially in test order, oracle availability, editable artifacts, and the role of execution.
• Score: 14.44743150931186
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tests increasingly participate in the decisions made by large language models and software engineering agents. They specify intended behavior, guide program construction and repair, select candidates, constrain transformations, and provide execution evidence for software analysis. These uses draw on test-driven development, yet differ substantially in test order, oracle availability, editable artifacts, and the role of execution. We present a structured scoping survey organized around the question of what decision a test changes. The review integrates 87 research and supporting records, with method- or protocol-level extraction for 83 records, alongside a separate collection of five practice resources. We distinguish the Red--Green--Refactor cycle from test-conditioned generation, execution-guided refinement, test-mediated analysis, and evaluation-only testing. We then compare code generation, repair, translation, refactoring, clone detection, code search, localization, training-data construction, and formal-specification validation. A dedicated analysis examines how agent workflows and reusable skills encode testing procedures and how their effects are evaluated. Across these tasks, the evidence supports treating test availability, test validity, feedback use, and evaluation independence as separate properties. Test passing alone does not establish behavioral equivalence, effective feedback, or process adherence; aggregate improvements can also conceal different outcomes across models, tasks, and denominators. We synthesize these distinctions into a mechanism taxonomy, a cross-task comparison, and a protocol-sensitive evidence analysis, and identify research directions in oracle validation, causal evaluation, long-horizon maintenance, and reusable test-driven agent capabilities

Related papers

• Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model [0.0]
  Book synthesizes 164 scholarly works, 100 practitioner records, 29 benchmark records, and 17 author-system case records.<n>Written as a structured multivocal review, targeted update audits, software-engineering coverage analysis, and distributed-systems evidence synthesis.<n>Book contributes a versioned catalog of 206 reliability records, including 56 developed in depth, plus 13 research leads.
  arXiv  Detail & Related papers  (2026-08-14T01:34:25Z)
• TTHE: Test-Time Harness Evolution [50.26245555541721]
  Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time.<n>We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs.<n>During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces.<n>A judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs.
  arXiv  Detail & Related papers  (2026-07-09T05:53:39Z)
• TestMap: Evidence Infrastructure for Foundation-Model-Assisted Test Generation [1.1546538067103256]
  This paper presents TestMap, an open-source prototype that automates foundation-model-assisted test generation for C#/.NET repositories.<n>TestMap supports repository analysis, source-test mapping, baseline execution, code metric collection, test smell detection, coverage measurement, mutation testing, model-guided test generation, validation, repair, and repository-specific experiment tracking.
  arXiv  Detail & Related papers  (2026-06-08T22:04:51Z)
• From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs [48.36707944399574]
  We study how vibe-testing works in practice and then formalize it to support systematic analysis.<n>In experiments on coding benchmarks, we find that combining personalized prompts and user-aware evaluation can change which model is preferred.
  arXiv  Detail & Related papers  (2026-04-15T17:57:08Z)
• ProdCodeBench: A Production-Derived Benchmark for Evaluating AI Coding Agents [10.578603956693696]
  This paper presents a methodology for curating production-derived benchmarks, illustrated through ProdCodeBench.<n>Each curated sample consists of a verbatim prompt, a committed code change and fail-to-pass tests spanning seven programming languages.<n>Our systematic analysis of four foundation models yields solve rates ranging from 53.2% to 72.2%.
  arXiv  Detail & Related papers  (2026-04-02T01:52:55Z)
• Pitfalls in Evaluating Interpretability Agents [91.49742416116635]
  We build an agentic system in which a research agent iteratively designs experiments and refines hypotheses.<n>Our work demonstrates fundamental challenges in evaluating complex automated interpretability systems.
  arXiv  Detail & Related papers  (2026-03-20T16:27:17Z)
• Scaling Agentic Verifier for Competitive Coding [66.11758166379092]
  Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt.<n>Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling.<n>We propose Agentic Verifier, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs.
  arXiv  Detail & Related papers  (2026-02-04T06:30:40Z)
• Scaling Test-time Compute for LLM Agents [51.790752085445384]
  Scaling test time compute has shown remarkable success in improving the reasoning abilities of large language models (LLMs)<n>In this work, we conduct the first systematic exploration of applying test-time scaling methods to language agents.
  arXiv  Detail & Related papers  (2025-06-15T17:59:47Z)
• Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy [8.927002750209295]
  Large Language Models (LLMs) and Multi-Agent LLMs (MALLMs) introduce non-determinism unlike traditional or machine learning software.<n>This paper presents a taxonomy for LLM test case design, informed by research literature and our experience.
  arXiv  Detail & Related papers  (2025-03-01T13:15:56Z)
• Test Case Recommendations with Distributed Representation of Code Syntactic Features [2.225268436173329]
  We propose an automated approach which exploits both structural and semantic properties of source code methods and test cases. The proposed approach initially trains a neural network to transform method-level source code, as well as unit tests, into distributed representations. The model computes cosine similarity between the method's embedding and the previously-embedded training instances.
  arXiv  Detail & Related papers  (2023-10-04T21:42:01Z)
• ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning [63.77667876176978]
  Large language models show improved downstream task interpretability when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively studying their correctness is difficult. We present ROS, a suite of interpretable, unsupervised automatic scores that improve and extend previous text generation evaluation metrics.
  arXiv  Detail & Related papers  (2022-12-15T15:52:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.