Hallucination to Consensus: Multi-Agent LLMs for End-to-End Test Generation

• URL: http://arxiv.org/abs/2506.02943v5
• Date: Wed, 27 Aug 2025 22:48:01 GMT
• Title: Hallucination to Consensus: Multi-Agent LLMs for End-to-End Test Generation
• Authors: Qinghua Xu, Guancheng Wang, Lionel Briand, Kui Liu,
• Abstract summary: Unit testing plays a critical role in ensuring software correctness.<n>Traditional methods rely on search-based or randomized algorithms to achieve high code coverage.<n>We propose CANDOR, a novel prompt engineering-based LLM framework for automated unit test generation in Java.
• Score: 2.794277194464204
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unit testing plays a critical role in ensuring software correctness. However, writing unit tests manually is labor-intensive, especially for strongly typed languages like Java, motivating the need for automated approaches. Traditional methods primarily rely on search-based or randomized algorithms to achieve high code coverage and produce regression oracles, which are derived from the program's current behavior rather than its intended functionality. Recent advances in LLMs have enabled oracle generation from natural language descriptions, aligning better with user requirements. However, existing LLM-based methods often require fine-tuning or rely on external tools such as EvoSuite for test prefix generation, making them costly or cumbersome to apply in practice. In this work, we propose CANDOR, a novel prompt engineering-based LLM framework for automated unit test generation in Java. CANDOR orchestrates multiple specialized LLM agents to collaboratively generate complete tests. To mitigate the notorious hallucinations in LLMs and improve oracle correctness, we introduce a novel strategy that engages multiple reasoning LLMs in a panel discussion and generates accurate oracles based on consensus. Additionally, to reduce the verbosity of reasoning LLMs' outputs, we propose a novel dual-LLM pipeline to produce concise and structured oracle evaluations. Our experiments show that CANDOR is comparable with EvoSuite in generating tests with high code coverage and clearly superior in terms of mutation score. Moreover, our prompt engineering-based approach CANDOR significantly outperforms the SOTA fine-tuning-based oracle generator TOGLL by at least 21.1 percentage points in oracle correctness on both correct and faulty source code. Further ablation studies confirm the critical contributions of key agents in generating high-quality tests.

Related papers

• RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis [78.32151470154422]
  We introduce RAVEL, an agentic framework that enables the testers to autonomously plan and execute typical synthesis operations.<n>We present C3EBench, a benchmark comprising 1,258 samples derived from professional human writings.<n>By augmenting RAVEL with SOTA LLMs as operators, we find that such agentic text synthesis is dominated by the LLM's reasoning capability.
  arXiv  Detail & Related papers  (2026-02-28T14:47:34Z)
• Automated Test Suite Enhancement Using Large Language Models with Few-shot Prompting [0.0]
  Unit testing is essential for verifying the functional correctness of code modules.<n>Unit tests generated by tools that employ traditional approaches, such as search-based software testing (SBST), lack readability, naturalness, and practical usability.<n>Software repositories now include a mix of human-written tests, LLM-generated tests, and those from tools employing traditional approaches such as SBST.
  arXiv  Detail & Related papers  (2026-02-12T18:42:49Z)
• Understanding LLM-Driven Test Oracle Generation [4.75370717332176]
  Existing techniques primarily generate regression oracles that predicate on the implemented behavior of the class under test.<n>With the rise of Foundation Models (FMs), particularly Large Language Models (LLMs), there is a new opportunity to generate test oracles that reflect intended behavior.<n>This paper presents an empirical study on the effectiveness of LLMs in generating test oracles that expose software failures.
  arXiv  Detail & Related papers  (2026-01-09T05:51:35Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• YATE: The Role of Test Repair in LLM-Based Unit Test Generation [22.67442101368384]
  We propose a technique for repairing some of these incorrect tests through a combination of rule-based static analysis and re-prompting.<n>We evaluate this simple approach, named YATE, on a set of 6 open-source projects.<n>YATE achieves 22% higher line coverage, 20% higher branch coverage and kill 20% more mutants at a comparable cost.
  arXiv  Detail & Related papers  (2025-07-24T11:32:31Z)
• On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization [54.965787768076254]
  Large Language Models have been recently exploited as judges for complex natural language processing tasks, such as Q&A.<n>We study the effectiveness of LLMs-as-a-judge for two code-related tasks, namely code generation and code summarization.
  arXiv  Detail & Related papers  (2025-07-22T13:40:26Z)
• Real-time Verification and Refinement of Language Model Text Generation [60.04718679054704]
  Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks.<n>A critical challenge remains in that they sometimes generate factually incorrect answers.<n>We propose Streaming-VR, a novel approach designed to enhance the efficiency of verification and refinement of LLM outputs.
  arXiv  Detail & Related papers  (2025-01-14T03:59:48Z)
• Improving the Readability of Automatically Generated Tests using Large Language Models [7.7149881834358345]
  We propose to combine the effectiveness of search-based generators with the readability of LLM generated tests.<n>Our approach focuses on improving test and variable names produced by search-based tools, while keeping their semantics unchanged.
  arXiv  Detail & Related papers  (2024-12-25T09:08:53Z)
• SpecTool: A Benchmark for Characterizing Errors in Tool-Use LLMs [77.79172008184415]
  SpecTool is a new benchmark to identify error patterns in LLM output on tool-use tasks. We show that even the most prominent LLMs exhibit these error patterns in their outputs. Researchers can use the analysis and insights from SPECTOOL to guide their error mitigation strategies.
  arXiv  Detail & Related papers  (2024-11-20T18:56:22Z)
• Do LLMs generate test oracles that capture the actual or the expected program behaviour? [7.772338538073763]
  Large Language Models (LLMs) are trained on an enormous amount of data to generate developer-like code and test cases. This study includes developer-written and automatically generated test cases and oracles for 24 open-source Java repositories. LLMs are better at generating test oracles rather than classifying the correct ones, and can generate better test oracles when the code contains meaningful test or variable names.
  arXiv  Detail & Related papers  (2024-10-28T15:37:06Z)
• Test Oracle Automation in the era of LLMs [52.69509240442899]
  Large Language Models (LLMs) have demonstrated remarkable proficiency in tackling diverse software testing tasks. This paper aims to enable discussions on the potential of using LLMs for test oracle automation, along with the challenges that may emerge during the generation of various types of oracles.
  arXiv  Detail & Related papers  (2024-05-21T13:19:10Z)
• TOGLL: Correct and Strong Test Oracle Generation with LLMs [0.8057006406834466]
  Test oracles play a crucial role in software testing, enabling effective bug detection.<n>Despite initial promise, neural-based methods for automated test oracle generation often result in a large number of false positives.<n>We present the first comprehensive study to investigate the capabilities of LLMs in generating correct, diverse, and strong test oracles.
  arXiv  Detail & Related papers  (2024-05-06T18:37:35Z)
• Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM [32.44432906540792]
  We present SymPrompt, a code-aware prompting strategy for large language models in test generation. SymPrompt enhances correct test generations by a factor of 5 and bolsters relative coverage by 26% for CodeGen2. Notably, when applied to GPT-4, SymPrompt improves coverage by over 2x compared to baseline prompting strategies.
  arXiv  Detail & Related papers  (2024-01-31T18:21:49Z)
• Allies: Prompting Large Language Model with Beam Search [107.38790111856761]
  In this work, we propose a novel method called ALLIES. Given an input query, ALLIES leverages LLMs to iteratively generate new queries related to the original query. By iteratively refining and expanding the scope of the original query, ALLIES captures and utilizes hidden knowledge that may not be directly through retrieval.
  arXiv  Detail & Related papers  (2023-05-24T06:16:44Z)
• ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers [60.6418431624873]
  Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems. We propose ALGO, a framework that synthesizes Algorithmic programs with LLM-Generated Oracles to guide the generation and verify their correctness. Experiments show that when equipped with ALGO, we achieve an 8x better one-submission pass rate over the Codex model and a 2.6x better one-submission pass rate over CodeT.
  arXiv  Detail & Related papers  (2023-05-24T00:10:15Z)
• LEVER: Learning to Verify Language-to-Code Generation with Execution [64.36459105535]
  We propose LEVER, a simple approach to improve language-to-code generation by learning to verify the generated programs with their execution results. Specifically, we train verifiers to determine whether a program sampled from the LLMs is correct or not based on the natural language input, the program itself and its execution results. LEVER consistently improves over the base code LLMs(4.6% to 10.9% with code-davinci) and achieves new state-of-the-art results on all of them.
  arXiv  Detail & Related papers  (2023-02-16T18:23:22Z)

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.