Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests

Recent advances in large language models (LLMs) have driven growing interest in using LLMs to automate test generation. Prior work commonly evaluates generated test suites using proxy metrics such as code coverage and mutation score. However, studies by Inozemtseva et al. and Papadakis et al. show that, for human-written tests, correlations among coverage, mutation, and real-bug detection can largely vanish once test suite size is controlled, raising concerns about the validity of evaluations based on proxy metrics. It also remains unclear whether these conclusions carry over to LLM-generated tests, given that prevailing LLM-based test-generation workflows differ substantially from traditional approaches. In this paper, we conduct a large-scale replication study of these two prior works using a wide range of test suites generated by a diverse set of LLMs, and re-examine the relationships among coverage, mutation, and real-bug detection effectiveness. Our findings diverge substantially from prior results. We show that the usefulness of coverage and mutation is highly context-dependent: in regression-style settings where the code provided to the LLM can be reasonably assumed bug-free, these metrics can provide meaningful signals when comparing across models; in another common scenario where the code-under-test may already be buggy and the goal is to expose the bug within the code-under-test, they no longer serve as reliable indicators. We also find little evidence that test suite size is a dominant confounder for correlations among coverage, mutation, and real-bug detection for LLM-generated tests. Based on these findings, we discuss how to interpret results from prior studies and provide actionable guidance for evaluating LLM-based test generation.

Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification-defined corner conditions. A popular fix has the model write its own tests and repair until they pass, but the source of the gain is unclear: does it come from the tests merely existing, or from their grounding in a specification of what the code should do? We isolate this factor. Holding the tester, test budget, and repair loop fixed, we change a single prompt line that controls whether the tester receives the spec as a checklist of rules. The baseline is strong: it is already told to probe invalid inputs and edge cases. Grounding the tests in the spec produces correct code +38 percentage points more often than this baseline across three Claude tiers (Haiku 4.5, Sonnet 4.6, Opus 4.8), and +36 points on a held-out set. Grounding, not test quantity, is the primary driver: doubling the test budget barely helps, and combining eight independent ungrounded suites plateaus far below grounding. An ablation isolates the spec's content, not its format: given the spec as a plain paragraph the tester recovers 27 of 30 bugs, but asked to plan tests without the spec it recovers only 2 of 30. The effect survives stronger baselines: a property-based generator catches 28 of 30 bugs but invents out-of-spec requirements, and an AlphaCodium-style loop only matches the baseline. It replicates across vendors (GPT-5.3-codex +28, Gemini 3.5 Flash +19), with a task-level sign test over 18 tasks significant at p=0.002. Grounding improves both sensitivity and precision: it catches more real bugs and wrongly rejects far less correct code, cutting the false-alarm rate from 33% (68% against a Python standard-library oracle) to 0%. On well-specified algorithmic problems it neither helps nor hurts.

Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the correctness of LLM-generated code remains a critical and largely unsolved challenge. Existing approaches either rely on dynamic consensus across multiple code candidates - making them costly and difficult to scale - or on static reasoning that is susceptible to dynamic bugs and order bias. In this paper, we propose TRAILS~ (Targeted Reasoning Agreement via Inputs and Specifications), an approach that grounds LLM reasoning with concrete (input, output) pairs. TRAILS~ first generates diverse test inputs via category partitioning based on the specification, then executes them against the candidate code and prompts LLMs to assess whether the resulting input-output pairs conform to the specification - without ever reasoning over the code itself. Scores are aggregated across inputs, to determines whether the program is likely correct. We evaluate TRAILS~ on two datasets, LiveCodeBench and CoCoClaNeL, across three LLMs (Qwen3Coder-30B, Devstral-Small-24B, and Olmo3.1-Instruct), comparing against HoarePrompt and a Zero-Shot Chain-of-Thought baseline. TRAILS~ improves Matthew Correlation Coefficient by up to 39% relative to Zero-Shot COT and consistently outperforms HoarePrompt. Beyond accuracy, TRAILS~ demonstrates greater stability across seeded runs, reducing sensitivity to LLM non-determinism, and assigns correct labels to a larger set of unique code samples than competing approaches.