TENET: Leveraging Tests Beyond Validation for Code Generation

ICLR 2026 Conference Submission15289 Authors

Keywords: Code Generation, Test-Driven Development, Large Language Models

TL;DR: TENET is a TDD-driven LLM agent that leverages test selection, context retrieval, and feedback refinement to achieve state-of-the-art repository-level code generation performance.

Abstract: Test-Driven Development (TDD) is a widely adopted software engineering practice that requires developers to create and execute tests alongside code implementation, ensuring that software behavior is continuously validated and refined. In the era of vibe coding, where developers increasingly delegate code writing to large language models (LLMs) by specifying high-level intentions, TDD becomes even more crucial, as test cases serve as executable specifications that explicitly define and verify intended functionality beyond what natural-language descriptions and code context can convey. While vibe coding under TDD is promising, there are three main challenges: (1) selecting a small yet effective test suite to improve the generation accuracy and control the execution workload, (2) retrieving context such as relevant code effectively, and (3) systematically using test feedback for effective code refinement. To address these challenges, we introduce **TENET**, an LLM agent for generating functions in complex real-world repositories under the TDD setting. \ours features three components: (1) a novel **test harness mechanism** that selects a concise test suite to maximize diversity of target usage scenarios; (2) a **tailored agent toolset** that performs efficient retrieval of relevant code with interactive debugging; and (3) a **reflection-based refinement workflow** that iteratively analyzes failures, replenishes context, and applies code refinement. **TENET** achieves 69.08% and 81.77% Pass@1 on RepoCod and RepoEval benchmarks, outperforming the best agentic baselines by 9.49 and 2.17 percentage points, respectively. In addition, this is the first study of test-driven code generation with repository-level context, examining how different aspects of test suites affect the performance of LLM agents under the TDD setting.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 15289