TDFlow: Agentic Workflows for Test Driven Software Engineering

• URL: http://arxiv.org/abs/2510.23761v1
• Date: Mon, 27 Oct 2025 18:44:59 GMT
• Title: TDFlow: Agentic Workflows for Test Driven Software Engineering
• Abstract summary: TDFlow frames repository-scale software engineering as a test-resolution task.<n>We show that TDFlow attains 88.8% pass rate on SWE-Bench Lite.<n>We envision a human-LLM interactive system powered by TDFlow where human developers write tests.
• Score: 9.028820294564566
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes, revises, and debugs repository-scale patches using precisely engineered sub-agents and tightly constrained tools. The workflow decomposes software engineering program repair into four components governed by respective sub-agents. This simple, forced decoupling of patch proposing, debugging, patch revision, and optional test generation (1) reduces long-context burden on any individual sub-agent, (2) focuses each sub-agent on specific, pre-defined sub-tasks, and (3) allows for specialized performance improvement on specific sub-tasks. When provided human-written tests, TDFlow attains 88.8% pass rate on SWE-Bench Lite (an absolute improvement of 27.8% over the next best system) and 94.3% on SWE-Bench Verified. Manual inspection of the 800 TDFlow runs within SWE-Bench Lite and Verified uncover only 7 instances of test hacking, which were subsequently counted as failures. Furthermore, we show that the primary obstacle to human-level software engineering performance lies within writing successful reproduction tests. We envision a human-LLM interactive system powered by TDFlow where human developers write tests solved by LLM systems. Together, these results indicate that modern LLMs, when embedded in a narrowly engineered, test-driven workflow, already achieve human-level test resolution -- with the final frontier for fully autonomous repository repair being the accurate generation of valid reproduction tests.

Related papers

• ExecCritic: Learn to Test, Test to Improve for Coding Agents [68.42713285082912]
  Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue.<n>We introduce ExecCritic, combining a test--verify--revise scaffold with a role-specific reinforcement learning recipe for training agents within it.<n>The scaffold separates test construction from source-code repair: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code from their execution feedback without changing the tests.
  arXiv  Detail & Related papers  (2026-09-08T17:53:37Z)
• SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents [63.65682461568621]
  We introduce SWE-Gate, a repository-level benchmark for software engineering agents that explicitly evaluates review constraint compliance alongside functional correctness.<n>SWE-Gate derives review constraints from real pull request review comments and synthesizes repository-level repair instances around these constraints.<n>Each instance provides separate functional and constraint tests, together with non-compliant and gold patches, enabling explicit separation between issue resolution capability and review constraint compliance.
  arXiv  Detail & Related papers  (2026-09-03T17:53:34Z)
• 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)
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows [67.92316850084575]
  We introduce Claw-Eval-Live, a live benchmark for workflow agents.<n>Each release is constructed from public workflow-demand signals.<n>Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts.
  arXiv  Detail & Related papers  (2026-04-30T17:23:19Z)
• SWE-World: Building Software Engineering Agents in Docker-Free Environments [91.17484806743641]
  SWE-World is a Docker-free framework that replaces physical execution environments with a learned surrogate for training and evaluating software engineering agents.<n>We show that SWE-World raises Qwen2.5-Coder-32B from 6.2% to 52.0% via Docker-free SFT, 55.0% with Docker-free RL, and 68.2% with further TTS.
  arXiv  Detail & Related papers  (2026-02-03T11:44:39Z)
• TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance [1.4341136505032424]
  TAM-Eval is a framework to evaluate model performance across three core test maintenance scenarios.<n>Our benchmark comprises 1,539 automatically extracted and validated scenarios from Python, Java, and Go projects.<n>We release TAM-Eval as an open-source framework to support future research in automated software testing.
  arXiv  Detail & Related papers  (2026-01-26T07:47:22Z)
• Automated structural testing of LLM-based agents: methods, framework, and case studies [0.05254956925594667]
  LLM-based agents are rapidly being adopted across diverse domains.<n>Current testing approaches focus on acceptance-level evaluation from the user's perspective.<n>We present methods to enable structural testing of LLM-based agents.
  arXiv  Detail & Related papers  (2026-01-25T11:52:30Z)
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces [126.23612941699565]
  Terminal-Bench 2.0 is a benchmark composed of 89 tasks in computer terminal environments inspired by problems from real world.<n>We show that frontier models and agents score less than 65% on the benchmark.<n>We publish the dataset and evaluation harness to assist developers and researchers in future work at https://www.tbench.ai/.
  arXiv  Detail & Related papers  (2026-01-17T01:29:30Z)
• SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads? [22.075705411944895]
  SWE-fficiency is a benchmark for evaluating repository-level performance optimization on real workloads.<n>Our suite contains 498 tasks across nine widely used data-science, machine-learning, and HPC repositories.
  arXiv  Detail & Related papers  (2025-11-08T17:55:09Z)
• Automated Network Protocol Testing with LLM Agents [18.102379194660543]
  NeTestLLM takes advantage of multi-agent Large Language Models (LLMs) for end-to-end automated network protocol testing.<n>In experiments, NeTestLLM generated 4,632 test cases for OSPF, RIP, and BGP, covering 41 historical FRRouting bugs compared to 11 by current national standards.
  arXiv  Detail & Related papers  (2025-10-15T07:55:15Z)
• Unit Test Update through LLM-Driven Context Collection and Error-Type-Aware Refinement [5.8748750353007635]
  Test maintenance methods primarily focus on repairing broken tests, neglecting the scenario of enhancing existing tests to verify new functionality.<n>We propose TESTUPDATER, a novel approach that enables automated just-in-time test updates in response to production code changes.<n>TestUPDATER achieves a compilation pass rate of 94.4% and a test pass rate of 86.7%, outperforming the state-of-the-art method SYNTER by 15.9% and 20.0%, respectively.
  arXiv  Detail & Related papers  (2025-09-29T08:08:22Z)
• SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner [53.54568352375669]
  We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD)<n>Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests.<n>We generated 16,061 training instances and 2,020 test instances from real-world GitHub projects, creating the **SWE-Flow-Eval** benchmark.
  arXiv  Detail & Related papers  (2025-06-10T17:23:33Z)
• Acceptance Test Generation with Large Language Models: An Industrial Case Study [0.7874708385247353]
  Large language model (LLM)-powered assistants are increasingly used for generating program code and unit tests.<n>This paper explores the use of LLMs for generating executable acceptance tests for web applications through a two-step process.<n>This two-step approach supports acceptance test-driven development, enhances tester control, and improves test quality.
  arXiv  Detail & Related papers  (2025-04-09T19:33:38Z)
• ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization [51.280919773837645]
  We develop ScoreFlow, a high-performance framework for agent workflow optimization.<n>ScoreFlow incorporates Score-DPO, a novel variant of the direct preference optimization method that accounts for quantitative feedback.<n>It achieves an 8.2% improvement over existing baselines across question answering, coding, and mathematical reasoning.
  arXiv  Detail & Related papers  (2025-02-06T18:47:49Z)
• QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks [14.251006141747913]
  QualityFlow is a dynamic agentic workflow for program synthesis.<n>The Quality Checker can precisely accept any correct program, faulty synthesized tests, and prevent potential workflow deviation.
  arXiv  Detail & Related papers  (2025-01-20T21:47:06Z)
• AutoPT: How Far Are We from the End2End Automated Web Penetration Testing? [54.65079443902714]
  We introduce AutoPT, an automated penetration testing agent based on the principle of PSM driven by LLMs. Our results show that AutoPT outperforms the baseline framework ReAct on the GPT-4o mini model.
  arXiv  Detail & Related papers  (2024-11-02T13:24:30Z)
• SUPERNOVA: Automating Test Selection and Defect Prevention in AAA Video Games Using Risk Based Testing and Machine Learning [62.997667081978825]
  Testing video games is an increasingly difficult task as traditional methods fail to scale with growing software systems. We present SUPERNOVA, a system responsible for test selection and defect prevention while also functioning as an automation hub. The direct impact of this has been observed to be a reduction in 55% or more testing hours for an undisclosed sports game title.
  arXiv  Detail & Related papers  (2022-03-10T00:47:46Z)

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.