mlsanityData to 7 Oct 2026

Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments

arXiv 2607.28591 ↗First posted 30 Jul 2026cs.SE cs.CL cs.LGcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification. To expand this supply, we present Change2Task, a system grounded in repository history that converts merged pull requests into verified tasks on healthy modern revisions of the same repository. It aligns historical evidence with evolved code, reconstructs task states through Patch Reversal, Code Mapping, or Agent Reconstruction, and validates the lifecycle from a healthy base to a task state and a restored state. By deriving multiple tasks grounded in developer evidence from maintained environments, Change2Task provides executable data for coding agent training and evaluation while reducing repeated environment setup, storage, and task construction effort. We evaluate the system through five common and widely adopted coding agent task families: Bug Fix, Feature Addition, Test Generation, Application Programming Interface Migration, and Security Repair. Starting from 1,130 source changes eligible for construction, Change2Task achieves 79.6% verified task construction success across these task families. On a matched candidate set, it recovers 29.2% more verified tasks than a construction baseline based on pull requests. Historical and reconstructed cases achieve up to 98.0% matched outcome agreement under agent evaluation, while reuse of modern bases reduces measured expenditure across the complete pipeline by 10.8%.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 18 of its 50 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

18 of 50 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026FeatureBench: Benchmarking Agentic Coding for Complex Feature Development11 Feb
  2. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios20 Dec
  3. 2025Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents27 Sep
  4. 2025SWE-smith: Scaling Data for Software Engineering Agents30 Apr
  5. 2024Training Software Engineering Agents and Verifiers with SWE-Gym30 Dec
  6. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul
  7. 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents18 Jun

Other references · 11

  1. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  2. 2025SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?cited by 254
  3. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 196
  4. 2025FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementationcited by 57
  5. 2023How Effective Are Neural Networks for Fixing Security Vulnerabilitiescited by 50
  6. 2025Repo2Run: Automated Building Executable Environment for Code Repository at Scalecited by 39
  7. 2025EnvBench: A Benchmark for Automated Environment Setupcited by 36
  8. 2025SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositoriescited by 27
  9. 2026SWE-Universe: Scale Real-World Verifiable Environments to Millionscited by 16
  10. 2026MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineeringcited by 3
  11. 2026TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolutioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution
  2. 2026VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks
  3. 2025GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
  4. 2026E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch
  5. 2026SWE-Explore: Benchmarking How Coding Agents Explore Repositories
  6. 2026Zero2Repo: Can Coding Agents Build Repositories from Scratch?
  7. 2026Do Coding Agents Reuse Existing Code or Reinvent the Wheel?
  8. 2026Self-Evolving Coding Agents