Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution

Source

arXiv

arxiv.org/abs/2607.02469v1

Read the source

Source

Plain-Language Brief

Researchers have developed TestEvo-Bench, a benchmark for testing software that evolves alongside code changes. The benchmark includes tasks mined from 152 open-source Java projects, with two tracks: test generation and test update. Each task comes with environment configuration to support execution-grounded metrics such as pass rate, coverage, and mutation score. The benchmark is also a live one, with new tasks being periodically added. Four state-of-the-art agents were tested on this benchmark, achieving up to 77.5% success rate in test generation and 74.6% in test update, but their performance drops significantly under limited per-task cost.

What the Document Says

  • TestEvo-Bench is a benchmark for testing software that evolves alongside code changes.
  • It includes 746 test generation and 509 test update tasks, curated from 152 open-source Java projects.
  • Each task comes with environment configuration to support execution-grounded metrics such as pass rate, coverage, and mutation score.
  • The benchmark is a live one, with new tasks being periodically added.
  • Four state-of-the-art agents were tested on this benchmark: Claude Code, Gemini CLI, SWE-Agent, Claude Opus 4.7, and Gemini 3.1 Pro.
  • The agents achieved up to 77.5% success rate in test generation and 74.6% in test update.
  • However, their success rate is lower on the most recent benchmark tasks and drops significantly under limited per-task cost.

Key Concepts Mentioned

  • TestEvo-Bench
  • test and code co-evolution
  • execution-grounded metrics
  • state-of-the-art agents

Claims Made by the Document

  • TestEvo-Bench is a benchmark for testing software that evolves alongside code changes.
  • Four state-of-the-art agents were tested on TestEvo-Bench.

Evidence Used

  • The text states that TestEvo-Bench is designed to evaluate the understanding of a code change's propagation into the test suite.
  • The text mentions four specific agents tested on TestEvo-Bench.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing test generation and update benchmarks often isolate the test from the code change, and rely on static metadata that does not verify whether a test is executable or semantically tied to the code change. This makes it difficult to evaluate whether a test automation agent understands how a code change should propagate into the test suite. We introduce TestEvo-Bench, a benchmark of test and code co-evolution tasks mined from software repositories, with two tracks: in test generation, the agent shall write new tests to capture the new software behavior; in test update, the agent shall adapt failing existing tests to the changed software behavior. Each task is anchored to a real commit history and packaged with environment configuration to support execution-grounded metrics such as pass rate, coverage, and mutation score. TestEvo-Bench is also a live benchmark: each task records the timestamp of the test and code changes, and new tasks are periodically mined by our automated pipeline, so evaluation can be restricted to tasks postdating a model's training cutoff to reduce data leakage risk. The current snapshot contains 746 test generation and 509 test update tasks, curated from 59,950 candidate co-evolution records across 152 open-source Java projects. We experiment with four state-of-the-art agents that combine strong harnesses (Claude Code, Gemini CLI, and SWE-Agent) with strong foundation models (Claude Opus 4.7 and Gemini 3.1 Pro). Results show that they achieve up to 77.5% success rate on test generation and 74.6% on test update. However, success rate is materially lower on the most recent benchmark tasks and drops significantly under limited per-task cost.