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

The paper introduces TestEvo-Bench, a new benchmark for evaluating test automation agents that can generate or update tests in response to code changes. The benchmark includes 746 test generation and 509 test update tasks from 152 open-source Java projects, each anchored to real commit histories and environment configurations for execution-grounded metrics. Four state-of-the-art agents were tested, achieving up to 77.5% success rate on test generation and 74.6% on test update, but with lower success rates on the most recent tasks and under limited per-task cost.

What the Document Says

  • The paper presents TestEvo-Bench, a benchmark for evaluating test automation agents
  • It includes 746 test generation tasks and 509 test update tasks from 152 open-source Java projects
  • Each task is anchored to real commit histories and environment configurations
  • The success rate of four state-of-the-art agents on test generation and test update was tested, achieving up to 77.5% and 74.6% respectively
  • Success rates are lower on the most recent benchmark tasks and under limited per-task cost

Key Concepts Mentioned

  • TestEvo-Bench
  • test automation agents
  • code changes
  • test generation
  • test update

Claims Made by the Document

  • TestEvo-Bench is a new benchmark for evaluating test automation agents
  • It includes 746 test generation tasks and 509 test update tasks from 152 open-source Java projects
  • The success rate of four state-of-the-art agents on test generation and test update was tested
  • The success rates are lower on the most recent benchmark tasks and under limited per-task cost

Evidence Used

  • TestEvo-Bench is introduced in the paper as a solution to the problem of existing test generation and update benchmarks relying on static metadata
  • The number and sources of the tasks are stated in the text
  • The success rates of the tested agents are reported in the results section

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.