Backend
Can Coding Agents Write and Transpile Unit Tests
arXiv cs.SE0 views
arXiv:2611.21797v1 Announce Type: new Abstract: Coding assistants built on Large Language Models (LLMs) have become a staple of modern software development, increasingly trusted to execute workflows and modernize code end-to-end. Much of this trust rests on passing tests, which are often written by the coding agents themselves. In this work, we examine the ability of these agents to both write reliable tests and translate them between programming languages. We benchmark three popular coding agents, each evaluated with a native frontier model and high reasoning effort. Verifying across a broad suite of metrics, we find that coding agents far exceed human written suites on traditional measures of coverage. This advantage, however, is uneven: agent test quality degrades sharply with project size, and much of the advantage lies in a greater number of written tests. We also show that agentic test translation---while seemingly strong in aggregate---remains inconsistent and unreliable.
Source:https://arxiv.org/abs/2611.21797PreviousRevisiting the Survival of Agent-Attributed Code: How Measurement Choices Decide the VerdictNextEmbedGym: Letting Coding Agents Develop and Debug Embedded Firmware Without Physical Hardware
Related posts
A government portal answered our CI runner but not our laptop
0dev.to DevOps
Attacker agents now turn fresh patches into exploits on their own.
0dev.to DevOps
AWS FinOps Field Notes: Finding Unattached Elastic IPs and the Public IPv4 Surcharge
0dev.to DevOps
CI Check Passes Without Reading What It Claims to Check
0dev.to DevOps
Check If a Cron Job Is Running: Grep Matches Your Own Job
0dev.to DevOps
Writing a Server-to-Cloud Migration Runbook: Assessment, Waves, Rollback and Day-2 Checks
0dev.to DevOps