# Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution

arXiv: https://arxiv.org/abs/2605.06125 · HTML: https://mlsanity.com/paper/2605.06125/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 23 of 23)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM](https://mlsanity.com/paper/2402.00097/) (2024)
- [SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios](https://mlsanity.com/paper/2512.18470/) (2025)
- [TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark](https://mlsanity.com/paper/2410.00752/) (2024)
- [Pynguin: Automated Unit Test Generation for Python](https://mlsanity.com/paper/2202.05218/) (2022)
- [CoverUp: Effective High Coverage Test Generation for Python](https://mlsanity.com/paper/2403.16218/) (2024)
- [HITS: High-coverage LLM-based Unit Test Generation via Method Slicing](https://mlsanity.com/paper/2408.11324/) (2024)
- [TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?](https://mlsanity.com/paper/2412.02883/) (2024)
- [ASTER: Natural and Multi-language Unit Test Generation with LLMs](https://mlsanity.com/paper/2409.03093/) (2024)
- [REACCEPT: Automated Co-evolution of Production and Test Code Based on Dynamic Validation and Large Language Models](https://mlsanity.com/paper/2411.11033/) (2024)
- [Automated Test Case Repair Using Language Models](https://mlsanity.com/paper/2401.06765/) (2024)
- [Fix the Tests: Augmenting LLMs to Repair Test Cases with Static Collector and Neural Reranker](https://mlsanity.com/paper/2407.03625/) (2024)
- [UTFix: Change Aware Unit Test Repairing using LLM](https://mlsanity.com/paper/2503.14924/) (2025)
- [Unit Test Update through LLM-Driven Context Collection and Error-Type-Aware Refinement](https://mlsanity.com/paper/2509.24419/) (2025)

## Built on by (most cited first, 1 of 1)

- [MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs](https://mlsanity.com/paper/2607.26591/) (2026)

## Abstract (arXiv)

As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full project and excluding the need for new tests entirely. We present TEBench, the first project-level benchmark for test evolution. Given a project repository and a code-changing commit, TEBench requires systems to autonomously identify tests requiring modification, determine where new tests are needed, and produce the corresponding test patch. We construct TEBench through a four-stage pipeline over Defects4J projects, curating 314 task instances from 10 projects with developer-written ground truth. Each instance is annotated with one or more of three evolution types: Test-Breaking (tests that fail), Test-Stale (tests that pass but no longer meaningfully validate updated behavior), and Test-Missing (new tests needed for introduced behavior). We evaluate seven configurations spanning three industrial agent frameworks (Claude Code, Codex CLI, OpenCode) and six base models, alongside a heuristic baseline. All seven configurations converge on an identification F1 of 45.7% to 49.4%, revealing a shared performance ceiling across both frameworks and base models. Test-Stale is the most challenging type, averaging F1 around 36%, since configurations rely on execution failure signals and lack proactive semantic reasoning. On the update task, configurations produce highly executable test modifications whose surface form diverges substantially from ground truth. Trajectory analysis reveals a reactive "execute-fail-fix" loop that succeeds for breaking tests but structurally cannot address stale or missing tests. TEBench is available at https://github.com/iSEngLab/TEBench with a leaderboard at https://tebench-leadership.vercel.app.