---
title: "LibraryDesignBench Catches AI Coding Agents Rebuilding Code That Already Exists"
subtitle: "LibraryDesignBench tests whether AI coding agents can build libraries that other agents actually find usable, exposing why reuse keeps breaking down."
url: "https://alphasignal.ai/news/librarydesignbench-catches-ai-coding-agents-rebuilding-code-that-already-exists"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-09-29T05:04:44.000Z"
updated: "2026-10-01T00:06:06.248Z"
type: "Paper"
topics:
  - "Agents"
  - "Benchmarks"
subtopics:
  - "Code Agents"
  - "Tool Use"
  - "Multi Agent"
upvotes: 112
source_url: "https://arxiv.org/abs/2609.36730"
comments: 0
truncated: true
---

# LibraryDesignBench Catches AI Coding Agents Rebuilding Code That Already Exists

> LibraryDesignBench tests whether AI coding agents can build libraries that other agents actually find usable, exposing why reuse keeps breaking down.

# LibraryDesignBench measures whether coding agents create reusable APIs

Researchers from Wisconsin, MIT, Snorkel AI, and Stanford have introduced [LibraryDesignBench](https://arxiv.org/abs/2609.36730), a benchmark for libraries written by coding agents. The project measures a recurring failure mode: downstream agents often rebuild functionality that an upstream agent already implemented.

Most coding benchmarks score code for an immediate task. SWE-bench uses repository issues; HumanEval uses function-level prompts. LibraryDesignBench adds a downstream test: can another agent use the resulting library to solve later problems correctly and with less code?

Reimplementation expands codebases, duplicates logic, and creates more opportunities for defects. For agent-facing SDKs and tools, API flexibility, defaults, naming, and examples directly affect how much code downstream agents write.

## The second agent becomes the judge

LibraryDesignBench separates library creation from library use, allowing researchers to evaluate the design through fresh implementors rather than the original author.

| Phase      | Agent             | What happens                                                                             |
| ---------- | ----------------- | ---------------------------------------------------------------------------------------- |
| Design     | Author agent      | Reads design/instruction.md and creates a complete library in /workspace.                |
| Evaluation | Implementor agent | Receives a programming problem and one library condition, then writes a tested solution. |

The design specification defines required capabilities while leaving interfaces, abstractions, names, and workflows open. Those constraints force the author agent to make genuine API decisions rather than follow a supplied template.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Can Agents Design Libraries for Agents? (arXiv)](https://arxiv.org/abs/2609.36730)
- [LibraryDesignBench GitHub Repository](https://github.com/SprocketLab/librarydesignbench)
- [Can Agents Design Libraries for Agents? (HTML)](https://arxiv.org/html/2609.36730)
- [SlopCodeBench: Measuring Code Erosion as Agents Iterate](https://snorkel.ai/blog/slopcodebench-measuring-code-erosion-as-agents-iterate/)