# Can Agents Design Libraries for Agents?

arXiv: https://arxiv.org/abs/2609.36730 · HTML: https://mlsanity.com/paper/2609.36730/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 46 of its 65 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 30 of 46)

- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations](https://mlsanity.com/paper/2411.00640/) (2024)
- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets](https://mlsanity.com/paper/2309.17428/) (2023)
- [CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models](https://mlsanity.com/paper/2305.14318/) (2023)
- [TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks](https://mlsanity.com/paper/2401.12869/) (2024)
- [NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents](https://mlsanity.com/paper/2512.12730/) (2025)
- [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://mlsanity.com/paper/2605.03546/) (2026)
- [When Language Model Meets Private Library](https://mlsanity.com/paper/2210.17236/) (2022)
- [Commit0: Library Generation from Scratch](https://mlsanity.com/paper/2412.01769/) (2024)
- [DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks](https://mlsanity.com/paper/2607.07946/) (2026)
- [ReGAL: Refactoring Programs to Discover Generalizable Abstractions](https://mlsanity.com/paper/2401.16467/) (2024)
- [LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion](https://mlsanity.com/paper/2406.09834/) (2024)
- [RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code](https://mlsanity.com/paper/2503.07832/) (2025)
- [SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks](https://mlsanity.com/paper/2603.24755/) (2026)
- [ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation](https://mlsanity.com/paper/2503.07010/) (2025)
- [Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects](https://mlsanity.com/paper/2511.04427/) (2025)
- [On Mitigating Code LLM Hallucinations with API Documentation](https://mlsanity.com/paper/2407.09726/) (2024)
- [A Study of LLMs' Preferences for Libraries and Programming Languages](https://mlsanity.com/paper/2503.17181/) (2025)
- [Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments](https://mlsanity.com/paper/2606.05661/) (2026)
- [RepoZero: Can LLMs Generate a Code Repository from Scratch?](https://mlsanity.com/paper/2605.07122/) (2026)
- [When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?](https://mlsanity.com/paper/2503.15231/) (2025)
- [CodeTaste: Can LLMs Generate Human-Level Code Refactorings?](https://mlsanity.com/paper/2603.04177/) (2026)
- [DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch](https://mlsanity.com/paper/2606.10728/) (2026)

## Abstract (arXiv)

Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To measure how well agents design libraries for other agents, we introduce LibraryDesignBench, a two-phase benchmark in which an agent implements a full-featured library from a specification that defines required capabilities and potential use cases without prescribing the design. We evaluate the library through the correctness and simplicity of programs written by three user agents from different model families. The benchmark spans 242 expert-validated programming problems across 15 library-design tasks in four languages. On eleven of the fifteen tasks, agent designers reproduce the abstractions of the human-written production library. Downstream agents adopt agent- and human-written libraries alike but underuse them, reimplementing capabilities the library already provides. Our failure analysis finds that downstream agents write extra code mainly because agent-written libraries are rigid or hard to use, not because capabilities are missing. We also experiment with giving designers more prescriptive, agent-first guidance and having them test their library with subagents; this improves downstream scores and yields simpler programs. LibraryDesignBench provides both a testbed for evaluating library-design practices for agent users and an initial design baseline that improves downstream reuse.