# ProgramBench: Can Language Models Rebuild Programs From Scratch?

arXiv: https://arxiv.org/abs/2605.03546 · HTML: https://mlsanity.com/paper/2605.03546/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 27 of 27)

- [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)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents](https://mlsanity.com/paper/2505.20411/) (2025)
- [SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents](https://mlsanity.com/paper/2504.08703/) (2025)
- [Evaluating Language Models for Efficient Code Generation](https://mlsanity.com/paper/2408.06450/) (2024)
- [DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2405.19856/) (2024)
- [NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents](https://mlsanity.com/paper/2512.12730/) (2025)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios](https://mlsanity.com/paper/2512.18470/) (2025)
- [SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories](https://mlsanity.com/paper/2409.07440/) (2024)
- [SWE-chat: Coding Agent Interactions From Real Users in the Wild](https://mlsanity.com/paper/2604.20779/) (2026)
- [LLM4Decompile: Decompiling Binary Code with Large Language Models](https://mlsanity.com/paper/2403.05286/) (2024)
- [Repo2Run: Automated Building Executable Environment for Code Repository at Scale](https://mlsanity.com/paper/2502.13681/) (2025)
- [EnvBench: A Benchmark for Automated Environment Setup](https://mlsanity.com/paper/2503.14443/) (2025)
- [SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?](https://mlsanity.com/paper/2507.12415/) (2025)
- [Mercury: A Code Efficiency Benchmark for Code Large Language Models](https://mlsanity.com/paper/2402.07844/) (2024)
- [ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?](https://mlsanity.com/paper/2407.14044/) (2024)
- [ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation](https://mlsanity.com/paper/2503.07010/) (2025)
- [GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents](https://mlsanity.com/paper/2505.23671/) (2025)
- [SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs](https://mlsanity.com/paper/2504.14757/) (2025)
- [CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis](https://mlsanity.com/paper/2503.23145/) (2025)
- [Effective Strategies for Asynchronous Software Engineering Agents](https://mlsanity.com/paper/2603.21489/) (2026)

## Built on by (most cited first, 30 of 59)

- [OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks](https://mlsanity.com/paper/2606.29537/) (2026)
- [LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks](https://mlsanity.com/paper/2608.01964/) (2026)
- [Decentralized Multi-Agent Systems with Shared Context](https://mlsanity.com/paper/2606.10662/) (2026)
- [SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?](https://mlsanity.com/paper/2605.26548/) (2026)
- [CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies](https://mlsanity.com/paper/2606.16613/) (2026)
- [The Verification Horizon: No Silver Bullet for Coding Agent Rewards](https://mlsanity.com/paper/2606.26300/) (2026)
- [AgentRewind: Recoverable Execution for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.14380/) (2026)
- [MirrorCode: AI can rebuild entire programs from behavior alone](https://mlsanity.com/paper/2606.30182/) (2026)
- [ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders](https://mlsanity.com/paper/2607.21217/) (2026)
- [ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance](https://mlsanity.com/paper/2607.02606/) (2026)
- [Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement](https://mlsanity.com/paper/2609.01481/) (2026)
- [SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research](https://mlsanity.com/paper/2606.09730/) (2026)
- [Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering](https://mlsanity.com/paper/2606.17799/) (2026)
- [PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization](https://mlsanity.com/paper/2607.19653/) (2026)
- [Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution](https://mlsanity.com/paper/2608.08311/) (2026)
- [Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering](https://mlsanity.com/paper/2607.01087/) (2026)
- [MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis](https://mlsanity.com/paper/2607.27146/) (2026)
- [Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking](https://mlsanity.com/paper/2608.14808/) (2026)
- [The Problem Is the Problem: Towards Scalable Mathematical Discovery](https://mlsanity.com/paper/2608.16977/) (2026)
- [ττ-Bench: An Environment for End-To-End, Realistic Agent Construction](https://mlsanity.com/paper/2609.04611/) (2026)
- [CodeMidas: Scaling Agentic Coding RL Environments from Code Itself](https://mlsanity.com/paper/2609.22068/) (2026)
- [Emergent Collusion in Long-Horizon LLM Agent Interaction](https://mlsanity.com/paper/2609.24967/) (2026)
- [An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models](https://mlsanity.com/paper/2606.01462/) (2026)
- [Do programming languages still matter to your AI coding agent teammate? Evidence at scale from chess engines](https://mlsanity.com/paper/2606.13763/) (2026)
- [Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning](https://mlsanity.com/paper/2606.16576/) (2026)
- [ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?](https://mlsanity.com/paper/2606.19787/) (2026)
- [SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements](https://mlsanity.com/paper/2607.27409/) (2026)
- [The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark](https://mlsanity.com/paper/2608.11469/) (2026)
- [Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation](https://mlsanity.com/paper/2609.04298/) (2026)
- [RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents](https://mlsanity.com/paper/2609.22000/) (2026)

## Abstract (arXiv)

Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain, and grow codebases over extended periods with minimal human oversight. Such settings require models to make high-level software architecture decisions. However, existing benchmarks measure focused, limited tasks such as fixing a single bug or developing a single, specified feature. We therefore introduce ProgramBench to measure the ability of software engineering agents to develop software holisitically. In ProgramBench, given only a program and its documentation, agents must architect and implement a codebase that matches the reference executable's behavior. End-to-end behavioral tests are generated via agent-driven fuzzing, enabling evaluation without prescribing implementation structure. Our 200 tasks range from compact CLI tools to widely used software such as FFmpeg, SQLite, and the PHP interpreter. We evaluate 9 LMs and find that none fully resolve any task, with the best model passing 95% of tests on only 3% of tasks. Models favor monolithic, single-file implementations that diverge sharply from human-written code.