# NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

arXiv: https://arxiv.org/abs/2512.12730 · HTML: https://mlsanity.com/paper/2512.12730/

## Key facts

- Cited by 65 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 25 of its 31 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (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)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving](https://mlsanity.com/paper/2504.02605/) (2025)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models](https://mlsanity.com/paper/2411.04905/) (2024)
- [SWE-Lancer: Can Frontier LLMs Earn 1 Million from Real-World Freelance Software Engineering?](https://mlsanity.com/paper/2502.12115/) (2025)
- [Commit0: Library Generation from Scratch](https://mlsanity.com/paper/2412.01769/) (2024)
- [Seed-Coder: Let the Code Model Curate Data for Itself](https://mlsanity.com/paper/2506.03524/) (2025)
- [ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation](https://mlsanity.com/paper/2507.04952/) (2025)
- [DDK: Distilling Domain Knowledge for Efficient Large Language Models](https://mlsanity.com/paper/2407.16154/) (2024)
- [AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators](https://mlsanity.com/paper/2508.09101/) (2025)
- [M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation](https://mlsanity.com/paper/2410.21157/) (2024)
- [CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models](https://mlsanity.com/paper/2502.16614/) (2025)
- [ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding](https://mlsanity.com/paper/2510.11498/) (2025)
- [SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models](https://mlsanity.com/paper/2511.05459/) (2025)

## Built on by (most cited first, 30 of 65)

- [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://mlsanity.com/paper/2605.03546/) (2026)
- [SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks](https://mlsanity.com/paper/2603.24755/) (2026)
- [SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents](https://mlsanity.com/paper/2605.21384/) (2026)
- [Immersion in the GitHub Universe: Scaling Coding Agents to Mastery](https://mlsanity.com/paper/2602.09892/) (2026)
- [BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?](https://mlsanity.com/paper/2603.03194/) (2026)
- [LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks](https://mlsanity.com/paper/2608.01964/) (2026)
- [ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development](https://mlsanity.com/paper/2602.01655/) (2026)
- [Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents](https://mlsanity.com/paper/2606.16038/) (2026)
- [EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions](https://mlsanity.com/paper/2605.24110/) (2026)
- [SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution](https://mlsanity.com/paper/2603.13428/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [The Verification Horizon: No Silver Bullet for Coding Agent Rewards](https://mlsanity.com/paper/2606.26300/) (2026)
- [SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades](https://mlsanity.com/paper/2605.14415/) (2026)
- [ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders](https://mlsanity.com/paper/2607.21217/) (2026)
- [Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI](https://mlsanity.com/paper/2607.22368/) (2026)
- [Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios](https://mlsanity.com/paper/2604.06742/) (2026)
- [SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle](https://mlsanity.com/paper/2605.13139/) (2026)
- [Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields](https://mlsanity.com/paper/2606.11042/) (2026)
- [SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks](https://mlsanity.com/paper/2603.00575/) (2026)
- [RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades](https://mlsanity.com/paper/2605.15846/) (2026)
- [SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering](https://mlsanity.com/paper/2605.17526/) (2026)
- [CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation](https://mlsanity.com/paper/2606.22082/) (2026)
- [ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance](https://mlsanity.com/paper/2607.02606/) (2026)
- [Constraint Decay: The Fragility of LLM Agents in Backend Code Generation](https://mlsanity.com/paper/2605.06445/) (2026)
- [RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions](https://mlsanity.com/paper/2606.03889/) (2026)
- [ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis](https://mlsanity.com/paper/2607.00041/) (2026)
- [LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation](https://mlsanity.com/paper/2608.00267/) (2026)
- [Repo0: Design-Driven Zero-to-All Code Generation](https://mlsanity.com/paper/2608.19854/) (2026)
- ["What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents](https://mlsanity.com/paper/2603.28551/) (2026)
- [MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis](https://mlsanity.com/paper/2607.27146/) (2026)

## Abstract (arXiv)

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior evaluations focus on localized code generation, scaffolded completion, or short-term repair tasks, leaving open the question of whether agents can sustain coherent reasoning, planning, and execution over the extended horizons demanded by real-world repository construction. To address this gap, we present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents. Given only a single natural-language requirements document and an empty workspace, agents must autonomously design the architecture, manage dependencies, implement multi-module logic, and produce a fully installable Python library. Our experiments across state-of-the-art open- and closed-source models reveal that long-horizon repository generation remains largely unsolved: even the strongest agents achieve below 40% average test pass rates and rarely complete an entire repository correctly. Detailed analysis uncovers fundamental long-horizon failure modes, including premature termination, loss of global coherence, fragile cross-file dependencies, and inadequate planning over hundreds of interaction steps. NL2Repo Bench establishes a rigorous, verifiable testbed for measuring sustained agentic competence and highlights long-horizon reasoning as a central bottleneck for the next generation of autonomous coding agents.