# L2MAC: Large Language Model Automatic Computer for Extensive Code Generation

arXiv: https://arxiv.org/abs/2310.02003 · HTML: https://mlsanity.com/paper/2310.02003/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2023.

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

- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks](https://mlsanity.com/paper/2410.11782/) (2024)
- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (2024)
- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Discovering Preference Optimization Algorithms with and for Large Language Models](https://mlsanity.com/paper/2406.08414/) (2024)
- [Internet of Agents: Fundamentals, Applications, and Challenges](https://mlsanity.com/paper/2505.07176/) (2025)
- [Adaptive Graph Pruning for Multi-Agent Communication](https://mlsanity.com/paper/2506.02951/) (2025)
- [AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction](https://mlsanity.com/paper/2506.17784/) (2025)
- [Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs](https://mlsanity.com/paper/2406.18294/) (2024)
- [Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling](https://mlsanity.com/paper/2412.15305/) (2024)
- [SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs](https://mlsanity.com/paper/2501.09316/) (2025)
- [TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems](https://mlsanity.com/paper/2605.26563/) (2026)
- [SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology](https://mlsanity.com/paper/2604.17503/) (2026)
- [Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions](https://mlsanity.com/paper/2503.24180/) (2025)
- [Planning-Driven Programming: A Large Language Model Programming Workflow](https://mlsanity.com/paper/2411.14503/) (2024)
- [Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition](https://mlsanity.com/paper/2604.08708/) (2026)
- [Re-Aligning Language to Visual Objects with an Agentic Workflow](https://mlsanity.com/paper/2503.23508/) (2025)
- [QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm](https://mlsanity.com/paper/2506.12355/) (2025)
- [Fetch.ai: An Architecture for Modern Multi-Agent Systems](https://mlsanity.com/paper/2510.18699/) (2025)
- [Can Github issues be solved with Tree Of Thoughts?](https://mlsanity.com/paper/2405.13057/) (2024)
- [TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems](https://mlsanity.com/paper/2601.10120/) (2026)
- [NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code](https://mlsanity.com/paper/2603.00805/) (2026)
- [LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review](https://mlsanity.com/paper/2604.16321/) (2026)
- [Towards Green AI: Current status and future research](https://mlsanity.com/paper/2407.10237/) (2024)
- [Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling](https://mlsanity.com/paper/2605.19418/) (2026)
- [Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve](https://mlsanity.com/paper/2505.23946/) (2025)
- [EstRTL: Functional Estimation Guided RTL Code Generation](https://mlsanity.com/paper/2606.09867/) (2026)
- [Dalek: A Constructive Agent Machine](https://mlsanity.com/paper/2609.03546/) (2026)
- [Rethinking Multi-Agent Collaboration: When More Is Less](https://mlsanity.com/paper/2609.19759/) (2026)
- [Absorbed in Inertia: Activation Analysis for Computer-Use Agents](https://mlsanity.com/paper/2609.37176/) (2026)

## Abstract (arXiv)

Transformer-based large language models (LLMs) are constrained by the fixed context window of the underlying transformer architecture, hindering their ability to produce long and coherent outputs. Memory-augmented LLMs are a promising solution, but current approaches cannot handle long output generation tasks since they (1) only focus on reading memory and reduce its evolution to the concatenation of new memories or (2) use very specialized memories that cannot adapt to other domains. This paper presents L2MAC, the first practical LLM-based general-purpose stored-program automatic computer (von Neumann architecture) framework, an LLM-based multi-agent system, for long and consistent output generation. Its memory has two components: the instruction registry, which is populated with a prompt program to solve the user-given task, and a file store, which will contain the final and intermediate outputs. Each instruction in turn is executed by a separate LLM agent, whose context is managed by a control unit capable of precise memory reading and writing to ensure effective interaction with the file store. These components enable L2MAC to generate extensive outputs, bypassing the constraints of the finite context window while producing outputs that fulfill a complex user-specified task. We empirically demonstrate that L2MAC achieves state-of-the-art performance in generating large codebases for system design tasks, significantly outperforming other coding methods in implementing the detailed user-specified task; we show that L2MAC works for general-purpose extensive text-based tasks, such as writing an entire book; and we provide valuable insights into L2MAC's performance improvement over existing methods.