TheBotCompany: Self-Organizing Multi-agent Systems for Continuous Software Development
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
Large language model (LLM)-based multi-agent systems have shown promise in automating software development tasks. However, most vibe-coding systems focus on completing small tasks and incremental code changes, leaving persistent, continuous software development largely unexplored. We present TheBotCompany, an open-source orchestration framework for continuous multi-agent software development. TheBotCompany introduces three key innovations: (1) a three-phase state machine (Strategy to Execution to Verification) for milestone-driven development, (2) self-organizing agent teams where manager agents dynamically hire, assign, and retire worker agents based on project needs, and (3) asynchronous human oversight. We evaluate TheBotCompany on real-world software projects over multiple days of continuous development, measuring team adaptation patterns, milestone completion rates, cost efficiency, and code quality. Our results demonstrate that the self-organizing approach enables effective long-term software development with measurable progress, while the verification phase catches defects that would otherwise persist.
Key facts. Cited by 1 paper 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 16 of its 55 references that are in the map. First posted on arXiv 26 Mar 2026.
Builds on
16 of 55 references.
Closest ancestors · 4
Same direction, newest first
- 2026ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development2 Feb
- 2025ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework3 Oct
- 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization2 Apr
- 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repair25 Mar
Other references · 12
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
- 2021Program Synthesis with Large Language Modelscited by 3,637
- 2023Code Llama: Open Foundation Models for Codecited by 2,139
- 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 367
- 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
- 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
- 2023Large Language Models for Software Engineering: Survey and Open Problemscited by 181
- 2023CodePlan: Repository-level Coding using LLMs and Planningcited by 140
- 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planningcited by 60
- 2023Experiential Co-Learning of Software-Developing Agentscited by 57
- 2024AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodologycited by 46
- 2018Task Interruption in Software Development Projects: What Makes some Interruptions More Disruptive than Others?cited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
- 2025AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation
- 2024Agentless: Demystifying LLM-based Software Engineering Agents
- 2026OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
- 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
- 2025Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
- 2025LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
- 2026AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering