# MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision

arXiv: https://arxiv.org/abs/2505.14996 · HTML: https://mlsanity.com/paper/2505.14996/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://mlsanity.com/paper/2310.06117/) (2023)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [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)
- [EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms](https://mlsanity.com/paper/2406.14228/) (2024)
- [Self-Discover: Large Language Models Self-Compose Reasoning Structures](https://mlsanity.com/paper/2402.03620/) (2024)
- [Language Agents as Optimizable Graphs](https://mlsanity.com/paper/2402.16823/) (2024)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion](https://mlsanity.com/paper/2409.14051/) (2024)
- [Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2406.14891/) (2024)
- [Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators](https://mlsanity.com/paper/2504.15253/) (2025)

## Built on by (most cited first, 28 of 28)

- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks](https://mlsanity.com/paper/2601.14652/) (2026)
- [Self-Evolving Multi-Agent Systems via Textual Backpropagation](https://mlsanity.com/paper/2506.09046/) (2025)
- [The Illusion of Multi-Agent Advantage](https://mlsanity.com/paper/2606.13003/) (2026)
- [Toward a Safe Internet of Agents](https://mlsanity.com/paper/2512.00520/) (2025)
- [MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems](https://mlsanity.com/paper/2602.03053/) (2026)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains](https://mlsanity.com/paper/2510.17793/) (2025)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)
- [Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces](https://mlsanity.com/paper/2605.02801/) (2026)
- [Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems](https://mlsanity.com/paper/2606.18837/) (2026)
- [Urban-MAS: Human-Centered Urban Prediction with LLM-Based Multi-Agent System](https://mlsanity.com/paper/2511.00096/) (2025)
- [Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems](https://mlsanity.com/paper/2603.21475/) (2026)
- [EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?](https://mlsanity.com/paper/2609.04280/) (2026)
- [MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning](https://mlsanity.com/paper/2509.24922/) (2025)
- [Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems](https://mlsanity.com/paper/2606.04306/) (2026)
- [Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks](https://mlsanity.com/paper/2509.05651/) (2025)
- [Grammar Search for Multi-Agent Systems](https://mlsanity.com/paper/2512.14079/) (2025)
- [Towards Adaptive, Scalable, and Robust Coordination of LLM Agents: A Dynamic Ad-Hoc Networking Perspective](https://mlsanity.com/paper/2602.08009/) (2026)
- [Reward Modeling for Multi-Agent Orchestration](https://mlsanity.com/paper/2606.13598/) (2026)
- [Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research](https://mlsanity.com/paper/2603.28986/) (2026)
- [Serving Agentic Workflows with a Physical-Plan Compiler and Adaptive Runtime](https://mlsanity.com/paper/2607.02942/) (2026)
- [Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning](https://mlsanity.com/paper/2511.20694/) (2025)
- [EASy: Towards Efficient LLM-Based Agentic System](https://mlsanity.com/paper/2608.04588/) (2026)
- [Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2609.14227/) (2026)
- [Decoupled Multi-Agent Orchestration](https://mlsanity.com/paper/2610.07556/) (2026)
- [MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification](https://mlsanity.com/paper/2610.17613/) (2026)

## Abstract (arXiv)

Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles and communication protocols. These manual designs often fail to align with the underlying LLMs' strengths and struggle to adapt to novel tasks. Recent automatic MAS approaches attempt to mitigate these limitations but typically necessitate a validation set for tuning and yield static MAS designs lacking adaptability during inference, while also removing the flexibility to reduce to simpler systems. We introduce MAS-ZERO, the first self-evolved, inference-time framework for automatic MAS design. MAS-ZERO employs meta-level design to iteratively design, critique, and refine MAS configurations tailored to each problem instance, without requiring a validation set. Critically, it enables dynamic problem decomposition and agent composition through meta-feedback on solvability and completeness, and reduction to simpler systems when appropriate. Experiments across reasoning (math and graduate-level QA), coding, and agentic (search-based) benchmarks, using both closed-source and open-source LLM backbones of varying sizes, demonstrate that MAS-ZERO outperforms strong manual and automatic MAS baselines. It achieves substantial average accuracy improvements of up to 16.69% on reasoning, 16.66% on coding, and 5.45% on agentic tasks, while maintaining cost efficiency.