# Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline

arXiv: https://arxiv.org/abs/2601.12307 · HTML: https://mlsanity.com/paper/2601.12307/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 18 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)
- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [Latent Collaboration in Multi-Agent Systems](https://mlsanity.com/paper/2511.20639/) (2025)
- [FlowReasoner: Reinforcing Query-Level Meta-Agents](https://mlsanity.com/paper/2504.15257/) (2025)
- [ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization](https://mlsanity.com/paper/2502.04306/) (2025)
- [EvoFlow: Evolving Diverse Agentic Workflows On The Fly](https://mlsanity.com/paper/2502.07373/) (2025)
- [X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs](https://mlsanity.com/paper/2505.16997/) (2025)
- [When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail](https://mlsanity.com/paper/2601.04748/) (2026)
- [Thought Communication in Multiagent Collaboration](https://mlsanity.com/paper/2510.20733/) (2025)
- [OAgents: An Empirical Study of Building Effective Agents](https://mlsanity.com/paper/2506.15741/) (2025)
- [Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors](https://mlsanity.com/paper/2504.04785/) (2025)
- [Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models](https://mlsanity.com/paper/2506.07334/) (2025)

## Built on by (most cited first, 22 of 22)

- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)
- [On the Reliability Limits of LLM-Based Multi-Agent Planning](https://mlsanity.com/paper/2603.26993/) (2026)
- [From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?](https://mlsanity.com/paper/2604.01608/) (2026)
- [The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams](https://mlsanity.com/paper/2608.23541/) (2026)
- [Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems](https://mlsanity.com/paper/2604.03295/) (2026)
- [Towards Optimal Agentic Architectures for Offensive Security Tasks](https://mlsanity.com/paper/2604.18718/) (2026)
- [FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse](https://mlsanity.com/paper/2606.11290/) (2026)
- [Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2605.03310/) (2026)
- [Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows](https://mlsanity.com/paper/2606.05670/) (2026)
- [How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysis](https://mlsanity.com/paper/2606.13733/) (2026)
- [Automating the Design of Embodied Agent Architectures](https://mlsanity.com/paper/2606.30111/) (2026)
- [OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents](https://mlsanity.com/paper/2603.03005/) (2026)
- [Towards Multi-Agent Autonomous Reasoning in Hydrodynamics](https://mlsanity.com/paper/2605.01102/) (2026)
- [Width, Memory, and Delay: A Resource Accounting for the Limits of Flat Multi-Agent Systems](https://mlsanity.com/paper/2608.00028/) (2026)
- [Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep](https://mlsanity.com/paper/2608.23395/) (2026)
- [What Do CAE Simulation Agents Really Need Beyond a Generic Harness?](https://mlsanity.com/paper/2609.03718/) (2026)
- [Learning What to Skip: Counterfactual Credit Assignment for Efficient Multi-Agent LLM Workflows](https://mlsanity.com/paper/2609.30734/) (2026)
- [How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?](https://mlsanity.com/paper/2609.40303/) (2026)
- [Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams](https://mlsanity.com/paper/2610.00583/) (2026)
- [Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help](https://mlsanity.com/paper/2610.06069/) (2026)
- [Joint Workflow and Prompt Optimization for User Behavior Simulation](https://mlsanity.com/paper/2610.07663/) (2026)
- [SquidAgent: Parallelize Wisely, Coordinate Efficiently](https://mlsanity.com/paper/2610.08647/) (2026)

## Abstract (arXiv)

Recent advances in LLM-based multi-agent systems (MAS) show that workflows composed of multiple LLM agents with distinct roles, tools, and communication patterns can outperform single-LLM baselines on complex tasks. However, most frameworks are homogeneous, where all agents share the same base LLM and differ only in prompts, tools, and positions in the workflow. This raises the question of whether such workflows can be simulated by a single agent through multi-turn conversations. We investigate this across seven benchmarks spanning coding, mathematics, general question answering, domain-specific reasoning, and real-world planning and tool use. Our results show that a single agent can reach the performance of homogeneous workflows with an efficiency advantage from KV cache reuse, and can even match the performance of an automatically optimized heterogeneous workflow. Building on this finding, we propose OneFlow, an algorithm that automatically tailors workflows for single-agent execution, reducing inference costs compared to existing automatic multi-agent design frameworks without trading off accuracy. These results position the single-LLM implementation of multi-agent workflows as a strong baseline for MAS research. We also note that single-LLM methods cannot capture heterogeneous workflows due to the lack of KV cache sharing across different LLMs, highlighting future opportunities in developing textittruly heterogeneous multi-agent systems.