# Single-agent or Multi-agent Systems? Why Not Both? arXiv: https://arxiv.org/abs/2505.18286 ยท HTML: https://mlsanity.com/paper/2505.18286/ ## Key facts - Cited by 29 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 14 of its 46 references that are in the map. - First posted on arXiv 23 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, 14 of 14) - [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021) - [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021) - [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021) - [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023) - [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023) - [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024) - [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023) - [HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification](https://mlsanity.com/paper/2011.03088/) (2020) - [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025) - [PaperQA: Retrieval-Augmented Generative Agent for Scientific Research](https://mlsanity.com/paper/2312.07559/) (2023) - [TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation](https://mlsanity.com/paper/2402.10178/) (2024) - [AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology](https://mlsanity.com/paper/2406.11912/) (2024) - [FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models](https://mlsanity.com/paper/2405.14767/) (2024) - [Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning](https://mlsanity.com/paper/2502.08056/) (2025) ## Built on by (most cited first, 29 of 29) - [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025) - [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026) - [MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks](https://mlsanity.com/paper/2601.14652/) (2026) - [Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets](https://mlsanity.com/paper/2604.02460/) (2026) - [Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference](https://mlsanity.com/paper/2509.08682/) (2025) - [CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems](https://mlsanity.com/paper/2509.24088/) (2025) - [Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding](https://mlsanity.com/paper/2603.17307/) (2026) - [The Illusion of Multi-Agent Advantage](https://mlsanity.com/paper/2606.13003/) (2026) - [BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Web](https://mlsanity.com/paper/2508.13787/) (2025) - [On the Importance of Task Complexity in Evaluating LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2510.04311/) (2025) - [A Survey on AgentOps: Categorization, Challenges, and Future Directions](https://mlsanity.com/paper/2508.02121/) (2025) - [SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning](https://mlsanity.com/paper/2511.05528/) (2025) - [Towards Optimal Agentic Architectures for Offensive Security Tasks](https://mlsanity.com/paper/2604.18718/) (2026) - [When Does Multi-Agent Collaboration Help? An Entropy Perspective](https://mlsanity.com/paper/2602.04234/) (2026) - [AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks](https://mlsanity.com/paper/2605.10286/) (2026) - [StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems](https://mlsanity.com/paper/2606.03467/) (2026) - [Rethinking the Illusion of Thinking](https://mlsanity.com/paper/2507.01231/) (2025) - [Agentifying Agentic AI](https://mlsanity.com/paper/2511.17332/) (2025) - [Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems](https://mlsanity.com/paper/2606.01351/) (2026) - [Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems](https://mlsanity.com/paper/2609.05933/) (2026) - [Structured Debate Improves Corporate Credit Reasoning in Financial AI](https://mlsanity.com/paper/2510.17108/) (2025) - [Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning](https://mlsanity.com/paper/2601.23027/) (2026) - [Advanced Assistance for Traffic Crash Analysis: An AI-Driven Multi-Agent Approach to Pre-Crash Reconstruction](https://mlsanity.com/paper/2511.10853/) (2025) - [InterventionLens: A Multi-Agent Framework for Detecting ASD Intervention Strategies in Parent-Child Shared Reading](https://mlsanity.com/paper/2603.13710/) (2026) - [Towards Multi-Agent Autonomous Reasoning in Hydrodynamics](https://mlsanity.com/paper/2605.01102/) (2026) - [The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems](https://mlsanity.com/paper/2606.30524/) (2026) - [When Do Multi-Agent Systems Help? An Information Bottleneck Perspective](https://mlsanity.com/paper/2607.16133/) (2026) - [Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2608.06865/) (2026) - [The Wealth of Agents: Scaling Agentic AI Across Developers](https://mlsanity.com/paper/2610.20518/) (2026) ## Abstract (arXiv) Multi-agent systems (MAS) decompose complex tasks and delegate subtasks to different large language model (LLM) agents and tools. Prior studies have reported the superior accuracy performance of MAS across diverse domains, enabled by long-horizon context tracking and error correction through role-specific agents. However, the design and deployment of MAS incur higher complexity and runtime cost compared to single-agent systems (SAS). Meanwhile, frontier LLMs, such as OpenAI-o3 and Gemini-2.5-Pro, have rapidly advanced in long-context reasoning, memory retention, and tool usage, mitigating many limitations that originally motivated MAS designs. In this paper, we conduct an extensive empirical study comparing MAS and SAS across various popular agentic applications. We find that the benefits of MAS over SAS diminish as LLM capabilities improve, and we propose efficient mechanisms to pinpoint the error-prone agent in MAS. Furthermore, the performance discrepancy between MAS and SAS motivates our design of a hybrid agentic paradigm, request cascading between MAS and SAS, to improve both efficiency and capability. Our design improves accuracy by 1.1-12% while reducing deployment costs by up to 20% across various agentic applications.