# When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail

arXiv: https://arxiv.org/abs/2601.04748 · HTML: https://mlsanity.com/paper/2601.04748/

## Key facts

- Cited by 35 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 32 of its 51 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## 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 32)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method](https://mlsanity.com/paper/2402.17193/) (2024)
- [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://mlsanity.com/paper/2303.16434/) (2023)
- [The Quantization Model of Neural Scaling](https://mlsanity.com/paper/2303.13506/) (2023)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools](https://mlsanity.com/paper/2502.04644/) (2025)
- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [Inverse scaling can become U-shaped](https://mlsanity.com/paper/2211.02011/) (2022)

## Built on by (most cited first, 30 of 35)

- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026)
- [SkillX: Automatically Constructing Skill Knowledge Bases for Agents](https://mlsanity.com/paper/2604.04804/) (2026)
- [Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale](https://mlsanity.com/paper/2603.02176/) (2026)
- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [SkillNet: Create, Evaluate, and Connect AI Skills](https://mlsanity.com/paper/2603.04448/) (2026)
- [SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems](https://mlsanity.com/paper/2604.06811/) (2026)
- [Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline](https://mlsanity.com/paper/2601.12307/) (2026)
- [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://mlsanity.com/paper/2602.03955/) (2026)
- [ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents](https://mlsanity.com/paper/2603.20340/) (2026)
- [From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?](https://mlsanity.com/paper/2604.01608/) (2026)
- [SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration](https://mlsanity.com/paper/2605.14089/) (2026)
- [SkillsInjector: Dynamic Skill Context Construction for LLM Agents](https://mlsanity.com/paper/2605.29794/) (2026)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems](https://mlsanity.com/paper/2606.18837/) (2026)
- [Phase Transition for Budgeted Multi-Agent Synergy](https://mlsanity.com/paper/2601.17311/) (2026)
- [Living-Harness Is an Interactive-Agent Evolver](https://mlsanity.com/paper/2607.26598/) (2026)
- [ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners](https://mlsanity.com/paper/2608.09732/) (2026)
- [When Does Multi-Agent Collaboration Help? An Entropy Perspective](https://mlsanity.com/paper/2602.04234/) (2026)
- [Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments](https://mlsanity.com/paper/2602.16653/) (2026)
- [FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse](https://mlsanity.com/paper/2606.11290/) (2026)
- [Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams](https://mlsanity.com/paper/2603.20380/) (2026)
- [In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks](https://mlsanity.com/paper/2604.27891/) (2026)
- [MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks](https://mlsanity.com/paper/2605.21917/) (2026)
- [When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval](https://mlsanity.com/paper/2608.16502/) (2026)
- [Can Small Agents Collaborate to Beat a Single Large Language Model?](https://mlsanity.com/paper/2601.11327/) (2026)
- [A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search](https://mlsanity.com/paper/2604.16394/) (2026)
- [Workflow Closure Is Not Scientific Closure in Auto-Research Systems](https://mlsanity.com/paper/2605.26200/) (2026)
- [Safe Bilevel Delegation (SBD): A Formal Framework for Runtime Delegation Safety in Multi-Agent Systems](https://mlsanity.com/paper/2604.27358/) (2026)
- [HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization](https://mlsanity.com/paper/2605.07214/) (2026)

## Abstract (arXiv)

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question arises: can we achieve similar modularity benefits with a single agent that selects from a library of skills? We explore this question by viewing skills as internalized agent behaviors. From this perspective, a multi-agent system can be compiled into an equivalent single-agent system, trading inter-agent communication for skill selection. Our preliminary experiments suggest this approach can substantially reduce token usage and latency while maintaining competitive accuracy on reasoning benchmarks. However, this efficiency raises a deeper question that has received little attention: how does skill selection scale as libraries grow? Drawing on principles from cognitive science, we propose that LLM skill selection exhibits bounded capacity analogous to human decision-making. We investigate the scaling behavior of skill selection and observe a striking pattern. Rather than degrading gradually, selection accuracy remains stable up to a critical library size, then drops sharply, indicating a phase transition reminiscent of capacity limits in human cognition. Furthermore, we find evidence that semantic confusability among similar skills, rather than library size alone, plays a central role in this degradation. This perspective suggests that hierarchical organization, which has long helped humans manage complex choices, may similarly benefit AI systems. Our initial results with hierarchical routing support this hypothesis. This work opens new questions about the fundamental limits of semantic-based skill selection in LLMs and offers a cognitive-grounded framework and practical guidelines for designing scalable skill-based agents.