# Multi-Agent Teams Hold Experts Back arXiv: https://arxiv.org/abs/2602.01011 ยท HTML: https://mlsanity.com/paper/2602.01011/ ## Key facts - Cited by 21 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 15 of its 61 references that are in the map. - First posted on arXiv 1 Feb 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, 15 of 15) - [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023) - [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023) - [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023) - [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024) - [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025) - [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024) - [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024) - [AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2504.00587/) (2025) - [Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?](https://mlsanity.com/paper/2508.17536/) (2025) - [Latent Collaboration in Multi-Agent Systems](https://mlsanity.com/paper/2511.20639/) (2025) - [SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning](https://mlsanity.com/paper/2502.04780/) (2025) - [Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs](https://mlsanity.com/paper/2505.11556/) (2025) - [Combating Adversarial Attacks with Multi-Agent Debate](https://mlsanity.com/paper/2401.05998/) (2024) - [The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation](https://mlsanity.com/paper/2511.02687/) (2025) - [When none of us perform better than all of us together: the role of analogical decision rules in groups](https://mlsanity.com/paper/1406.7562/) (2014) ## Built on by (most cited first, 21 of 21) - [The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems](https://mlsanity.com/paper/2602.15382/) (2026) - [AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation](https://mlsanity.com/paper/2605.28655/) (2026) - [Scaling Discovery through Test-Time Communication](https://mlsanity.com/paper/2609.21032/) (2026) - [Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning](https://mlsanity.com/paper/2603.01221/) (2026) - [Emergent Risks in Generative Multi-Agent Systems](https://mlsanity.com/paper/2603.27771/) (2026) - [The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams](https://mlsanity.com/paper/2608.23541/) (2026) - [Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.29790/) (2026) - [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026) - [Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs](https://mlsanity.com/paper/2605.06320/) (2026) - [CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments](https://mlsanity.com/paper/2606.06399/) (2026) - [Declarative Data Services: Structured Agentic Discovery for Composing Data Systems](https://mlsanity.com/paper/2605.20690/) (2026) - [Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems](https://mlsanity.com/paper/2606.05985/) (2026) - [Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey](https://mlsanity.com/paper/2606.08500/) (2026) - [Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems](https://mlsanity.com/paper/2608.14667/) (2026) - [Measuring Collective Semantic Change in Populations of Language Model Agents](https://mlsanity.com/paper/2608.28644/) (2026) - [What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality](https://mlsanity.com/paper/2609.08016/) (2026) - [Multi-agent Scaling Across Disjunctive and Compensatory Tasks](https://mlsanity.com/paper/2609.31563/) (2026) - [Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams](https://mlsanity.com/paper/2610.15788/) (2026) - [Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning](https://mlsanity.com/paper/2610.17456/) (2026) - [Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems](https://mlsanity.com/paper/2610.19799/) (2026) - [Scaling Discovery Requires Forgetting](https://mlsanity.com/paper/2610.20563/) (2026) ## Abstract (arXiv) Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, effective coordination cannot be fully designed in advance and must instead emerge through interaction. However, most prior work enforces coordination through fixed roles, workflows, or aggregation rules, leaving open the question of how well self-organizing teams perform when coordination is unconstrained. Drawing on organizational psychology, we study whether self-organizing LLM teams achieve strong synergy, where team performance matches or exceeds the best individual member. Across human-inspired and frontier ML benchmarks, we find that -- unlike human teams -- LLM teams consistently fail to match their expert agent's performance, even when explicitly told who the expert is, incurring performance losses of up to 41.1% on ML benchmarks. Decomposing this failure, we show that expert leveraging, rather than identification, is the primary bottleneck. Conversational analysis reveals a tendency toward integrative compromise -- averaging expert and non-expert views rather than appropriately weighting expertise -- which increases with team size and correlates negatively with performance. Interestingly, this consensus-seeking behavior improves robustness to adversarial agents, suggesting a trade-off between alignment and effective expertise utilization. Our findings reveal a significant gap in the ability of self-organizing multi-agent teams to harness the collective expertise of their members.