Rethinking Multi-Agent Collaboration: When More Is Less
cs.AI
Submitted: 2026-09-17
Updated: 2026-09-18
License: http://creativecommons.org/licenses/by/4.0/
The gist: The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-agent collaboration offers
Terminology
Abstract
The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-agent collaboration offers genuine value. As individual agent capabilities continue to scale, multi-agent collaboration faces diminishing returns while incurring growing context overhead. Through systematic analysis, we delineate the capability boundaries of multi-agent collaboration relative to single-agent alternatives, showing that it confers systematic benefits specifically in long-horizon tasks with sparse dependencies, while single-agent harnesses remain superior in tightly coupled, sequential workflows. Building on these insights, we propose SAIGE, a lightweight multi-agent collaboration mechanism based on Semantic-Aware Incremental Graph Evolution. SAIGE models collaboration as a dynamically evolving graph, where nodes are agent instances spawned on demand and edges encode semantic dependencies established through content-based information retrieval. Experiments on long-horizon, complex task benchmarks show that SAIGE achieves a favorable trade-off between context efficiency and task performance, and that scaling the agent pool or deepening the recursion level does not consistently improve outcomes. Our findings suggest that multi-agent superiority is bounded by task structure rather than universal, and that more agents do not necessarily make a system more intelligent.
Sources
- EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
- HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization
- Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
- ROMA: Recursive Open Meta-Agent Framework for Long-Horizon Multi-Agent Systems
- Do LLMs Benefit From Their Own Words?
- SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models
- CodeDelegator: Mitigating Context Pollution via Role Separation in Code-as-Action Agents
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems
- EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
- Latent Collaboration in Multi-Agent Systems
- Mixture-of-Agents Enhances Large Language Model Capabilities
- ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild
- Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
- Language Agents as Optimizable Graphs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection