mlsanityData to 14 Oct 2026

Self-Resource Allocation in Multi-Agent LLM Systems

arXiv 2504.02051 ↗First posted 2 Apr 2025cs.MA cs.AI cs.CLcited by 15

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in task assignment and coordination. This paper explores how LLMs can effectively allocate computational tasks among multiple agents, considering factors such as cost, efficiency, and performance. In this work, we address key questions, including the effectiveness of LLMs as orchestrators and planners, comparing their effectiveness in task assignment and coordination. Our experiments demonstrate that LLMs can achieve high validity and accuracy in resource allocation tasks. We find that the planner method outperforms the orchestrator method in handling concurrent actions, resulting in improved efficiency and better utilization of agents. Additionally, we show that providing explicit information about worker capabilities enhances the allocation strategies of planners, particularly when dealing with suboptimal workers.

Key facts. Cited by 15 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 35 of its 44 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

35 of 44 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  2. 2024Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models9 Jul
  3. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Tasks4 Jun
  4. 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration23 May
  5. 2024Embodied LLM Agents Learn to Cooperate in Organized Teams19 Mar
  6. 2024LLM Multi-Agent Systems: Challenges and Open Problems5 Feb
  7. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  8. 2023LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination23 Dec
  9. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Models16 Oct
  10. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models5 Oct
  11. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models18 Sep
  12. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
3 more
  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  2. 2023Building Cooperative Embodied Agents Modularly with Large Language Models5 Jul
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 20

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  3. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  4. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  5. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  6. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  7. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  8. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 205
  9. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 187
  10. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 107
  11. 2023MindAgent: Emergent Gaming Interactioncited by 88
  12. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
8 more
  1. 2024How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environmentscited by 67
  2. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  3. 2025RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMscited by 61
  4. 2024A Scalable Communication Protocol for Networks of Large Language Modelscited by 45
  5. 2024Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learningcited by 33
  6. 2024LLM Theory of Mind and Alignment: Opportunities and Riskscited by 18
  7. 2025Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agentscited by 2
  8. 2025When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemmacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025Creativity in LLM-based Multi-Agent Systems: A Surveycited by 23
  2. 2025A Survey on Collaborative Mechanisms Between Large and Small Language Modelscited by 14
  3. 2026Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agentscited by 8
  4. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  5. 2025WebDART: Dynamic Decomposition and Re-planning for Complex Web Taskscited by 5
  6. 2026Emergent Risks in Generative Multi-Agent Systemscited by 5
  7. 2025LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOScited by 4
  8. 2025Adaptive GPU Resource Allocation for Multi-Agent Collaborative Reasoning in Serverless Environmentscited by 4
  9. 2025Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Schedulingcited by 3
  10. 2025From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communicationscited by 2
  11. 2026ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestrationcited by 2
  12. 2026Multi-Agent LLMs Fail to Explore Each Othercited by 2
3 more
  1. 2025An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generationcited by 1
  2. 2026TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Servingcited by 1
  3. 2026Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teamscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination
  2. 2026Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance
  3. 2026Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis
  4. 2026Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams
  5. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  6. 2026SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction
  7. 2026EASy: Towards Efficient LLM-Based Agentic System
  8. 2026Multi-agent Scaling Across Disjunctive and Compensatory Tasks