mlsanityData to 14 Oct 2026

Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence

arXiv 2508.20019 ↗First posted 27 Aug 2025cs.LG cs.AI cs.CLcited by 8

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

Abstract (arXiv)

Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce Symphony, a decentralized multi-agent system which enables lightweight LLMs on consumer-grade GPUs to coordinate. Symphony introduces three key mechanisms: (1) a decentralized ledger that records capabilities, (2) a Beacon-selection protocol for dynamic task allocation, and (3) weighted result voting based on CoTs. This design forms a privacy-saving, scalable, and fault-tolerant orchestration with low overhead. Empirically, Symphony outperforms existing baselines on reasoning benchmarks, achieving substantial accuracy gains and demonstrating robustness across models of varying capacities.

Key facts. Cited by 8 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 27 references that are in the map. First posted on arXiv 27 Aug 2025.

Builds on

14 of 27 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems13 Mar
  2. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 11

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  3. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  5. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  6. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
  7. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  8. 2024Simulating Classroom Education with LLM-Empowered Agentscited by 127
  9. 2024WcDT: World-centric Diffusion Transformer for Traffic Scene Generationcited by 32
  10. 2024Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Usecited by 9
  11. 2025Hide-and-Shill: A Reinforcement Learning Framework for Market Manipulation Detection in Symphony-a Decentralized Multi-Agent Systemcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  2. 2026ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inferencecited by 5
  3. 2026AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agentscited by 3
  4. 2026Synergy: A Next-Generation General-Purpose Agent for Open Agentic Webcited by 2
  5. 2026MediHive: A Decentralized Agent Collective for Medical Reasoningcited by 0
  6. 2026An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuumcited by 0
  7. 2026Rethinking Multi-Agent Collaboration: When More Is Lesscited by 0
  8. 2026PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Decentralized Multi-Agent Systems with Shared Context
  2. 2025SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning
  3. 2026Towards Adaptive, Scalable, and Robust Coordination of LLM Agents: A Dynamic Ad-Hoc Networking Perspective
  4. 2025Benchmarking LLMs' Swarm intelligence
  5. 2025Adaptive GPU Resource Allocation for Multi-Agent Collaborative Reasoning in Serverless Environments
  6. 2026Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis
  7. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
  8. 2025Hierarchical Decentralized Multi-Agent Coordination with Privacy-Preserving Knowledge Sharing: Extending AgentNet for Scalable Autonomous Systems