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

arXiv: https://arxiv.org/abs/2508.20019 · HTML: https://mlsanity.com/paper/2508.20019/

## 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.

## 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, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [WcDT: World-centric Diffusion Transformer for Traffic Scene Generation](https://mlsanity.com/paper/2404.02082/) (2024)
- [LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems](https://mlsanity.com/paper/2504.01963/) (2025)
- [Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use](https://mlsanity.com/paper/2403.02626/) (2024)
- [Hide-and-Shill: A Reinforcement Learning Framework for Market Manipulation Detection in Symphony-a Decentralized Multi-Agent System](https://mlsanity.com/paper/2507.09179/) (2025)

## Built on by (most cited first, 8 of 8)

- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference](https://mlsanity.com/paper/2602.23681/) (2026)
- [AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents](https://mlsanity.com/paper/2602.20493/) (2026)
- [Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web](https://mlsanity.com/paper/2603.28428/) (2026)
- [MediHive: A Decentralized Agent Collective for Medical Reasoning](https://mlsanity.com/paper/2603.27150/) (2026)
- [An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuum](https://mlsanity.com/paper/2605.10718/) (2026)
- [Rethinking Multi-Agent Collaboration: When More Is Less](https://mlsanity.com/paper/2609.19759/) (2026)
- [PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems](https://mlsanity.com/paper/2609.38482/) (2026)

## 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.