Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.20175 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918147293970432 |
|---|---|
| author | Giusti, Lorenzo Werner, Ole Anton Taiello, Riccardo Costa, Matilde Carvalho Tosun, Emre Protani, Andrea Molina, Marc de Almeida, Rodrigo Lopes Cacace, Paolo Santos, Diogo Reis Serio, Luigi |
| author_facet | Giusti, Lorenzo Werner, Ole Anton Taiello, Riccardo Costa, Matilde Carvalho Tosun, Emre Protani, Andrea Molina, Marc de Almeida, Rodrigo Lopes Cacace, Paolo Santos, Diogo Reis Serio, Luigi |
| contents | We present Federation of Agents (FoA), a distributed orchestration framework that transforms static multi-agent coordination into dynamic, capability-driven collaboration. FoA introduces Versioned Capability Vectors (VCVs): machine-readable profiles that make agent capabilities searchable through semantic embeddings, enabling agents to advertise their capabilities, cost, and limitations. Our aarchitecturecombines three key innovations: (1) semantic routing that matches tasks to agents over sharded HNSW indices while enforcing operational constraints through cost-biased optimization, (2) dynamic task decomposition where compatible agents collaboratively break down complex tasks into DAGs of subtasks through consensus-based merging, and (3) smart clustering that groups agents working on similar subtasks into collaborative channels for k-round refinement before synthesis. Built on top of MQTT,s publish-subscribe semantics for scalable message passing, FoA achieves sub-linear complexity through hierarchical capability matching and efficient index maintenance. Evaluation on HealthBench shows 13x improvements over single-model baselines, with clustering-enhanced laboration particularly effective for complex reasoning tasks requiring multiple perspectives. The system scales horizontally while maintaining consistent performance, demonstrating that semantic orchestration with structured collaboration can unlock the collective intelligence of heterogeneous federations of AI agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20175 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI Giusti, Lorenzo Werner, Ole Anton Taiello, Riccardo Costa, Matilde Carvalho Tosun, Emre Protani, Andrea Molina, Marc de Almeida, Rodrigo Lopes Cacace, Paolo Santos, Diogo Reis Serio, Luigi Artificial Intelligence Computation and Language We present Federation of Agents (FoA), a distributed orchestration framework that transforms static multi-agent coordination into dynamic, capability-driven collaboration. FoA introduces Versioned Capability Vectors (VCVs): machine-readable profiles that make agent capabilities searchable through semantic embeddings, enabling agents to advertise their capabilities, cost, and limitations. Our aarchitecturecombines three key innovations: (1) semantic routing that matches tasks to agents over sharded HNSW indices while enforcing operational constraints through cost-biased optimization, (2) dynamic task decomposition where compatible agents collaboratively break down complex tasks into DAGs of subtasks through consensus-based merging, and (3) smart clustering that groups agents working on similar subtasks into collaborative channels for k-round refinement before synthesis. Built on top of MQTT,s publish-subscribe semantics for scalable message passing, FoA achieves sub-linear complexity through hierarchical capability matching and efficient index maintenance. Evaluation on HealthBench shows 13x improvements over single-model baselines, with clustering-enhanced laboration particularly effective for complex reasoning tasks requiring multiple perspectives. The system scales horizontally while maintaining consistent performance, demonstrating that semantic orchestration with structured collaboration can unlock the collective intelligence of heterogeneous federations of AI agents. |
| title | Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2509.20175 |