mlsanityData to 14 Oct 2026

PFedMA: Who Should Join Next as Federated Multi-Agent Orchestration Evolves?

arXiv 2610.19458 ↗First posted 14 Oct 2026cs.AIcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Federated Multi-Agent Systems (FedMAS) offer a promising paradigm for collaborative reasoning among LLM-based agents while keeping raw client data decentralized. However, reliable multi-round collaboration remains challenging. Agent selection must take into consideration evolving task requirements and the agent's historical reliability, while privacy rules must adapt to changing collaboration contexts and meet the client's personalized needs. To address these challenges, we propose PFedMA, a federated multi-agent framework for feedback driven multi-round collaboration under heterogeneous privacy requirements. Across rounds, PFedMA maintains historical capability and reliability states to guide agent selection, evaluates task responses before aggregation, and refines subsequent queries according to accumulated collaboration feedback. PFedMA enables bidirectional local to global and global to local private rule evolution across heterogeneous clients. Clients generalize locally updated privacy rules and selectively incorporate globally maintained rules, thereby facilitating cross-client privacy rule evolution while preserving personalized constraints. Extensive experiments across reasoning, privacy sensitive, and adversarial settings show that PFedMA improves task performance, reduces measured privacy leakage, and improves system robustness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 32 of its 41 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

32 of 41 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning20 Oct
  2. 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detection14 Oct
  3. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?24 Aug
  4. 2025CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate5 Jul
  5. 2024Federated In-Context LLM Agent Learning11 Dec
  6. 2024GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning13 Jun
  7. 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun

Other references · 25

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2023Qwen Technical Reportcited by 3,344
  5. 2025s1: Simple test-time scalingcited by 1,341
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  7. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  8. 2026Kimi K2.5: Visual Agentic Intelligencecited by 501
  9. 2024Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agentscited by 369
  10. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  11. 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Actioncited by 171
  12. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 88
13 more
  1. 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learningcited by 72
  2. 2026The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligencecited by 61
  3. 2025KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systemscited by 37
  4. 2024On the Privacy Risk of In-context Learningcited by 32
  5. 2025Searching for Privacy Risks in LLM Agents via Simulationcited by 22
  6. 2023Text-driven Prompt Generation for Vision-Language Models in Federated Learningcited by 17
  7. 2025Can Textual Gradient Work in Federated Learning?cited by 15
  8. 2025Federated In-Context Learning: Iterative Refinement for Improved Answer Qualitycited by 8
  9. 2025Many LLMs Are More Utilitarian Than Onecited by 8
  10. 2025Privacy-Enhancing Paradigms within Federated Multi-Agent Systemscited by 7
  11. 2025MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosiscited by 6
  12. 2021A Privacy-Preserving and Trustable Multi-agent Learning Frameworkcited by 2
  13. 2025Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Taskscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents
  2. 2026Agentic Federated Learning: The Future of Distributed Training Orchestration
  3. 2026FederatedSkill: Federated Learning for Agentic Skill Evolution
  4. 2026Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation
  5. 2026Federated Agent Optimization
  6. 2025From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0
  7. 2026Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data
  8. 2026Agentic Federated Learning: Rule-Based Client and Server Agents for Adaptive Training