Federated Agent Optimization

arXiv 2610.01195 ↗First posted 1 Oct 2026cs.AIcited by 0

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

Abstract (arXiv)

Large language model (LLM) agents increasingly operate in private environments and accumulate valuable experience from task execution, tool use, feedback, and local knowledge. Yet such experience is distributed across organizations and cannot be directly shared because of privacy and proprietary constraints. Conventional federated learning is insufficient for this setting, as agent capabilities extend beyond model parameters to memory, tools, rewards, skills, and structured knowledge. In this paper, we formulate Federated Agent Optimization (FAO), which studies how distributed agents can collaboratively improve through controlled information exchange while keeping raw data, complete trajectories, and private knowledge local. We define FAO as a multi-objective problem balancing agent utility, privacy leakage, and communication cost, and organize its optimization space across policy, memory, tool use, reward, and structured knowledge and skills. We further characterize how private experience can be abstracted, protected, aggregated, and adapted into transferable capabilities, providing a unified view of how agents can benefit from one another without direct experience sharing. Finally, we identify the key challenges of FAO and outline several promising directions for future research toward trustworthy federated agent systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 169 of its 240 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

169 of 240 references.

Closest ancestors · 20

Same direction, newest first

8 more

Other references · 149

2022Training language models to follow instructions with human feedbackcited by 15,712
2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
2017Deep reinforcement learning from human preferencescited by 3,846
2023Let's Verify Step by Stepcited by 3,598
2023A Survey of Large Language Modelscited by 2,537
2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908

38 more

2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
2019Deep Leakage from Gradientscited by 1,004
2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
2023ChatDev: Communicative Agents for Software Developmentcited by 893
2023Large Language Models as Optimizerscited by 830
2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
2023A Comprehensive Overview of Large Language Modelscited by 639
2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
2020Personalized Federated Learning with Moreau Envelopescited by 612
2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
2024Large Language Models: A Surveycited by 506
2020An Efficient Framework for Clustered Federated Learningcited by 505
2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
2021Towards Personalized Federated Learningcited by 462
2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
2019Agnostic Federated Learningcited by 451
2024AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agentscited by 406
2019Fair Resource Allocation in Federated Learningcited by 389
2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
2023Tool Learning with Foundation Modelscited by 302
2023Large Language Models as Tool Makerscited by 293
2023Reward Design with Language Modelscited by 257
2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238

50 most cited of 149 All 149 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way