mlsanityData to 7 Oct 2026

ADKO: Agentic Decentralized Knowledge Optimization

arXiv 2605.07863 ↗First posted 8 May 2026cs.LGcited by 0

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

also in 1 more
Abstract (arXiv)

We present Agentic Decentralized Knowledge Optimization (ADKO), a framework for collaborative black-box optimization across autonomous agents that achieves sample efficiency, privacy preservation, heterogeneous-objective handling, and communication efficiency. Each agent maintains a private Gaussian Process (GP) surrogate trained on local data and communicates only through knowledge tokens-compact, lossy summaries containing directional signals, advantage scores, and optional language-model (LM) insights-without sharing raw data or model parameters. ADKO unifies GP-Upper Confidence Bound (GP-UCB), parallel Bayesian optimization, decentralized learning, and LM-guided discovery. We provide the first formal analysis of dual information loss: token compression, quantified via mutual-information-based fidelity, and LM approximation error, decomposed into bias and stochastic noise. Our main result shows cumulative regret decomposes into GP error, LM bias, LM noise, and compression loss, with necessary and sufficient conditions for sublinear regret. We also propose fidelity-aware token pruning to preserve high-information tokens under memory budget. Experiments on neural architecture search and scientific discovery validate the theory and show consistent improvements over strong baselines.

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 30 of its 62 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

30 of 62 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search6 Jun

Other references · 29

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  4. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  5. 2023Large Language Models as Optimizerscited by 830
  6. 2019Scalable Global Optimization via Local Bayesian Optimizationcited by 359
  7. 2021Transformers Can Do Bayesian Inferencecited by 338
  8. 2013Bayesian Optimization in a Billion Dimensions via Random Embeddingscited by 178
  9. 2020On Information Gain and Regret Bounds in Gaussian Process Banditscited by 156
  10. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
  11. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  12. 2023Emergent autonomous scientific research capabilities of large language modelscited by 127
17 more
  1. 2024Large Language Models to Enhance Bayesian Optimizationcited by 127
  2. 2017Multi-fidelity Bayesian Optimisation with Continuous Approximationscited by 120
  3. 2015Batch Bayesian Optimization via Local Penalizationcited by 103
  4. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  5. 2020Federated Bayesian Optimization via Thompson Samplingcited by 77
  6. 2014Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictionscited by 66
  7. 2019Active Federated Learningcited by 63
  8. 2017Collaborative Deep Learning in Fixed Topology Networkscited by 60
  9. 2024Large Language Model-Based Evolutionary Optimizer: Reasoning with elitismcited by 27
  10. 2024Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Modelscited by 18
  11. 2025GridMind: LLMs-Powered Agents for Power System Analysis and Operationscited by 15
  12. 2015Differentially Private Bayesian Optimizationcited by 12
  13. 2023Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Designcited by 9
  14. 2025Radio: Rate-Distortion Optimization for Large Language Model Compressioncited by 4
  15. 2026Learning is Forgetting: LLM Training As Lossy Compressioncited by 3
  16. 2018Combining Bayesian Optimization and Lipschitz Optimizationcited by 2
  17. 2026OSCAgent: Accelerating the Discovery of Organic Solar Cells with LLM Agentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026OptiLoop: Coordination-in-the-Loop Verification and Repair for LLM-Generated Optimization Agents
  2. 2026An Empirical Study of Multi-Agent Collaboration for Automated Research
  3. 2026NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents
  4. 2026Federated Agent Optimization
  5. 2026The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
  6. 2025DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
  7. 2026AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
  8. 2026From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling