mlsanityData to 14 Oct 2026

KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

arXiv 2502.07350 ↗First posted 11 Feb 2025cs.AIcited by 37

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

Abstract (arXiv)

As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies. We introduces Knowledge-Aware Bayesian Bandits (KABB), a novel framework that enhances multi-agent system coordination through semantic understanding and dynamic adaptation. The framework features three key innovations: a three-dimensional knowledge distance model for deep semantic understanding, a dual-adaptation mechanism for continuous expert optimization, and a knowledge-aware Thompson Sampling strategy for efficient expert selection. Extensive evaluation demonstrates KABB achieves an optimal cost-performance balance, maintaining high performance while keeping computational demands relatively low in multi-agent coordination.

Key facts. Cited by 37 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 35 of its 51 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

35 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun
  2. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan

Other references · 33

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2023Qwen Technical Reportcited by 3,344
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  7. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  9. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  10. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  11. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  12. 2020Knowledge Graphscited by 621
21 more
  1. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  2. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  3. 2023FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setscited by 201
  4. 2023Large Language Model Routing with Benchmark Datasetscited by 172
  5. 2021Monte Carlo Tree Search: A Review of Recent Modifications and Applicationscited by 161
  6. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 145
  7. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  8. 2024Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaborationcited by 67
  9. 2023Fusing Models with Complementary Expertisecited by 46
  10. 2024Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Modelscited by 44
  11. 2024Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoningcited by 41
  12. 2024MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexitycited by 29
  13. 2025Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understandingcited by 28
  14. 2024A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Healthcited by 24
  15. 2020Modeling and Predicting Trust Dynamics in Human-Robot Teaming: A Bayesian Inference Approachcited by 14
  16. 2022Dual-Geometric Space Embedding Model for Two-View Knowledge Graphscited by 12
  17. 2024Jump Starting Bandits with LLM-Generated Prior Knowledgecited by 12
  18. 2023Knowledge Graph Embedding: An Overviewcited by 10
  19. 2025Offline-to-online hyperparameter transfer for stochastic banditscited by 7
  20. 2025Graph Feedback Bandits on Similar Arms: With and Without Graph Structurescited by 3
  21. 2024Optimizing Generative AI Networking: A Dual Perspective with Multi-Agent Systems and Mixture of Expertscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 24; 2026: 13.

37 papers.

Sort:

By area:

  1. 2025CF-VLM:CounterFactual Vision-Language Fine-tuningcited by 59
  2. 2025LongCodeZip: Compress Long Context for Code Language Modelscited by 39
  3. 2025MAT-Agent: Adaptive Multi-Agent Training Optimizationcited by 35
  4. 2025Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Controlcited by 28
  5. 2025ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichmentcited by 27
  6. 2026FastVMT: Eliminating Redundancy in Video Motion Transfercited by 23
  7. 2025Failure-Driven Workflow Refinementcited by 20
  8. 2025Learning Dynamics of VLM Finetuningcited by 17
  9. 2025FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Modelscited by 11
  10. 2026Group Editing: Edit Multiple Images in One Gocited by 11
  11. 2025STORM: Search-Guided Generative World Models for Robotic Manipulationcited by 7
  12. 2025CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generationcited by 4
25 more
  1. 2026Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systemscited by 4
  2. 2026GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflowscited by 4
  3. 2026PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligencecited by 3
  4. 2025Large Language Models as Discounted Bayesian Filterscited by 2
  5. 2025Adaptive-VoCo: Complexity-Aware Visual Token Compression for Vision-Language Modelscited by 2
  6. 2026ResWM: Residual-Action World Model for Visual RLcited by 2
  7. 2025Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraintscited by 1
  8. 2025Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correctioncited by 1
  9. 2026InstanceAnimator: Multi-Instance Sketch Video Colorizationcited by 1
  10. 2025From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Controlcited by 0
  11. 2025DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Losscited by 0
  12. 2025Guardian: Decoupling Exploration from Safety in Reinforcement Learningcited by 0
  13. 2025GTMA: Dynamic Representation Optimization for OOD Vision-Language Modelscited by 0
  14. 2025PTTA: A Pure Text-to-Animation Framework for High-Quality Creationcited by 0
  15. 2025SirenPose: Dynamic Scene Reconstruction via Geometric Supervisioncited by 0
  16. 2025RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blockscited by 0
  17. 2025A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generationcited by 0
  18. 2025Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priorscited by 0
  19. 2025Forgetting as a Feature: Cognitive Alignment of Large Language Modelscited by 0
  20. 2026LogicGaze: Benchmarking Causal Consistency in Visual Narratives via Counterfactual Verificationcited by 0
  21. 2026Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perceptioncited by 0
  22. 2026Uni-Animator: Towards Unified Visual Colorizationcited by 0
  23. 2026Causal Discovery Should Embrace the Wisdom of the Crowdcited by 0
  24. 2026ProgAgent:A Continual RL Agent with Progress-Aware Rewardscited by 0
  25. 2026PFedMA: Who Should Join Next as Federated Multi-Agent Orchestration Evolves?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Multi-Agent Coordination Adaptation via Structure-Guided Orchestration
  2. 2025From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
  3. 2026Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
  4. 2026Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems
  5. 2026Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
  6. 2025Dynamic Strategy Adaptation in Multi-Agent Environments with Large Language Models
  7. 2026Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems
  8. 2026ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems