mlsanityData to 7 Oct 2026

Position: agentic AI orchestration should be Bayes-consistent

arXiv 2605.00742 ↗First posted 1 May 2026cs.AI cs.LG stat.MLcited by 3

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

Abstract (arXiv)

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of Bayesian approaches remain unclear for LLM inference, this position paper argues that the control layer of an agentic AI system (that orchestrates LLMs and tools) is a clear case where Bayesian principles should shine. Bayesian decision theory provides a framework for agentic systems that can help to maintain beliefs over task-relevant latent quantities, to update these beliefs from observed agentic and human-AI interactions, and to choose actions. Making LLMs themselves explicitly Bayesian belief-updating engines remains computationally intensive and conceptually nontrivial as a general modeling target. In contrast, this paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system, not necessarily the LLM agent parameters. This paper articulates practical properties for Bayesian control that fit modern agentic AI systems and human-AI collaboration, and provides concrete examples and design patterns to illustrate how calibrated beliefs and utility-aware policies can improve agentic AI orchestration.

Key facts. Cited by 3 papers in the map (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 66 of its 99 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

66 of 99 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Agentic Uncertainty Reveals Agentic Overconfidence6 Feb
  2. 2026Bayesian Orchestration of Multi-LLM Agents for Cost-Aware Sequential Decision-Making4 Jan
  3. 2025Structured Uncertainty guided Clarification for LLM Agents11 Nov

Other references · 63

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  9. 2018World Modelscited by 1,444
  10. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  11. 2023A Survey on Multimodal Large Language Modelscited by 898
  12. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
38 more
  1. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  2. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  3. 2022What learning algorithm is in-context learning? Investigations with linear modelscited by 671
  4. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  5. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 627
  6. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  7. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  8. 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 527
  9. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  10. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  11. 2017Stochastic Gradient Descent as Approximate Bayesian Inferencecited by 298
  12. 2021GFlowNet Foundationscited by 286
  13. 2021The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networkscited by 285
  14. 2013Learning to Optimize Via Posterior Samplingcited by 253
  15. 2025LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristicscited by 227
  16. 2013A General Framework for Updating Belief Distributionscited by 172
  17. 2019Practical Deep Learning with Bayesian Principlescited by 158
  18. 2018Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adamcited by 131
  19. 2024To Believe or Not to Believe Your LLMcited by 120
  20. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  21. 2021The Bayesian Learning Rulecited by 95
  22. 2017Noisy Natural Gradient as Variational Inferencecited by 94
  23. 2025Reasoning with Sampling: Your Base Model is Smarter Than You Thinkcited by 84
  24. 2019Meta-learning of Sequential Strategiescited by 68
  25. 2017Concentration of tempered posteriors and of their variational approximationscited by 66
  26. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  27. 2024Variational Learning is Effective for Large Deep Networkscited by 62
  28. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  29. 2022Bayesian Model Selection, the Marginal Likelihood, and Generalizationcited by 56
  30. 2023Non-Vacuous Generalization Bounds for Large Language Modelscited by 53
  31. 2024Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspectivecited by 51
  32. 2020Meta-trained agents implement Bayes-optimal agentscited by 37
  33. 2021Data augmentation in Bayesian neural networks and the cold posterior effectcited by 36
  34. 2025Bayesian Teaching Enables Probabilistic Reasoning in Large Language Modelscited by 36
  35. 2024Improving Uncertainty Estimation through Semantically Diverse Language Generationcited by 34
  36. 2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debuggingcited by 31
  37. 2025Can Transformers Learn Full Bayesian Inference in Context?cited by 30
  38. 2021Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effectcited by 22

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Bayesian control for coding agentscited by 1
  2. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Studycited by 0
  3. 2026Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allowcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling
  2. 2026Towards a Belief-Based World Model for LLM Agents
  3. 2026Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses
  4. 2026Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability
  5. 2026Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents
  6. 2026Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
  7. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
  8. 2026Before Agents Decide: Epistemic Action in LLM-Based Systems