Position: agentic AI orchestration should be Bayes-consistent

• URL: http://arxiv.org/abs/2605.00742v2
• Date: Wed, 06 May 2026 18:32:55 GMT
• Title: Position: agentic AI orchestration should be Bayes-consistent
• Abstract summary: This paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system.<n>It provides examples and design patterns to illustrate how beliefs and utility-aware policies can improve agentic AI orchestration.
• Score: 92.04373485710285
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities [103.60384544335072]
  Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence.<n>Our framework aligns problem-solving agentic behaviors with a structured taxonomy of reusable mathematical atomic capabilities.<n> Experiments reveal that models with similar end-to-end accuracy can exhibit markedly different agentic capability profiles.
  arXiv  Detail & Related papers  (2026-08-27T10:52:06Z)
• Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication for Adaptive Method Selection [1.321203201549798]
  In multi-agent pipelines, small inconsistencies between agent intentions and actions can lead to semantic drift.<n>We introduce a multi-agent framework that combines contextual bandits with structured inter-agent communication and semantic checkpoints.<n>We show that reliable autonomous learning requires not only identifying high-quality actions, but also preserving the integrity of their propagation.
  arXiv  Detail & Related papers  (2026-05-28T14:57:21Z)
• StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning [44.2992619825834]
  General agents have given rise to phenomenal applications such as OpenClaw and Claude Code.<n>Agentic Reinforcement Learning (RL) is emerging as a central post-training paradigm for empowering Large Language Models.<n>We argue that the conventional token-level Markov Decision Process (MDP) should be advanced to a step-level MDP formulation.
  arXiv  Detail & Related papers  (2026-04-20T15:22:39Z)
• Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs [23.590034731179824]
  We present Through Role Orchestration (Maestro), a principled paradigm for collaboration that structurally decouples cognitive modes.<n>Maestro uses a collective of parallel Execution Agents for diverse exploration and a specialized Central Agent for convergent, evaluative synthesis.<n>Experiments on mathematical reasoning and general problem-solving benchmarks demonstrate that Maestro, coupled with CLPO, consistently outperforms existing state-of-the-art multi-agent approaches.
  arXiv  Detail & Related papers  (2025-11-08T21:01:27Z)
• Fundamentals of Building Autonomous LLM Agents [64.39018305018904]
  This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs)<n>The research aims to explore patterns to develop "agentic" LLMs that can automate complex tasks and bridge the performance gap with human capabilities.
  arXiv  Detail & Related papers  (2025-10-10T10:32:39Z)
• Toward a Theory of Agents as Tool-Use Decision-Makers [89.26889709510242]
  We argue that true autonomy requires agents to be grounded in a coherent epistemic framework that governs what they know, what they need to know, and how to acquire that knowledge efficiently.<n>We propose a unified theory that treats internal reasoning and external actions as equivalent epistemic tools, enabling agents to systematically coordinate introspection and interaction.<n>This perspective shifts the design of agents from mere action executors to knowledge-driven intelligence systems, offering a principled path toward building foundation agents capable of adaptive, efficient, and goal-directed behavior.
  arXiv  Detail & Related papers  (2025-06-01T07:52:16Z)
• Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents [61.132523071109354]
  This paper investigates the interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios.<n>Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" stances than pure game-theoretic agents.
  arXiv  Detail & Related papers  (2025-04-11T15:41:21Z)
• Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integration [0.0]
  Case-Based Reasoning (CBR) is a strategy that solves new problems by referencing past experiences.<n>This paper explores how Case-Based Reasoning (CBR), a strategy that solves new problems by referencing past experiences, can be integrated into Large Language Models.
  arXiv  Detail & Related papers  (2025-04-09T14:51:02Z)
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [85.95607119635102]
  Large language models (LLMs) can mimic human-like intelligence.<n>WorkArena++ is designed to evaluate the planning, problem-solving, logical/arithmetic reasoning, retrieval, and contextual understanding abilities of web agents.
  arXiv  Detail & Related papers  (2024-07-07T07:15:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.