mlsanityData to 7 Oct 2026

Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination

arXiv 2609.29366 ↗First posted 24 Sep 2026cs.AIcited by 0

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

Abstract (arXiv)

Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-agent systems theory, several shortcomings come to light: a lack of social intelligence, the absence of coordination mechanisms among agents, unknown emergent behavior, and interactions between agents that are bounded by natural language. We address two of these gaps: the absence of social behavior and the lack of mechanisms for inter-agent coordination. We introduce Epistemic Probabilistic Language Agents (EPLA), a neuro-symbolic architecture for multi-agent coordination under uncertainty. A Symbolic Guard provides structured diagnostic feedback. The LLM generates typed actions, and the Guard controls their execution against an authoritative symbolic state. We formalize the epistemic layer in a gossip testbed through epistemic lottery gossip models, which combine view-based call histories with agent-indexed probability weights. We argue that implementing such a formalism can address shortcomings of agentic LLMs.

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 9 of its 26 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

9 of 26 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025A DbC Inspired Neurosymbolic Layer for Trustworthy Agent Design5 Aug
  2. 2025Large Language Models Miss the Multi-Agent Mark27 May
  3. 2024The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap9 Dec

Other references · 6

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2021Multi-Agent Reinforcement Learning with Temporal Logic Specificationscited by 27
  3. 2024Adversarial Representation Engineering: A General Model Editing Framework for Large Language Modelscited by 12
  4. 2017Common Knowledge in a Logic of Gossipscited by 1
  5. 2017Conditional Belief, Knowledge and Probabilitycited by 1
  6. 2019Strengthening Gossip Protocols using Protocol-Dependent Knowledgecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Symbolic Guidance for LLM Agents in Distributed Multiagent Coordination
  2. 2026CRAFT: Grounded Multi-Agent Coordination Under Partial Information
  3. 2025Consensus Is All You Need: Gossip-Based Reasoning Among Large Language Models
  4. 2026Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems
  5. 2026Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
  6. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
  7. 2025Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
  8. 2026Silent Failure in LLM Agent Systems: The Entropy Principle and the Inevitable Disorder of Autonomous Agents