Agents That Model Agents: Five Principles Toward a Theory of Mind for 6G Networks

• URL: http://arxiv.org/abs/2609.01779v1
• Date: Tue, 01 Sep 2026 18:49:44 GMT
• Title: Agents That Model Agents: Five Principles Toward a Theory of Mind for 6G Networks
• Abstract summary: 6G networks will rely on Large Language Model (LLM) agents to manage the Radio Access Network (RAN)<n>Current architectures assume inter-agent messages convey objective facts.<n>A message is instead a emphtrace of the sender's reasoning.
• Score: 24.187937610076265
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Future 6G networks will rely on Large Language Model (LLM) agents to manage the Radio Access Network (RAN). However, current architectures assume inter-agent messages convey objective facts. A message is instead a \emph{trace} of the sender's reasoning: it carries a subjective conclusion, so a syntactically valid report can propagate an AI hallucination and trigger a cascading outage invisible to protocol validation. Reading such a trace requires a Theory of Mind (ToM)---before acting, the receiver must model what the peer believes, and what a peer in that position should have believed. Modeling these interactions as cognitive channels on a cellular sheaf, we obtain a unified framework for resilient multi-agent systems, from which five design principles emerge: (i) a message is evidence of the sender's hidden reasoning; (ii) trust is a continuous cognitive Signal-to-Noise Ratio (SNR)---asserted precision over deviation from the modeled peer belief; (iii) network-wide consistency and resistance to hallucination contagion are computable via the sheaf's Laplacian; (iv) peer-modeling must halt at exactly two levels to conserve compute and survive mutual information decay; and (v) credible capacity is bounded by operational goal alignment, not link bandwidth. A signaling-storm study on locally deployed 1B-parameter telecom language models validates it: cognitive SNR isolates a hallucinating peer that three of its four neighbors agree with, where a divergence gate ranks every wrong peer above the right one; only depth two ToM recovers the correct action; and the spectral gap decides whether a topology reaches consistency inside the near-real-time budget.

Related papers

• MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents [74.83535434786145]
  MNIST-PRO is a benchmark that isolates agentic perception by converting MNIST digit recognition into a sequential, glimpse-based search task with lookback constraints.<n>We evaluate ten multimodal models across four memory representations, including raw visual history, textual states, structured metric grid maps, and a consolidated visual canvas.
  arXiv  Detail & Related papers  (2026-08-31T16:05:39Z)
• Belief Cascades Drive Persuasion in LLM Agent Networks [71.17605142402785]
  We study how goal-directed persuaders shift elicited stances in networks of LLM agents grounded in real-world ego-network topologies.<n>We show that direct exposure reliably predicts next-round stance change in competing runs, and peer relays carry smaller but measurable influence.<n>These results argue for evaluating multi-agent persuasion as a trajectory- and exposure-level process.
  arXiv  Detail & Related papers  (2026-08-25T21:01:19Z)
• DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning [24.745715007832953]
  DiffuseAgent-MI improves accuracy by up to 5.1 points over prior self-evolving agents.<n>On GeoQA, SciVis, VQA-v2 and an in-house multimodal reasoning set, DiffuseAgent-MI improves accuracy by up to 5.1 points.
  arXiv  Detail & Related papers  (2026-08-01T08:54:44Z)
• Intent Signal Theory: A Computational Framework for Intent-State Control in Human-AI Interaction [0.585480332059272]
  Current AI interaction models treat the prompt as the primary object of exchange, omitting a critical layer: the user's latent source intent.<n>Here we introduce Intent Signal Theory (IST), a computational framework that formalises this missing intent layer.<n>IST distinguishes four objects routinely conflated: latent source intent (I*), observable intent proxy (I-hat), encoded carrier (P), and model output (O)
  arXiv  Detail & Related papers  (2026-05-24T13:10:33Z)
• FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning [49.65751420291115]
  Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps.<n>We propose FACT-E, a causality-inspired framework for evaluating CoT quality.<n>We show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learnings.
  arXiv  Detail & Related papers  (2026-04-12T15:35:08Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models [19.148124494194317]
  We propose TraceGuard, a process-guided security framework that transforms small-scale models into robust reasoning firewalls.<n>Our approach treats the reasoning trace as an untrusted payload and establishes a defense-in-depth strategy.<n>We demonstrate robustness against adaptive adversaries in a grey-box setting, establishing TraceGuard as a viable, low-latency security primitive.
  arXiv  Detail & Related papers  (2026-03-02T22:19:13Z)
• To Throw a Stone with Six Birds: On Agents and Agenthood [0.0]
  Six Birds Theory (SBT) treats macroscopic objects as induced closures rather than primitives.<n>We give a type-correct account of agency within SBT.<n>We operationalize this contract in finite controlled systems using four checkable components.
  arXiv  Detail & Related papers  (2026-02-03T10:46:23Z)
• Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
  We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
  arXiv  Detail & Related papers  (2025-03-21T06:12:06Z)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval [139.21955930418815]
  Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
  arXiv  Detail & Related papers  (2023-09-29T09:41:19Z)
• Distributed Inference with Sparse and Quantized Communication [7.155594644943642]
  We consider the problem of distributed inference where agents in a network observe a stream of private signals generated by an unknown state. We develop a novel event-triggered distributed learning rule that is based on the principle of diffusing low beliefs on each false hypothesis. We show that by sequentially refining the range of the quantizers, every agent can learn the truth exponentially fast almost surely, while using just $1$ bit to encode its belief on each hypothesis.
  arXiv  Detail & Related papers  (2020-04-02T23:08:51Z)

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.