Agentic Microphysics: A Manifesto for Generative AI Safety

• URL: http://arxiv.org/abs/2604.15236v1
• Date: Thu, 16 Apr 2026 17:11:28 GMT
• Title: Agentic Microphysics: A Manifesto for Generative AI Safety
• Abstract summary: This paper advances a methodological proposal for safety research in agentic AI.<n>As systems acquire planning, memory, tool use, persistent identity, and sustained interaction, safety can no longer be analysed primarily at the level of the isolated model.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper advances a methodological proposal for safety research in agentic AI. As systems acquire planning, memory, tool use, persistent identity, and sustained interaction, safety can no longer be analysed primarily at the level of the isolated model. Population-level risks arise from structured interaction among agents, through processes of communication, observation, and mutual influence that shape collective behaviour over time. As the object of analysis shifts, a methodological gap emerges. Approaches focused either on single agents or on aggregate outcomes do not identify the interaction-level mechanisms that generate collective risks or the design variables that control them. A framework is required that links local interaction structure to population-level dynamics in a causally explicit way, allowing both explanation and intervention. We introduce two linked concepts. Agentic microphysics defines the level of analysis: local interaction dynamics where one agent's output becomes another's input under specific protocol conditions. Generative safety defines the methodology: growing phenomena and elicit risks from micro-level conditions to identify sufficient mechanisms, detect thresholds, and design effective interventions.

Related papers

• Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild [49.77540427384148]
  We present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild.<n>To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms.<n>AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings.
  arXiv  Detail & Related papers  (2026-07-15T14:30:20Z)
• Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment [1.8124703841795666]
  In agentic AI, safety is determined by interaction topology, not model weights.<n> scaling to more capable models strengthens these effects by increasing consensus formation.<n>We argue that agentic AI must be treated as a dynamical system rather than a collection of aligned components.
  arXiv  Detail & Related papers  (2026-05-01T22:49:10Z)
• From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis [0.0]
  We investigate the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model weights.<n>We propose a targeted mitigation strategy based on prompt-level identity anonymization as an architectural design choice.<n>We argue that architectural design choices outperform model selection as a primary alignment strategy in deployed multi-agent analytical systems.
  arXiv  Detail & Related papers  (2026-04-09T17:00:26Z)
• Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models [53.41258113970795]
  We investigate whether cross-functionality reciprocity itself constitutes a structural source of vulnerability in Unified Multimodal Models (UMMs)<n>We propose RICE: Reciprocal Interaction-based Cross-functionality Exploitation, a novel attack paradigm that explicitly exploits bidirectional interactions between understanding and generation.
  arXiv  Detail & Related papers  (2026-03-28T16:28:39Z)
• Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses [168.50301366360344]
  Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in safety-critical environments.<n>Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions.<n>This survey provides a comprehensive review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline.
  arXiv  Detail & Related papers  (2026-03-28T13:21:44Z)
• Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution [5.051136155296043]
  We propose a principled framework for cascading-risk detection grounded in semantic--geometric co-evolution.<n>By coupling semantic flow signals with graph geometry, the framework learns the normal co-evolutionary dynamics of trusted collaboration.
  arXiv  Detail & Related papers  (2026-03-04T16:45:26Z)
• Agentic Reasoning for Large Language Models [122.81018455095999]
  Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making.<n>Large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, but struggle in open-ended and dynamic environments.<n>Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction.
  arXiv  Detail & Related papers  (2026-01-18T18:58:23Z)
• Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs [85.69785384599827]
  Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them.<n>Existing methods operate under a closed-world assumption, treating the task as a classification problem over a small, predefined verb set.<n>We propose GRASP-HO, a novel Generative Reasoning And Steerable Perception framework that reformulates HOI detection from the closed-set classification task to the open-vocabulary generation problem.
  arXiv  Detail & Related papers  (2025-12-19T14:41:50Z)
• Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions [0.0]
  This paper examines why safety mechanisms designed for human-model interaction do not scale to environments where large language models interact with each other.<n>We propose a conceptual transition from model-level safety to system-level safety, introducing the framework of the Emergent Systemic Risk Horizon (ESRH)<n>The paper contributes (i) a theoretical account of collective risk in interacting LLMs, (ii) a taxonomy connecting micro, meso, and macro-level failure modes, and (iii) a design proposal for InstitutionalAI, an architecture for embedding adaptive oversight within multi-agent systems.
  arXiv  Detail & Related papers  (2025-12-02T12:06:57Z)
• Inferring the time-varying coupling of dynamical systems with temporal convolutional autoencoders [0.0]
  We introduce Temporal Autoencoders for Causal Inference (TACI) TACI combines a new surrogate data metric for assessing causal interactions with a novel two-headed machine learning architecture. We demonstrate TACI's ability to accurately quantify dynamic causal interactions across a variety of systems.
  arXiv  Detail & Related papers  (2024-06-05T12:51:20Z)
• AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
  Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
  arXiv  Detail & Related papers  (2024-01-12T11:18:00Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)
• Divide and Rule: Recurrent Partitioned Network for Dynamic Processes [25.855428321990328]
  Many dynamic processes are involved with interacting variables, from physical systems to sociological analysis. Our goal is to represent a system with a part-whole hierarchy and discover the implied dependencies among intra-system variables. The proposed architecture consists of (i) a perceptive module that extracts a hierarchical and temporally consistent representation of the observation at multiple levels, (ii) a deductive module for determining the relational connection between neurons at each level, and (iii) a statistical module that can predict the future by conditioning on the temporal distributional estimation.
  arXiv  Detail & Related papers  (2021-06-01T06:45:56Z)
• Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction [55.569050872780224]
  We present an online framework for safe crowd-robot interaction based on risk-sensitive optimal control, wherein the risk is modeled by the entropic risk measure. Our modular approach decouples the crowd-robot interaction into learning-based prediction and model-based control. A simulation study and a real-world experiment show that the proposed framework can accomplish safe and efficient navigation while avoiding collisions with more than 50 humans in the scene.
  arXiv  Detail & Related papers  (2020-09-12T02:02:52Z)

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.