Causal symmetrization as an empirical signature of operational autonomy in complex systems

• URL: http://arxiv.org/abs/2512.09352v2
• Date: Fri, 12 Dec 2025 14:45:11 GMT
• Title: Causal symmetrization as an empirical signature of operational autonomy in complex systems
• Authors: Anthony Gosme,
• Abstract summary: Theoretical biology has proposed that autonomous systems sustain their identity through reciprocal constraints between structure and activity.<n>We empirically assess this framework in artificial sociotechnical systems by identifying a statistical signature consistent with operational autonomy.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Theoretical biology has long proposed that autonomous systems sustain their identity through reciprocal constraints between structure and activity, a dynamical regime underlying concepts such as closure to efficient causation and autopoiesis. Despite their influence, these principles have resisted direct empirical assessment outside biological systems. Here, we empirically assess this framework in artificial sociotechnical systems by identifying a statistical signature consistent with operational autonomy. Analyzing 50 large-scale collaborative software ecosystems spanning 11,042 system-months, we develop an order parameter ($Γ$) quantifying structural persistence under component turnover and use Granger causality to characterize directional coupling between organizational architecture and collective activity. $Γ$ exhibits a bimodal distribution (Hartigan's dip test $p = 0.0126$; $Δ$BIC = 2000), revealing a sharp phase transition between an exploratory regime of high variance and a mature regime characterized by a 1.77-fold variance collapse. At maturity, causal symmetrization emerges, with the structure--activity coupling ratio shifting from 0.71 (activity-driven) to 0.94 (bidirectional). A composite viability index combining activity and structural persistence outperforms activity-based prediction alone (AUC = 0.88 vs. 0.81), identifying ``structural zombie'' systems in which sustained activity masks architectural decay. Together, these results show that causal symmetrization functions as a necessary statistical signature consistent with theoretical notions of operational closure, without implying biological life or mechanistic closure. They demonstrate that core principles of autonomy can be empirically probed in artificial collaborative systems, supporting substrate-independent dynamical signatures of self-organizing autonomy across complex adaptive systems.

Related papers

• Weight Updates as Activation Shifts: A Principled Framework for Steering [54.70188910511715]
  Activation steering promises to be an extremely parameter-efficient form of adaptation, but its effectiveness depends on critical design choices.<n>We establish a first-order equivalence between activation-space interventions and weight-space updates, deriving the conditions under which activation steering can replicate fine-tuning behavior.<n>This equivalence yields a principled framework for steering design and identifies the post-block output as a theoretically-backed and highly expressive intervention site.
  arXiv  Detail & Related papers  (2026-02-28T02:50:04Z)
• Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science [70.3658845234978]
  Large Language Models (LLMs) have greatly extended the capabilities of Multi-Agent Systems (MAS)<n>Despite this rapid progress, the field still relies heavily on empirical trial-and-error.<n>This bottleneck stems from the ambiguity of attribution.<n>We propose a factor attribution paradigm to systematically identify collaboration-driving factors.
  arXiv  Detail & Related papers  (2026-02-05T04:19:52Z)
• Toward a Sustainable Federated Learning Ecosystem: A Practical Least Core Mechanism for Payoff Allocation [71.86087908416255]
  We introduce a payoff allocation framework based on the least core (LC) concept.<n>Unlike traditional methods, the LC prioritizes the cohesion of the federation by minimizing the maximum dissatisfaction.<n>Case studies in federated intrusion detection demonstrate that our mechanism correctly identifies pivotal contributors and strategic alliances.
  arXiv  Detail & Related papers  (2026-02-03T11:10:50Z)
• Revising Bloom's Taxonomy for Dual-Mode Cognition in Human-AI Systems: The Augmented Cognition Framework [0.0]
  cognitive acts increasingly occur in two distinct modes: individually, using biological resources alone, or distributed across a human-AI system.<n>Existing revisions to Bloom's taxonomy treat AI as an external capability to be mapped against human cognition rather than as a driver of this dual-mode structure.<n>This paper proposes the Augmented Cognition Framework (ACF), a restructured taxonomy built on three principles.
  arXiv  Detail & Related papers  (2026-01-31T12:45:43Z)
• Quantifying Model Uniqueness in Heterogeneous AI Ecosystems [1.1162481475388237]
  We introduce a statistical framework for auditing model uniqueness based on In-Silico Quasi-Experimental Design.<n>By enforcing matched interventions across models, we isolate intrinsic model identity and quantify uniqueness as the Peer-Inexpressible Residual (PIER)<n>These results move trustworthy AI beyond explaining single models.
  arXiv  Detail & Related papers  (2026-01-30T13:41:53Z)
• Smooth embeddings in contracting recurrent networks driven by regular dynamics: A synthesis for neural representation [45.88028371034407]
  Recent empirical work has documented topology-preserving latent organization in trained recurrent models.<n>Recent theoretical results in reservoir computing establish conditions under which the synchronization map is an embedding.<n>Our contribution is an integrated framework that assembles generalized synchronization and embedding guarantees for contracting reservoirs.
  arXiv  Detail & Related papers  (2026-01-26T23:10:39Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  Agents, language model (LM)-based systems that are capable of reasoning, planning, and acting are becoming the dominant paradigm for real-world AI applications.<n>Despite this widespread adoption, the principles that determine their performance remain underexplored.<n>We address this gap by deriving scaling principles for agent systems.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems [22.357102759752234]
  This paper introduces a novel framework for simulating and analyzing how uncooperative behaviors can destabilize or collapse multi-agent systems.<n>Our framework includes two key components: (1) a game theory-based taxonomy of uncooperative agent behaviors, and (2) a multi-stage simulation pipeline that dynamically generates and refines uncooperative behaviors as agents' states evolve.
  arXiv  Detail & Related papers  (2025-11-19T20:39:19Z)
• Structured Contrastive Learning for Interpretable Latent Representations [2.8870482999983094]
  We propose Structured Contrastive Learning (SCL), a framework that partitions latent space representations into three semantic groups.<n> Experiments on ECG phase invariance and IMU rotation demonstrate superior performance.<n>This work represents a paradigm shift from reactive data augmentation to proactive structural learning, enabling interpretable latent representations in neural networks.
  arXiv  Detail & Related papers  (2025-11-18T21:18:20Z)
• The Information-Theoretic Imperative: Compression and the Epistemic Foundations of Intelligence [0.0]
  Existing frameworks converge on the centrality of compression to intelligence but leave underspecified why this process enforces the discovery of causal structure.<n>We introduce a two-level framework to address this gap.
  arXiv  Detail & Related papers  (2025-10-29T18:28:06Z)
• Parallel BiLSTM-Transformer networks for forecasting chaotic dynamics [24.960864709838436]
  This study proposes a parallel predictive framework integrating Transformer and Bidirectional Long Short-Term Memory networks.<n>The proposed hybrid model employs a dual-branch architecture, where the Transformer branch mainly captures long-range dependencies.<n>The results consistently indicate that the proposed hybrid framework outperforms both single-branch architectures across tasks.
  arXiv  Detail & Related papers  (2025-10-27T16:17:10Z)
• Bidirectional Representations Augmented Autoregressive Biological Sequence Generation:Application in De Novo Peptide Sequencing [51.12821379640881]
  Autoregressive (AR) models offer holistic, bidirectional representations but face challenges with generative coherence and scalability.<n>We propose a hybrid framework enhancing AR generation by dynamically integrating rich contextual information from non-autoregressive mechanisms.<n>A novel cross-decoder attention module enables the AR decoder to iteratively query and integrate these bidirectional features.
  arXiv  Detail & Related papers  (2025-10-09T12:52:55Z)
• PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis [75.14189839277928]
  We present PowerGrow, a co-generative framework that significantly reduces computational overhead while maintaining operational validity.<n> Experiments across benchmark settings show that PowerGrow outperforms prior diffusion models in fidelity and diversity.<n>This demonstrates its ability to generate operationally valid and realistic power grid scenarios.
  arXiv  Detail & Related papers  (2025-08-29T01:47:27Z)
• Emergence of Hierarchies in Multi-Agent Self-Organizing Systems Pursuing a Joint Objective [12.899919591015912]
  Multi-agent self-organizing systems (MASOS) exhibit key characteristics including scalability, adaptability, flexibility, and robustness.<n>This paper focuses on the emergence of dependency hierarchies during task execution.<n>By calculating the gradients of each agent's actions in relation to the states of other agents, the inter-agent dependencies are quantified.
  arXiv  Detail & Related papers  (2025-08-13T06:50:03Z)
• A Neuroscience-Inspired Dual-Process Model of Compositional Generalization [12.494200165412186]
  We propose textscMirage, a neuro-inspired dual-process model.<n>It combines a fast, intuitive System1'' (a meta-trained Transformer) with a deliberate, rule-based System2'' (a Engine)<n>Mirage achieves $>$99% accuracy on all splits of the SCAN benchmark in a task-agnostic setting.
  arXiv  Detail & Related papers  (2025-07-25T01:02:07Z)
• Multi-Agent Collaboration via Evolving Orchestration [55.574417128944226]
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving.<n>We propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states.<n> Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs.
  arXiv  Detail & Related papers  (2025-05-26T07:02:17Z)
• Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA [81.4991350761909]
  Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
  arXiv  Detail & Related papers  (2021-07-21T14:22:14Z)
• An active inference model of collective intelligence [0.0]
  This paper posits a minimal agent-based model that simulates the relationship between local individual-level interaction and collective intelligence. Results show that stepwise cognitive transitions increase system performance by providing complementary mechanisms for alignment between agents' local and global optima.
  arXiv  Detail & Related papers  (2021-04-02T14:32:01Z)
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems [74.80320120264459]
  We present an approach to learn such motions from a limited number of human demonstrations. The complex motions are encoded as rollouts of a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.
  arXiv  Detail & Related papers  (2020-05-27T03:51:57Z)

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.