Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space

• URL: http://arxiv.org/abs/2604.12016v1
• Date: Mon, 13 Apr 2026 20:00:42 GMT
• Title: Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space
• Abstract summary: Large language models map semantically related prompts to similar internal representations.<n>We ask whether the identity document of a persistent cognitive agent exhibits analogous attractor-like behavior.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models map semantically related prompts to similar internal representations -- a phenomenon interpretable as attractor-like dynamics. We ask whether the identity document of a persistent cognitive agent (its cognitive_core) exhibits analogous attractor-like behavior. We present a controlled experiment on Llama 3.1 8B Instruct, comparing hidden states of an original cognitive_core (Condition A), seven paraphrases (Condition B), and seven structurally matched controls (Condition C). Mean-pooled states at layers 8, 16, and 24 show that paraphrases converge to a tighter cluster than controls (Cohen's d > 1.88, p < 10^{-27}, Bonferroni-corrected). Replication on Gemma 2 9B confirms cross-architecture generalizability. Ablations suggest the effect is primarily semantic rather than structural, and that structural completeness appears necessary to reach the attractor region. An exploratory experiment shows that reading a scientific description of the agent shifts internal state toward the attractor -- closer than a sham preprint -- distinguishing knowing about an identity from operating as that identity. These results provide representational evidence that agent identity documents induce attractor-like geometry in LLM activation space.

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)
• Measuring What Persists: Conditioning Mechanisms and a Geometric Framework for AI Agent Identity [0.0]
  AI agents in long-context applications drift from their specified identity.<n>Current methods detect this only after qualitative degradation is visible.<n>We present a geometric framework for measuring identity structure using $sqrtmathrmJSD$ metric spaces.
  arXiv  Detail & Related papers  (2026-06-20T02:38:43Z)
• HypoAgent: An Agentic Framework for Interactive Abductive Hypothesis Generation over Knowledge Graphs [52.91976391891331]
  Abductive reasoning over knowledge graphs aims to generate logical hypotheses that explain observed entities or facts.<n>Existing controllable hypothesis generation methods allow users to guide this process with explicit conditions.<n>We propose HypoAgent, an Agentic framework for interactive abductive Hypothesis Generation over knowledge graphs.
  arXiv  Detail & Related papers  (2026-05-29T14:40:37Z)
• Towards Explainability of SLMs by investigating Token Level Activation [2.7590644934977764]
  This work introduces a framework for quantifying token-level representational importance using hidden-state activation strengths at Layer 8 of BERT.<n>The proposed Activation Flow Network (AFN) framework computes Token Activation Strength using the L2 norm of Layer-8 hidden representations.<n>The study further introduces a threshold-based activation bucket formulation that partitions tokens into HIGH-activation and LOW-activation groups.
  arXiv  Detail & Related papers  (2026-05-21T12:09:12Z)
• How to Interpret Agent Behavior [56.59836196946289]
  We introduce ACT*ONOMY, a taxonomy for describing and analyzing agent behavior at runtime.<n>By providing a shared vocabulary, ACT*ONOMY helps researchers, agent designers, and end users interpret agent behavior more consistently.
  arXiv  Detail & Related papers  (2026-05-13T14:52:40Z)
• The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions [6.357772907811544]
  We evaluate 22,500 deterministic trajectories across 3 dataset contexts with 3 state-of-the-art (SOTA) models.<n>We formalize the textitSovereignty Gap: models frequently compute the correct derivation internally but suffer Alignment Hallucinations''<n>We prove that multi-agent social load is strictly non-commutative; the "brand" identity of the Lead Anchor'' auditor disproportionately dictates the swarm's integrity.
  arXiv  Detail & Related papers  (2026-05-11T15:13:01Z)
• Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM Agents [0.0]
  We extend the blicket detector paradigm from developmental science to test capacity in AI agents equipped with architectural scaffolding that targets hypothesis-space restructuring.<n>Our compositional architecture has two discrete components: context graphs, which structure exploration as typed state machines, and dynamic behaviors, which monitor for evidence that the current hypothesis space is inadequate and expand it at runtime.
  arXiv  Detail & Related papers  (2026-04-21T22:49:17Z)
• Detecting LLM Hallucinations via Embedding Cluster Geometry: A Three-Type Taxonomy with Measurable Signatures [0.0]
  We propose a geometric taxonomy of large language model hallucinations based on observable signatures in token embedding cluster structure.<n>We identify three operationally distinct hallucination types: Type 1 (center-drift) under weak context, Type 2 (wrong-well convergence) to locally coherent but contextually incorrect cluster regions, and Type 3 (coverage gaps) where no cluster structure exists.
  arXiv  Detail & Related papers  (2026-02-15T18:14:10Z)
• A Geometric Taxonomy of Hallucinations in LLMs [0.2538209532048866]
  The term "hallucination" in large language models conflates distinct phenomena with different geometric signatures in embedding space.<n>We propose a taxonomy identifying three types: unfaithfulness, confabulation, and factual error.<n>The contribution is a geometric taxonomy clarifying the scope of embedding-based detection.
  arXiv  Detail & Related papers  (2026-01-26T22:07:09Z)
• Structured Episodic Event Memory [37.643537420763344]
  We propose Structured Episodic Event Memory (SEEM), a hierarchical framework that synergizes a graph memory layer for relational facts with a dynamic episodic memory layer for narrative progression.<n> Experimental results on the LoCoMo and LongMemEval benchmarks demonstrate that SEEM significantly outperforms baselines.
  arXiv  Detail & Related papers  (2026-01-10T03:17:25Z)
• Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward [67.00373428443879]
  We introduce a paradigm shift towards subgoal-level evaluation and learning.<n>We first construct GeoGoal, a benchmark synthesized via a rigorous formal verification data engine.<n>We propose the Sub-Goal Verifiable Reward (SGVR) framework, which replaces sparse signals with dense rewards based on the Skeleton Rate.
  arXiv  Detail & Related papers  (2026-01-08T16:17:56Z)
• Mechanistic Interpretability of GPT-2: Lexical and Contextual Layers in Sentiment Analysis [0.0]
  We test the hypothesized two-stage sentiment architecture comprising early lexical detection and mid-layer contextual integration.<n>Our experiments confirm that early layers (0-3) act as lexical sentiment detectors, encoding stable, position specific polarity signals that are largely independent of context.<n>Instead of mid-layer specialization, we find that contextual phenomena such as negation, sarcasm, domain shifts etc. are integrated primarily in late layers (8-11) through a unified, non-modular mechanism.
  arXiv  Detail & Related papers  (2025-12-07T06:36:35Z)
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark [71.3555284685426]
  We introduce RealUnify, a benchmark designed to evaluate bidirectional capability synergy.<n>RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks.<n>We find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient.
  arXiv  Detail & Related papers  (2025-09-29T15:07:28Z)
• Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning [54.69189620971405]
  We provide a unified framework, termed Identifiable Exchangeable Mechanisms (IEM), for representation and structure learning.<n>IEM provides new insights that let us relax the necessary conditions for causal structure identification in exchangeable non-i.i.d. data.<n>We also demonstrate the existence of a duality condition in identifiable representation learning, leading to new identifiability results.
  arXiv  Detail & Related papers  (2024-06-20T13:30:25Z)
• Influence of the Geometry of the world model on Curiosity Based Exploration [1.4461582662466375]
  In human spatial awareness, 3-D projective geometry structures information integration and action planning. We show how geometry can play a key role in information integration and action planning.
  arXiv  Detail & Related papers  (2023-04-01T00:56:06Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)

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.