Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Vasilenko, Vladimir
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Machine Learning I.2.7
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Persistent Identity in AI Agents: A Multi-Anchor Architecture for Resilient Memory and Continuity
par: Menon, Prahlad G.
Publié: (2026)

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
par: Gao, Heyang, et autres
Publié: (2025)

CortexCompile: Harnessing Cortical-Inspired Architectures for Enhanced Multi-Agent NLP Code Synthesis
par: Ramachandran, Gautham, et autres
Publié: (2024)

End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
par: Chen, Guanzhong, et autres
Publié: (2025)

ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing
par: Kadu, Ankush, et autres
Publié: (2025)

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams
par: Llorente-Saguer, Isaac
Publié: (2026)

Large Language Model (LLM) Bias Index -- LLMBI
par: Oketunji, Abiodun Finbarrs, et autres
Publié: (2023)

Beyond the Black Box: A Statistical Model for LLM Reasoning and Inference
par: Dalal, Siddhartha, et autres
Publié: (2024)

Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction
par: Zhang, Guoxiao, et autres
Publié: (2024)

JavelinGuard: Low-Cost Transformer Architectures for LLM Security
par: Datta, Yash, et autres
Publié: (2025)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
par: Oketunji, Abiodun Finbarrs
Publié: (2023)

Autonomous Deep Agent
par: Yu, Amy, et autres
Publié: (2025)

Random Rule Forest (RRF): Interpretable Ensembles of LLM-Generated Questions for Predicting Startup Success
par: Griffin, Ben, et autres
Publié: (2025)

Social Cooperation in Conversational AI Agents
par: Çelikok, Mustafa Mert, et autres
Publié: (2025)

Node-Level Uncertainty Estimation in LLM-Generated SQL
par: Hasson, Hilaf, et autres
Publié: (2025)

Social Learning through Interactions with Other Agents: A Survey
par: Hillier, Dylan, et autres
Publié: (2024)

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
par: Eisenstadt, Roy, et autres
Publié: (2025)

FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
par: Yuan, Xin, et autres
Publié: (2025)

Automating the Deep Space Network Data Systems; A Case Study in Adaptive Anomaly Detection through Agentic AI
par: Chou, Evan J., et autres
Publié: (2025)

OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration
par: Ma, Xinyue, et autres
Publié: (2026)

Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
par: Bhandari, Pranav, et autres
Publié: (2026)

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
par: Kaplanski, Pawel
Publié: (2026)

Behavioural Analysis of Alignment Faking
par: Hadida, Nathaniel Mitrani, et autres
Publié: (2026)

Disposition Distillation at Small Scale: A Three-Arc Negative Result
par: Sadasivan, Hari
Publié: (2026)

Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors
par: Zhang, Zhiwei, et autres
Publié: (2026)

XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference
par: Vankov, Daniil, et autres
Publié: (2026)

GNN for Structural Displacement Prediction
par: Chang, Hung-Fu, et autres
Publié: (2026)

Attention Drift: What Autoregressive Speculative Decoding Models Learn
par: Eldenk, Doğaç, et autres
Publié: (2026)

Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning
par: Mircea, Andrei, et autres
Publié: (2025)

CoDA: Coding LM via Diffusion Adaptation
par: Chen, Haolin, et autres
Publié: (2025)

Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
par: Zhang, Zhengxin, et autres
Publié: (2024)

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
par: Lasby, Mike, et autres
Publié: (2025)

Beyond Memorization: Violating Privacy Via Inference with Large Language Models
par: Staab, Robin, et autres
Publié: (2023)

Meta-Learning at Scale for Large Language Models via Low-Rank Amortized Bayesian Meta-Learning
par: Zhang, Liyi, et autres
Publié: (2025)

xInv: Explainable Optimization of Inverse Problems
par: Memery, Sean, et autres
Publié: (2025)

InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning
par: Zhang, Bo-Wen, et autres
Publié: (2024)

Explainable AI for Smart Greenhouse Control: Interpretability of Temporal Fusion Transformer in the Internet of Robotic Things
par: Bashir, Muhammad Jawad, et autres
Publié: (2025)

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
par: Ashrafi, Nazmus
Publié: (2026)

NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation
par: Saito, Kei
Publié: (2025)

ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering
par: Ghosh, Shubhra, et autres
Publié: (2025)