AI Wiki — Knowledge Base

LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents

arXiv:2609.30662v1 Announce Type: new Abstract: Large language models (LLMs) can plan, use tools, write code, and execute long-horizon workflows, yet strong local competence does not guarantee project

model-releasesarxiv-cs-ai

28 Sept 2026

Search: “persistence”

Persistence Spheres: a Bi-continuous Linear Representation of Measures for Partial Optimal Transport

PreSIST: Vision-Language-Informed Object Persistence Prediction in Open-World Scenes

A Long-Run Persistence Theory for AI Systems under the Redundancy-Adjusted Artificial Age Score (AAS)

Complexity of Normalized Persistence Problems for Topological Data Analysis and Local Hamiltonians

Persistence Paradox in Dynamic Science: Evidence from the Deep Learning Revolution

A Spatial Persistence Gradient in European Warming Consistent with North Atlantic Cold-Blob Influence

Voronoi Histograms for Adaptive Vectorization of Expected Persistence Diagrams

From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features

Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning

Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells

Automatic persistence now in beta on Vercel Sandbox

Where Do Two Populations of Persistence Diagrams Differ? Calibrated Local Inference at a Fixed Budget

Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion

Age of Learning: Temporal Persistence of Prediction Errors as a Learning Signal

Sierpinski--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation

ChatGPT Sites means ChatGPT in 'Work' mode can build and deploy public websites running on Cloudflare Workers, including with persistence on…

Sandbox persistence is now GA

Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents

Language Mutations Sustain the Persistences of Conspiracy Theories on Social Media

A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification

langgraph persistence lets you checkpoint agent state at every step so you can pause, resume, and replay from any point. essential for long-…

ChronoFuseGS: Multi-Temporal Gaussian Fusion with Per-Splat Persistence and Change Visualization

Replication Without Persistence in Hosted LLMs: Measurement Sensitivity in Action-Time Belief Evaluation

COMPLEX: A Closed-Form Certified Embedding of Multiparameter Persistence Modules

Parser States Already Know: Structure-Conditioned KV Persistence for Structured Generation

The persistence of painting styles

Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning

AI Assistance Reduces Persistence and Hurts Independent Performance

Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing

Long-running models can solve hard open-ended problems, but their persistence can create safety risks that shorter-horizon evaluations miss.…

PFlow-T: A Persistence-Driven Forward Process for Topology-Controlled Generation

Cloud agent infrastructure has a lot of moving parts: VM isolation, session persistence, environment provisioning, orchestration, integratio…

persistence always pays off, even for ml interns (btw, I haven't done anything for the past 30 mins, just observing the intern making mistak…

Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos

A scaling law of contextual persistence in human language

Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning

PHIDA: Persistence-Guided Node-to-Cluster Mapping for Online Clustering

Persistence-Augmented Neural Networks

LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents

Gradient Descent with Stochastic Subspaces via Persistence of Memory

Uncensored Open-weight Models: Redistribution as the Persistence Layer

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence

Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence

PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models