Research
LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
Do LLMs Understand Context? A Knowledge Graph-Based Evaluation Framework (opens in a new tab)
arXiv cs.AI ·
Research
Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study (opens in a new tab)
arXiv cs.AI ·
Research
ORCA: Evaluating LLMs on Data Science Code Translation (opens in a new tab)
arXiv cs.AI ·
Research
When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess (opens in a new tab)
arXiv cs.AI ·
Research
Spectral Feedback for Test-Time Alignment of Protein Diffusion Models (opens in a new tab)
arXiv cs.AI ·
Research
HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models (opens in a new tab)
arXiv cs.AI ·
Research
A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory (opens in a new tab)
arXiv cs.AI ·
Research
HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases (opens in a new tab)
arXiv cs.AI ·