2026
A Metacognitive Architecture for Correcting LLM Errors in AI Agents
AAAI 2026technical
The ability to correct mistakes and adapt to users
12 accepted papers
The ability to correct mistakes and adapt to users
In modern machine learning pipelines, abundant pretrained representations act as noisy proxy covariates while task-specific labels remain scarce. We study semi-supervised regression in this noisy-covariate setting and propose a simple two-stage estimator. We derive finite-sample generalization bound…
Idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions. While recent studies have leveraged large language models (LLMs) to handle idioms across various tasks, e.g., idiom-containing sentence generation and idiomatic machine t
With the introduction of the Fourth Industrial Revolution and the spread of smart factories, the demand for small-quantity batch production systems is rapidly increasing. As a result, the implementation of robotic gripper systems that can handle various objects is required. Until now, grippers have…
Understanding treatment effect heterogeneity is vital for scientific and policy research. However, identifying and evaluating heterogeneous treatment effects pose significant challenges due to the typically unknown subgroup structure. Recently, a novel approach, causal k-means clustering, has emerge…
Persistence diagrams are one of the most popular types of data summaries used in Topological Data Analysis. The prevailing statistical approach to analyzing persistence diagrams is concerned with filtering out topological noise. In this paper, we adopt a different viewpoint and aim at estimating the…
We propose a robust and reliable evaluation metric for generative models called Topological Precision and Recall (TopP&R, pronounced “topper”), which systematically estimates supports by retaining only topologically and statistically significant features with a certain level of confidence. Existing…
This letter proposes and verifies a new method, the ring-pull mechanism, to overcome the disadvantages of existing wearable robotic gloves. By attaching a ring to the metacarpopha-langeal joint of the finger, the ring-pull mechanism supplements the grasping force of the user, while reducing the weig
We propose PLLay, a novel topological layer for general deep learning models based on persistence landscapes, in which we can efficiently exploit the underlying topological features of the input data structure. In this work, we show differentiability with respect to layer inputs, for a general persi…
In this paper, we propose a novel penetration metric, called deformable penetration depth PDd, to define a measure of inter-penetration between two linearly deforming tetrahedra using the object norm [1]. First of all, we show that a distance metric for a tetrahedron deforming between two configurat…
We derive concentration inequalities for the supremum norm of the difference between a kernel density estimator (KDE) and its point-wise expectation that hold uniformly over the selection of the bandwidth and under weaker conditions on the kernel and the data generating distribution than previously…
A cluster tree provides an intuitive summary of a density function that reveals essential structure about the high-density clusters. The true cluster tree is estimated from a finite sample from an unknown true density. This paper addresses the basic question of quantifying our uncertainty by assess…