We introduce a new approach to *agent programming*, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy (e.g., tree search). We introduce *probabilistic angelic nondeterminism* (PAN), a programming model that disentangles these two concerns, allowing the programmer to describe the agent workflow and independently experiment with different inference-time strategies by simply changing a few inputs. We provide an implementation of PAN in Python as the EnCompass framework, which uses a Python decorator to compile agent workflow programs into a search space. We present three case studies that demonstrate how the framework lets the programmer quickly improve the reliability of an agent and easily switch between different inference-time strategies, all with little additional coding.

Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a precise characterization has been absent. We provide the first such characterization, focusing on the utility of deterministic skills in deterministic sparse-reward environments with finite action spaces. We show theoretically and empirically that RL performance gain from skills is worse in environments where solutions to states are less compressible. Additional theoretical results suggest that skills benefit exploration more than they benefit learning from existing experience, and that using unexpressive skills such as macroactions may worsen RL performance. We hope our findings can guide research on automatic skill discovery and help RL practitioners better decide when and how to use skills.

This paper focuses on using natural language descriptions to enhance predictive models in the chemistry field.Conventionally, chemoinformatics models are trained with extensive structured data manually extracted from the literature.In this paper, we introduce TextReact, a novel method that directly augments predictive chemistry with texts retrieved from the literature.TextReact retrieves text descriptions relevant for a given chemical reaction, and then aligns them with the molecular representation of the reaction.This alignment is enhanced via an auxiliary masked LM objective incorporated in the predictor training.We empirically validate the framework on two chemistry tasks: reaction condition recommendation and onestep retrosynthesis.By leveraging text retrieval, TextReact significantly outperforms state-ofthe-art chemoinformatics models trained solely on molecular data.

Unsupervised feature selection has attracted remarkable attention recently. With the development of data acquisition technology, multi-dimensional tensor data has been appeared in enormous real-world applications. However, most existing unsupervised feature selection methods are non-tensor-based which results the vectorization of tensor data as a preprocessing step. This seemingly ordinary operation has led to an unnecessary loss of the multi-dimensional structural information and eventually restricted the quality of the selected features. To overcome the limitation, in this paper, we propose a novel unsupervised feature selection model: Nonnegative tensor CP (CANDECOMP/PARAFAC) decomposition based unsupervised feature selection, CPUFS for short. In specific, we devise new tensor-oriented linear classifier and feature selection matrix for CPUFS. In addition, CPUFS simultaneously conducts graph regularized nonnegative CP decomposition and newly-designed tensor-oriented pseudo label regression and feature selection to fully preserve the multi-dimensional data structure. To solve the CPUFS model, we propose an efficient iterative optimization algorithm with theoretically guaranteed convergence, whose computational complexity scales linearly in the number of features. A variation of the CPUFS model by incorporating nonnegativity into the linear classifier, namely CPUFSnn, is also proposed and studied. Experimental results on ten real-world benchmark datasets demonstrate the effectiveness of both CPUFS and CPUFSnn over the state-of-the-arts.

Feature extraction plays an indispensable role in image and video technology. However, it is difficult for traditional matrix based feature extraction methods to handle massive multi-dimensional data. This, alongside with the ubiquitous uncertainty (noise) in real-world data, resulted in many robust tensor based feature extraction models. All these existing models did not consider the worst-case model performance (i.e., the largest fitting error among all samples), which is critically important from a robust optimization perspective. In this paper, we propose a novel robust feature extraction model via$\ell _{\infty }$-norm based nonnegative Tucker decomposition. The model is to minimize the maximum sample fitting error so as to overcome the influence of data uncertainty. Although the new model is nonconvex and nonsmooth, we design an effective iterative optimization algorithm with theoretical guarantee on its convergence. The performance of the new model on five real-world benchmark object classification and face recognition datasets under various corruption scenarios are evaluated, and the experimental results show the excellence of the new model by comparing to many existing models.