We carry out a series of experiments to test large language models' multi-hop reasoning ability from three aspects: selecting and combining external knowledge, dealing with non-sequential reasoning tasks and generalising to data samples with larger numbers of hops. We test the GPT-3.5 model on four reasoning benchmarks with Chain-of-Thought prompting (and its variations). Our results reveal that despite the amazing performance achieved by large language models on various reasoning tasks, models still suffer from severe drawbacks which shows a large gap with humans.

Recently, Deep reinforcement learning (DRL) models have shown promising results in solving routing problems. However, most DRL solvers are commonly proposed to solve node routing problems, such as the Traveling Salesman Problem (TSP). Meanwhile, there has been limited research on applying neural methods to arc routing problems, such as the Chinese Postman Problem (CPP), since they often feature irregular and complex solution spaces compared to TSP. To fill these gaps, this paper proposes a novel DRL framework to address the CPP with load-dependent costs (CPP-LC) (Corberan et al., 2018), which is a complex arc routing problem with load constraints. The novelty of our method is two-fold. First, we formulate the CPP-LC as a Markov Decision Process (MDP) sequential model. Subsequently, we introduce an autoregressive model based on DRL, namely Arc-DRL, consisting of an encoder and decoder to address the CPP-LC challenge effectively. Such a framework allows the DRL model to work efficiently and scalably to arc routing problems. Furthermore, we propose a new bio-inspired meta-heuristic solution based on Evolutionary Algorithm (EA) for CPP-LC. Extensive experiments show that Arc-DRL outperforms existing meta-heuristic methods such as Iterative Local Search (ILS) and Variable Neighborhood Search (VNS) proposed by (Corberan et al., 2018) on large benchmark datasets for CPP-LC regarding both solution quality and running time; while the EA gives the best solution quality with much more running time. We release our C++ implementations for metaheuristics such as EA, ILS and VNS along with the code for data generation and our generated data at https://github.com/HySonLab/Chinese_Postman_Problem

Classifications organize entities into categories that identify similarities within a category and discern dissimilarities among categories, and they powerfully classify information in support of analysis. We propose a new classification scheme premised on the reality of imperfect data. Our computational model uses uncertain data envelopment analysis to define a classification's proximity to equitable efficiency, which is an aggregate measure of intra-similarity within a classification's categories. Our classification process has two overriding computational challenges, those being a loss of convexity and a combinatorially explosive search space. We overcome the first by establishing lower and upper bounds on the proximity value, and then by searching this range with a first-order algorithm. We overcome the second by adapting the p-median problem to initiate our exploration, and by then employing an iterative neighborhood search to finalize a classification. We conclude by classifying the thirty stocks in the Dow Jones Industrial average into performant tiers and by classifying prostate treatments into clinically effectual categories.

Abstract-- This paper presents the DeltaZ robot, a centimeter-scale, low-cost, delta-style robot that allows for a broad range of capabilities and robust functionalities. Current technologies allow DeltaZ to be 3D-printed from soft and rigid materials so that it is easy to assemble and maintain, and lowers the barriers to utilize. Functionality of the robot stems from its three translational degrees of freedom and a closed form kinematic solution which makes manipulation problems more intuitive compared to other manipulators. Moreover, the low cost of the robot presents an opportunity to democratize manipulators for a research setting. We also describe how the robot can be used as a reinforcement learning benchmark. Open-source 3D-printable designs and code are available to the public.

Most survivors of World War II's Nazi concentration camps are now in their 80s and 90s, and soon there will be no one left who experienced the horrors of the Holocaust firsthand -- no one to answer questions or bear witness to future generations. But as we first reported two years ago, a new and dramatic effort is underway to change that by harnessing the technologies of the present and the future. To keep alive the ability to talk to -- and get answers from -- the past. Our interview with Holocaust survivor Aaron Elster, who spent two years of his childhood hidden in a neighbor's attic, was unlike any interview we have ever done. "Aaron, tell us what your parents did before the war," Stahl asked Elster. "They owned and operated a butcher shop," Elster said. It wasn't the content of the interview that was so unusual. "Where did you live?" Stahl asked. "I was born in a small town in Poland called Sokolów Podlaski," Elster said. It's the fact that this interview was with a man who was no longer alive. Aaron Elster died four years ago.

Many state-of-art neural models designed for monotonicity reasoning perform poorly on downward inference. To address this shortcoming, we developed an attentive tree-structured neural network. It consists of a tree-based long-short-term-memory network (Tree-LSTM) with soft attention. It is designed to model the syntactic parse tree information from the sentence pair of a reasoning task. A self-attentive aggregator is used for aligning the representations of the premise and the hypothesis. We present our model and evaluate it using the Monotonicity Entailment Dataset (MED). We show and attempt to explain that our model outperforms existing models on MED.

Artificial intelligence, robots, and automation are rising in importance in many areas. As noted in the recent book, "The Future of Work: Robots, AI, and Automation," there are exciting advances in finance, transportation, national defense, smart cities, and health care, among other areas. Businesses are developing solutions that improve the efficiency and effectiveness of their operations and using these tools to improve the way their firms function. Yet there also are concerns about the impact of these developments on jobs and personal privacy. A Pew Research Center national survey revealed considerable unease about emerging trends.

New York real estate heir Robert Durst has been assigned to an Indiana federal prison, frustrating his defense attorney, who said Sunday that he wants Durst sent to Los Angeles to face a murder charge in the death of his friend Susan Berman. Last December, the Los Angeles County district attorney's office reached an extradition deal with Durst's attorneys. Durst, 73, was due to be transferred by Aug. 18 to a federal prison in Southern California after he agreed to plead guilty to a weapons charge in New Orleans. But Durst has remained in a Louisiana jail. His legal team learned Friday that he was to be relocated to a federal prison with a a specialized medical facility in Terre Haute, Ind. "It is contrary to everything that was agreed upon," attorney Richard DeGuerin told The Times.

Past educational robotics research has indicated that the use of simulators can increase students’ performance in introductory robotics programming courses. In this paper, we introduce a simulator for the iRobot Create that works on Windows PCs. It was developed to work with a Python robotics library and includes an Eclipse plugin, but can simulate any library that uses the serial Open Interface on the Create. The platform, library, and simulator are all easy to use and have been well-received initially by students.

Six high-level requirements drive the implementation of intelligent synthetic adversaries for training: (1) competence, (2) taskability, (3) observational fidelity, (4) behavior variability, most difficult tasks soldiers perform. Frequent Competence: The adversaries must perform training is an essential element in reducing the tactics and missions humans perform in casualties. For this application, the adversaries' environments is costly and restricted to physical goal is to defend a small multistoried mockups of buildings and small towns. The agents must move Environments (VIRTE) program is developing immersive virtual trainers for military operations through the environment, identify tactically on urbanized terrain (MOUT). In this relevant features (such as escape routes), and trainer, four-person fire teams of U.S. Marines communicate and coordinate with other are situated in a virtual urban environment and agents. Virtual opponents new missions for different training scenarios, are required to populate the environment and and they must change their objectives challenge the trainees. Behavior is not scripted or This article describes the general requirements specific to a particular mission, terrain, or operational for virtual MOUT opponents and our development setting, providing flexibility for operational of synthetic adversaries to meet use.