Large Language Models (LLM) based agents have shown promise in autonomously completing tasks across various domains, e.g., robotics, games, and web navigation. However, these agents typically require elaborate design and expert prompts to solve tasks in specific domains, which limits their adaptability. We introduce AutoManual, a framework enabling LLM agents to autonomously build their understanding through interaction and adapt to new environments. AutoManual categorizes environmental knowledge into diverse rules and optimizes them in an online fashion by two agents: 1) The Planner codes actionable plans based on current rules for interacting with the environment. 2) The Builder updates the rules through a well-structured rule system that facilitates online rule management and essential detail retention. To mitigate hallucinations in managing rules, we introduce \textit{case-conditioned prompting} strategy for the Builder. Finally, the Formulator agent compiles these rules into a comprehensive manual. The self-generated manual can not only improve the adaptability but also guide the planning of smaller LLMs while being human-readable. Given only one simple demonstration, AutoManual significantly improves task success rates, achieving 97.4\% with GPT-4-turbo and 86.2\% with GPT-3.5-turbo on ALFWorld benchmark tasks. The source code will be available soon.

In this paper, we investigate the scheduling issue of diesel generators (DGs) in an Internet of Things (IoT)-Driven isolated microgrid (MG) by deep reinforcement learning (DRL). The renewable energy is fully exploited under the uncertainty of renewable generation and load demand. The DRL agent learns an optimal policy from history renewable and load data of previous days, where the policy can generate real-time decisions based on observations of past renewable and load data of previous hours collected by connected sensors. The goal is to reduce operating cost on the premise of ensuring supply-demand balance. In specific, a novel finite-horizon partial observable Markov decision process (POMDP) model is conceived considering the spinning reserve. In order to overcome the challenge of discrete-continuous hybrid action space due to the binary DG switching decision and continuous energy dispatch (ED) decision, a DRL algorithm, namely the hybrid action finite-horizon RDPG (HAFH-RDPG), is proposed. HAFH-RDPG seamlessly integrates two classical DRL algorithms, i.e., deep Q-network (DQN) and recurrent deterministic policy gradient (RDPG), based on a finite-horizon dynamic programming (DP) framework. Extensive experiments are performed with real-world data in an IoT-driven MG to evaluate the capability of the proposed algorithm in handling the uncertainty due to inter-hour and inter-day power fluctuation and to compare its performance with those of the benchmark algorithms. J. Qi, L. Lei, and S. X. Yang are with the School of Engineering, University of Guelph, Guelph, ON N1G 2W1, Canada (e-mail: jiaju@uoguelph.ca; K. Zheng is with the College of Electrical Engineering and Computer Sciences, Ningbo University, Ningbo, 315211, China.

Scientists have developed an artificial intelligence (AI) system that can analyze eye scans taken during a routine visit to an optician or eye clinic and identify patients at a high risk of a heart attack.  Doctors have recognized that changes to the tiny blood vessels in the retina are indicators of broader vascular disease, including problems with the heart.  In the research, led by the University of Leeds, deep learning techniques were used to train the AI system to automatically read retinal scans and identify those people who, over the following year, were likely to have a heart attack.   Deep learning is a complex series of algorithms that enable computers to identify patterns in data and make predictions.  Writing in the journal Nature Machine Intelligence, the researchers report that the AI system had an accuracy of between 70% and 80% and could be used as a second referral mechanism for in-depth cardiovascular investigation.   The use of deep learning in the analysis of retinal scans could revolutionize the way patients are regularly screened for signs of heart disease.  Professor Alex Frangi, who holds the Diamond Jubilee Chair in Computational Medicine at the University of Leeds and is a Turing Fellow at the Alan Turing Institute, supervised the research. He said: “Cardiovascular diseases, including heart attacks, are the leading cause of early death worldwide and the second-largest killer in the UK. This causes chronic ill-health and misery worldwide.  “This technique opens up the possibility of revolutionizing the screening of cardiac disease. Retinal scans are comparatively cheap and routinely used in many optician practices. As a result of automated screening, patients who are at high risk of becoming ill could be referred to specialist cardiac services.  “The scans could also be used to track the early signs of heart disease.”  The study involved a worldwide collaboration of scientists, engineers, and clinicians from the University of Leeds; Leeds Teaching Hospitals NHS Trust; the University of York; the Cixi Institute of Biomedical Imaging in Ningbo, part of the Chinese Academy of Sciences; the University of Cote d’Azur, France; the National Centre for Biotechnology Information and the National Eye Institute, both part of the National Institutes for Health in the US; and KU Leuven in Belgium.  The UK Biobank provided data for the study.  Chris Gale, Professor of Cardiovascular Medicine at the University of Leeds and a Consultant Cardiologist at Leeds Teaching Hospitals NHS Trust, was one of the authors of the research paper.  He said: “The AI system has the potential to identify individuals attending routine eye screening who are at higher future risk of cardiovascular disease, whereby preventative treatments could be started earlier to prevent premature cardiovascular disease.”  Deep learning  During the deep learning process, the AI system analyzed the retinal scans and cardiac scans of more than 5,000 people. The AI system identified associations between pathology in the retina and changes in the patient’s heart.   Once the image patterns were learned, the AI system could estimate the size and pumping efficiency of the left ventricle, one of the heart’s four chambers, from retinal scans alone. An enlarged ventricle is linked with an increased risk of heart disease.   With information on the estimated size of the left ventricle and its pumping efficiency combined with basic demographic data about the patient, their age, and sex, the AI system could predict their risk of a heart attack over the subsequent 12 months.   Currently, details about the size and pumping efficiency of a patient’s left ventricle can only be determined if they have diagnostic tests such as echocardiography or magnetic resonance imaging of the heart. Those diagnostic tests can be expensive and are often only available in a hospital setting, making them inaccessible for people in countries with less well-resourced healthcare systems - or unnecessarily increasing healthcare costs and waiting times in developed countries.  Sven Plein, British Heart Foundation Professor of Cardiovascular Imaging at the University of Leeds and one of the authors of the research paper, said: “The AI system is an excellent tool for unraveling the complex patterns that exist in nature, and that is what we have found here – the intricate pattern of changes in the retina linked to changes in the heart.” 

Parking demand forecasting and behaviour analysis have received increasing attention in recent years because of their critical role in mitigating traffic congestion and understanding travel behaviours. However, previous studies usually only consider temporal dependence but ignore the spatial correlations among parking lots for parking prediction. This is mainly due to the lack of direct physical connections or observable interactions between them. Thus, how to quantify the spatial correlation remains a significant challenge. To bridge the gap, in this study, we propose a spatial-aware parking prediction framework, which includes two steps, i.e. spatial connection graph construction and spatio-temporal forecasting. A case study in Ningbo, China is conducted using parking data of over one million records before and during COVID-19. The results show that the approach is superior on parking occupancy forecasting than baseline methods, especially for the cases with high temporal irregularity such as during COVID-19. Our work has revealed the impact of the pandemic on parking behaviour and also accentuated the importance of modelling spatial dependence in parking behaviour forecasting, which can benefit future studies on epidemiology and human travel behaviours.

Deep reinforcement learning (DRL) is an emerging methodology that is transforming the way many complicated transportation decision-making problems are tackled. Researchers have been increasingly turning to this powerful learning-based methodology to solve challenging problems across transportation fields. While many promising applications have been reported in the literature, there remains a lack of comprehensive synthesis of the many DRL algorithms and their uses and adaptations. The objective of this paper is to fill this gap by conducting a comprehensive, synthesized review of DRL applications in transportation. We start by offering an overview of the DRL mathematical background, popular and promising DRL algorithms, and some highly effective DRL extensions. Building on this overview, a systematic investigation of about 150 DRL studies that have appeared in the transportation literature, divided into seven different categories, is performed. Building on this review, we continue to examine the applicability, strengths, shortcomings, and common and application-specific issues of DRL techniques with regard to their applications in transportation. In the end, we recommend directions for future research and present available resources for actually implementing DRL.

The first time many of us heard about China's use of facial recognition on jaywalkers was just this week when a prominent Chinese businesswoman was publicly "named and shamed" for improper street crossing. Turns out, she wasn't even there: China's terrifyingly over-the-top use of tech for citizen surveillance made a mistake. The AI system identified Dong Mingzhu's face from a bus advertisement for her company's products. "[The] president of China's biggest air conditioning maker," wrote The Telegraph, "had her image flashed up on a public display screen in the city of Ningbo, near Shanghai, with a caption saying she had illegally crossed the street on a red light." Shortly after, Ningbo traffic police admitted the mistake and claimed to have "completely upgraded the system to reduce the false recognition rate."

There are many criticisms you can level at China's growing reliance on facial recognition, including its absolute faith in technology: what happens if there's a false positive? Unfortunately, we just saw an example of that in action. Police in the city of Ningbo have taken corrective action after the facial recognition system at a crosswalk mistakenly accused famous businesswoman Dong Mingzhu of jaywalking because she appeared in an ad on a passing bus. As with any other detected offender in the area, it posted both Dong's name (incorrectly displaying her surname as "Ju") and government ID. The police have since deleted the infraction and claim they've upgraded the facial recognition technology to "reduce the false recognition rate," although it's unclear just what they could have done to address this specific issue.

Could you perceive the touch of an ant's antenna on your fingertip? This new tactile sensor can, and its inventors report that it could one day be integrated into prostheses to give wearers a superhuman sense of touch. The sensor converts pressure from touch to electric signals that, theoretically, could be perceived by the brain. Researchers at the Chinese Academy of Sciences in Ningbo, Zhenhai, described their invention yesterday in the journal Science Robotics. There have been a lot of touch sensors described in the literature, but this one's sensitivity is off the charts.

Aircraft fuel is without a doubt the biggest cost for any airline and often receives widespread attention, especially when airlines hedge their bets the wrong way. Cathay Pacific reported a HK$4.49 billion fuel-hedging loss in the first half of 2016, which has hurt the airline's profitability. The second biggest expense for an airline is human capital, and researchers from Hong Kong Polytechnic University and University of Nottingham Ningbo China Business School may have found a solution to ease some of Cathays financial woes through an unlikely source – Machine Learning and Data Science. The researchers say that a "poorly designed airline crew schedule can result in unreliable flight schedules, significantly jeopardizing airline operations and profitability if insufficient crew members are available or other glitches occur. For that reason, managing airline crew scheduling and costs are one of the most crucial topics for airlines because it yields enormous economic benefits and ranks as the second highest expenditure after fuel costs."

Aircraft fuel is without a doubt the biggest cost for any airline and often receives widespread attention, especially when airlines hedge their bets the wrong way. Cathay Pacific reported a HK$4.49 billion fuel-hedging loss in the first half of 2016, which has hurt the airline's profitability. The second biggest expense for an airline is human capital, and researchers from Hong Kong Polytechnic University and University of Nottingham Ningbo China Business School may have found a solution to ease some of Cathays financial woes through an unlikely source – Machine Learning and Data Science. The researchers say that a "poorly designed airline crew schedule can result in unreliable flight schedules, significantly jeopardizing airline operations and profitability if insufficient crew members are available or other glitches occur. For that reason, managing airline crew scheduling and costs are one of the most crucial topics for airlines because it yields enormous economic benefits and ranks as the second highest expenditure after fuel costs."