Large Language Model (LLM) based agents have garnered significant attention and are becoming increasingly popular. Furthermore, planning ability is a crucial component of an LLM-based agent, involving interaction with the environment and executing actions to complete a planning task, which generally entails achieving a desired goal from an initial state. This paper investigates enhancing the planning abilities of LLMs through instruction tuning, referred to as agent training. Recent studies have demonstrated that utilizing expert-level trajectory for instruction-tuning LLMs effectively enhances their planning capabilities. However, existing work primarily focuses on synthesizing trajectories from manually designed planning tasks and environments. The labor-intensive nature of creating these environments and tasks impedes the generation of sufficiently varied and extensive trajectories. To address this limitation, this paper explores the automated synthesis of diverse environments and a gradual range of planning tasks, from easy to difficult. We introduce a framework, AgentGen, that leverages LLMs first to generate environments and subsequently generate planning tasks conditioned on these environments. Specifically, to improve environmental diversity, we propose using an inspiration corpus composed of various domain-specific text segments as the context for synthesizing environments. Moreover, to increase the difficulty diversity of generated planning tasks, we propose a bidirectional evolution method, Bi-Evol, that evolves planning tasks from easier and harder directions to synthesize a task set with a smoother difficulty curve. The evaluation results derived from AgentBoard show that AgentGen greatly improves LLMs' planning ability, e.g., the AgentGen instruction-tuned Llama-3 8B surpasses GPT-3.5 in overall performance. Moreover, in certain tasks, it even outperforms GPT-4.

Obesity, the leading cause of many non-communicable diseases, occurs mainly for eating more than our body requirements and lack of proper activity. So, being healthy requires heathy diet plans, especially for patients with comorbidities. But it is difficult to figure out the exact quantity of each nutrient because nutrients requirement varies based on physical and disease conditions. In our study we proposed a novel machine learning based system to predict the amount of nutrients one individual requires for being healthy. We applied different machine learning algorithms: linear regression, support vector machine (SVM), decision tree, random forest, XGBoost, LightGBM on fluid and 3 other major micronutrients: carbohydrate, protein, fat consumption prediction. We achieved high accuracy with low root mean square error (RMSE) by using linear regression in fluid prediction, random forest in carbohydrate prediction and LightGBM in protein and fat prediction. We believe our diet recommender system, OBESEYE, is the only of its kind which recommends diet with the consideration of comorbidities and physical conditions and promote encouragement to get rid of obesity.

Companies are experimenting with personalized eating apps and say the future of healthy eating lies in artificial intelligence. After 20 years with type 2 diabetes, Tom Idema has given up hope of getting his condition under control. He tried many diets without success and even considered bariatric surgery. When her employer gave her the opportunity to use a new diet app that uses artificial intelligence to monitor blood sugar, she accepted. READ MORE: What is Dark Matter?

Changing your diet to improve your health is nothing new--people with diabetes, obesity, Crohn's disease, celiac disease, food allergies, and a host of other conditions have long done so as part of their treatment. But new and sophisticated knowledge about biochemistry, nutrition, and artificial intelligence has given people more tools to figure out what to eat for good health, leading to a boom in the field of personalized nutrition. Personalized nutrition, often used interchangeably with the terms "precision nutrition" or "individualized nutrition" is an emerging branch of science that uses machine learning and "omics" technologies (genomics, proteomics, and metabolomics) to analyze what people eat and predict how they respond to it. Scientists, nutritionists, and health care professionals take the data, analyze it, and use it for a variety of purposes including identifying diet and lifestyle interventions to treat disease, promote health, and enhance performance in elite athletes. Increasingly, it's being adopted by businesses to sell products and services such as nutritional supplements, apps that use machine learning to provide a nutritional analysis of a meal based on a photograph, and stool-sample tests whose results are used to create customized dietary advice that promises to fight bloat, brain fog, and a myriad of other maladies.

Sarmishta Neogy, a fitness enthusiast from Delhi, uses the HealthifyMe app to log and track her calorie intake. Neogy recently upgraded from the company's free service to a paid tier, which gives her access to an artificial intelligence (AI)-based assistant called Ria. However, Neogy says she still uses the app mostly for their recipes, tips and to document food. She found the AI's tips generic and not very helpful. "The Ria service is very basic, so I don't know if I will benefit from it. For instance, if you ask Ria what is missing from my diet, it will tell you what is missing but nothing more," she added.

Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment. We evaluated the effectiveness of a recommender algorithm developed for an online dietary assessment system called Intake24, that automates the multiple-pass 24-hour recall method. The recommender builds a model of eating behavior from recalls collected in past surveys. Based on foods they have already selected, the model is used to remind respondents of associated foods that they may have omitted to report. The performance of prompts generated by the model was compared to that of prompts hand-coded by nutritionists in two dietary studies. The results of our studies demonstrate that the recommender system is able to capture a higher number of foods omitted by respondents of online dietary surveys than prompts hand-coded by nutritionists. However, the considerably lower precision of generated prompts indicates an opportunity for further improvement of the system.

HealthifyMe, a five-year-old start-up backed by Dubai-based NB Ventures, has unveiled a new health and fitness app, by which a user can talk to a nutritionist created by artificial intelligence. The Bengaluru-based firm, which developed the eponymous app, will make the new AI-powered app available to select consumers initially and roll-out the full feature version by January, Tushar Vashisht, co-founder and CEO said in an interview. "There are three million users and 100 million exercises on the app," Mr. Vashisht said. "Millions of exchanges between nutritionists and consumers led us to create a knowledge graph. The graph consisted of both structured and unstructured data. It is probably the world's first completely artificial intelligent nutritionist."

How many people start every year with a promise to themselves that they are going to eat better, drink less and exercise more? I don't have any fancy stats to hand, but I'll go out on a limb and say it's a lot of people (including myself). Of these people, how many are still on track a few weeks later? Even with all the will power in the world it's really difficult. Unfortunately, there's no magic bullet either, nothing that can convert a pizza-eating wine guzzler into a quinoa loving, spirulina sipping health fanatic.

Many people today can't resist snapping beautifully artistic photos of their meals, from the simple morning smoothie to that deliciously sinful sticky toffee pudding. But what if you could instantly find out how many calories you're about to consume as well? Boston-based startup AVA has launched an "intelligent eating" service that allows you to take a photo of your meal, send it to AVA via text and instantly receive nutritional and caloric information about your grub with the help of artificial intelligence and nutritionists. "We wanted to provide an easier way for people to track what they're eating and provide them with really personalised recommendations from a health coach based on what their specific needs are," co-founder and CMO of AVA, Jeanne Connon told IBTimes UK. "AVA uses artificial intelligence to assist nutritionists in estimating calories as well as making recommendations, factoring in historical eating habits, diet patterns, location and behavioural analysis against a database of roughly 50,000 meals." The team has not disclosed exactly how the AI-powered technology works since the service is still in private beta mode.