The emergence of specialized large language models (LLMs) has shown promise in addressing complex tasks for materials science. Many LLMs, however, often struggle with distinct complexities of material science tasks, such as materials science computational tasks, and often rely heavily on outdated implicit knowledge, leading to inaccuracies and hallucinations. To address these challenges, we introduce HoneyComb, the first LLM-based agent system specifically designed for materials science. HoneyComb leverages a novel, high-quality materials science knowledge base (MatSciKB) and a sophisticated tool hub (ToolHub) to enhance its reasoning and computational capabilities tailored to materials science. MatSciKB is a curated, structured knowledge collection based on reliable literature, while ToolHub employs an Inductive Tool Construction method to generate, decompose, and refine API tools for materials science. Additionally, HoneyComb leverages a retriever module that adaptively selects the appropriate knowledge source or tools for specific tasks, thereby ensuring accuracy and relevance. Our results demonstrate that HoneyComb significantly outperforms baseline models across various tasks in materials science, effectively bridging the gap between current LLM capabilities and the specialized needs of this domain. Furthermore, our adaptable framework can be easily extended to other scientific domains, highlighting its potential for broad applicability in advancing scientific research and applications.

Construction defects are costly for the economy. The cost of defect elimination is between 2% and 12.4% of the total cost of construction [1] and much time and effort is required to inspect construction sites and document defects [2]. Automating the inspection of construction projects would free up resources and may even enable more frequent inspections, leading to more efficient construction projects. The progress in CV and ML may enable the complete automation of this process in the future. Although deep learning is applied to many different fields, research into image-based defect detection using deep learning is still limited in the construction industry, despite its large size, and focuses on security, progress, and productivity. In contrast, there appear to be relatively few publications on methods utilized for object detection in quality assurance in construction. So far, the research into detecting defects has been mainly limited to defects occurring in the maintenance phase of infrastructure facilities such as roads, bridges, and sewer systems.

Insurance technology brings in more innovative solutions for homeowners and insurers thanks to artificial intelligence (AI). AI is disrupting the industry by allowing for faster and more user-friendly claims and creating more transparent and customized policies that suit the client's situation. This replaces the traditionally long and painful process of getting a claim or settling for a one-size-fits-all property insurance policy. AI Property from Tractable, for example, allows anyone with a smartphone to access damage quickly and efficiently to buildings caused by hurricanes, floods, and other natural disasters. Use its mobile-friendly web-based app to take photos of the external conditions and submit them to Tractable's AI platform, trained on an extensive database of claims and damaged property.

The typical ingredient-tetris bottleneck played between guest and server while dining out has amplified during COVID-19. Growth in online ordering and takeout has prompted customers with dietary needs to search online for dietary answers more than ever before.1 With over 52% of Americans following at least one diet, and less than 10% of restaurants labeling dietary information (typically not exhaustive), the information gap has never been wider. Prompted by an Ulcerative Colitis health scare for co-founder Tamir Barzilai, Honeycomb.ai is set on eliminating the frustrating process of manual menu parsing by creating a portal for anyone with dietary needs to find suitable food to eat. "After my personal diagnosis, I realized how many others struggle with finding food to eat due to a variety of reasons. The lack of ubiquitous dietary and ingredient transparency didn't make sense from both consumer and business perspectives," says Barzilai.

When honeybees are ready to establish a new colony, they initiate a coordinated procedure called swarming. For beekeepers, swarming provides an opportunity to capture the departing bees and establish a new hive. To forecast a swarm, beekeepers regularly inspect their hives for the presence of larger honeycomb cells that host developing future queens. But those regular inspections are laborious. Now Martin Bencsik of Nottingham Trent University in the UK and his colleagues are automating the process by using machine learning.

Waymo from 2011 has been developing its own set of sensors from the ground up, including three different types of lidars. The company is now making these sensors available to companies outside of self-driving?--?beginning with robotics, security, agricultural technology, and more?--?so they can achieve their own technological breakthroughs. The company has announced that one of our 3D lidar sensors, called Laser Bear Honeycomb, is available to select partners. According to the company, Laser Bear Honeycomb is a best-in-class perimeter sensor. That means one Honeycomb can do the job of three other 3D sensors stacked on top of one another.

Speckling the surface of one of Mars' oldest impact basins, NASA's Mars Reconnaissance Orbiter has spotted a sprawling expanse of'honeycomb' landforms, with individual cells of up to 6 miles wide. The origin of these textured features has long remained a mystery, as scientists debate which type of natural process could be responsible, from glacial events to wind erosion. It's possible that multiple processes are at play, according to NASA, with evidence suggesting the honeycombs and the surrounding landscape in Mars northwestern Hellas Planitia may still be undergoing activity today. Speckling the surface of one of Mars' oldest impact basins, NASA's Mars Reconnaissance Orbiter has spotted a sprawling expanse of'honeycomb' landforms, with individual cells of up to 6 miles wide. According to NASA, the area has features of different natural processes, suggesting activity may still be reshaping the land today.

Two new announcements from Ford highlight how the auto and mobility company is harnessing technology to get ahead. With ambitious plans to launch an autonomous vehicle in 2021, Ford has announced that it is investing $1 billion over the next five years in Argo AI, an artificial intelligence company founded by former Google and Uber leaders, to develop a virtual driver system. Argo AI founders Bryan Salesky, company CEO, and Peter Rander, COO, -- both of whom have worked on self-driving car teams at Google and Uber -- have brought together a team of some of the most experienced roboticists and engineers in the industry to develop the new system for Ford's SAE level 4 self-driving vehicles. "The next decade will be defined by the automation of the automobile, and autonomous vehicles will have as significant an impact on society as Ford's moving assembly line did 100 years ago," said Ford President and CEO Mark Fields. "As Ford expands to be an auto and a mobility company, we believe that investing in Argo AI will create significant value for our shareholders by strengthening Ford's leadership in bringing self-driving vehicles to market in near term and by creating technology that could be licensed to others in the future."

Robots have become one step closer to being more human-like. Researchers have developed actuators that generate movements similar to those of a bicep muscle and are also shock absorbent. This innovated technology uses vacuum power to automate soft, rubber beams, which could one-day allow robots and humans to safely work alongside each other. Researchers have developed actuators for cyborgs that generates movements similar to those of skeletal muscles and are even shock absorbing. Similar to human muscles, actuators are soft, shock absorbing and are not harmful to the robots environment or the humans in it.

The honeycombs in which they store their amber nectar are marvels of precision engineering, an array of prism-shaped cells with a perfectly hexagonal cross-section. The wax walls are made with a very precise thickness, the cells are gently tilted from the horizontal to prevent the viscous honey from running out, and the entire comb is aligned with the Earth's magnetic field. Yet this structure is made without any blueprint or foresight, by many bees working simultaneously and somehow coordinating their efforts to avoid mismatched cells. The ancient Greek philosopher Pappus of Alexandria thought that the bees must be endowed with "a certain geometrical forethought." And who could have given them this wisdom, but God?