Enhancing the reasoning capabilities of large language models (LLMs) is crucial for enabling them to tackle complex, multi-step problems. Multi-agent frameworks have shown great potential in enhancing LLMs' reasoning capabilities. However, the lack of effective cooperation between LLM agents hinders their performance, especially for multi-step reasoning tasks. This paper proposes a novel cooperative multi-agent reasoning framework (CoPlanner) by separating reasoning steps and assigning distinct duties to different agents. CoPlanner consists of two LLM agents: a planning agent and a reasoning agent. The planning agent provides high-level strategic hints, while the reasoning agent follows these hints and infers answers. By training the planning agent's policy through the interactive reasoning process via Proximal Policy Optimization (PPO), the LLaMA-3-8B-based CoPlanner outperforms the previous best method by 9.94\% on LogiQA and 3.09\% on BBH. Our results demonstrate that the guidance from the planning agent and the effective cooperation between the agents contribute to the superior performance of CoPlanner in tackling multi-step reasoning problems.

Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods. Though detection of such counterfeits has been a taxing problem in the image forensics community, a recent class of forensic detectors -- universal detectors -- are able to surprisingly spot counterfeit images regardless of generator architectures, loss functions, training datasets, and resolutions. This intriguing property suggests the possible existence of transferable forensic features (T-FF) in universal detectors. In this work, we conduct the first analytical study to discover and understand T-FF in universal detectors. Our contributions are 2-fold: 1) We propose a novel forensic feature relevance statistic (FF-RS) to quantify and discover T-FF in universal detectors and, 2) Our qualitative and quantitative investigations uncover an unexpected finding: color is a critical T-FF in universal detectors. Code and models are available at https://keshik6.github.io/transferable-forensic-features/

We've all experienced those interminable, necessary post-pandemic Zoom calls where time appears to stand still, and everything wonderful about a writer's everyday life crumbles to dust. Fortunately, some of us have had better times. Despite the fact that I usually have a good time at meetings, I decided to add some AI to the mix. I thought about how I might make a meeting more enjoyable. How can something so drab and uninteresting be transformed into a rainbow of laughter and delight?

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. We've all experienced those interminable, necessary post-pandemic Zoom calls where time appears to stand still, and everything wonderful about a writer's everyday life crumbles to dust. Fortunately, some of us have had better times.

Counterfeiting is a big business. Nearly $509 billion of fake and pirated products were sold internationally in 2016. In that year, the latest for which data was available, counterfeit goods made up 3.3% of international trade, up from 2.5% three years earlier, according to the Organization for Economic Cooperation and Development. That figure, which does not include domestic trade in fakes, not only means companies are losing revenue and consumers are not getting their money's worth; counterfeiting also helps fund organized crime. Because it skirts safety regulations, makers of counterfeits could use toxic materials or produce unsafe products.

It normally takes a user three to five minutes to go through the authentication process, but she is faster because the store, Opulent Habits, in Madison, N.J., has been using the app since 2018. "I can do it in less than a minute at this point," Ms. Matthaei says. A look at how innovation and technology are transforming the way we live, work and play. Increasingly, the role of spotting counterfeits is being filled by artificial-intelligence algorithms that have studied every angle of tens of thousands of bags, shoes and other items that are often knocked off. Inc. are developing machine-learning tools to help protect shoppers.

When Olivia Matthaei, a consignment store sales clerk, needs to check whether a designer handbag is authentic, she knows the drill. She grabs a custom camera with a microscope lens provided by Entrupy, a New York-based artificial-intelligence startup. The shape of a bulky battery pack, it pops onto an iPhone or iPod. She opens the Entrupy app and selects a brand from a list. It normally takes a user three to five minutes to go through the authentication process, but she is faster because the store, Opulent Habits, in Madison, N.J., has been using the app since 2018.

Life sciences and the pharmaceutical industry need robotic applications for their ability to perform tasks that are beyond human capabilities. Due to trend changes in the design automation and life science laboratory environments, increased interaction with the robotics landscape has resulted in significant impacts. The assembly of implants and manufacturing processes of drugs, together with the packaging of both, has harmful proximities like biohazards, radioactivity, and toxic compounds. There are expectations that the design componentry and influenced inspirations of robotics in life science and pharmaceutical processes have fulfilled in the areas of personalized medicine, aged population, and outsourced operations. Systems that have already been fully automated include mass spectrometry, liquid handling, and cell culture in the life science front, while providing higher uniformity and accuracy for the pharmaceutical processes.

A face spoofing attack occurs when an intruder attempts to impersonate someone who carries a gainful authentication clearance. It is a trending topic due to the increasing demand for biometric authentication on mobile devices, high-security areas, among others. This work introduces a new database named Sense Wax Attack dataset (SWAX), comprised of real human and wax figure images and videos that endorse the problem of face spoofing detection. The dataset consists of more than 1800 face images and 110 videos of 55 people/waxworks, arranged in training, validation and test sets with a large range in expression, illumination and pose variations. Experiments performed with baseline methods show that despite the progress in recent years, advanced spoofing methods are still vulnerable to high-quality violation attempts.

Amazon is taking additional steps to stop counterfeit sellers. Dharmesh Mehta, Amazon's vice president of consumer trust and partner support, told CBS News that the e-commerce giant has made'progress in reducing the amount of counterfeit' on the site. But Mehta admits the firm is still a long ways off from eradicating the issue. So far, Amazon has added 500 brands to its invite-only Project Zero initiative, which was rolled out in February and aims to give sellers greater controls over fake goods. Amazon has announced new steps to combat fake listings on the site.