This paper presents a novel framework, called PLANTOR (PLanning with Natural language for Task-Oriented Robots), that integrates Large Language Models (LLMs) with Prolog-based knowledge management and planning for multi-robot tasks. The system employs a two-phase generation of a robot-oriented knowledge base, ensuring reusability and compositional reasoning, as well as a three-step planning procedure that handles temporal dependencies, resource constraints, and parallel task execution via mixed-integer linear programming. The final plan is converted into a Behaviour Tree for direct use in ROS2. We tested the framework in multi-robot assembly tasks within a block world and an arch-building scenario. Results demonstrate that LLMs can produce accurate knowledge bases with modest human feedback, while Prolog guarantees formal correctness and explainability. This approach underscores the potential of LLM integration for advanced robotics tasks requiring flexible, scalable, and human-understandable planning.

Automated testing of computer games is a challenging problem, especially when lengthy scenarios have to be tested. Automating such a scenario boils down to finding the right sequence of interactions given an abstract description of the scenario. Recent works have shown that an agent-based approach works well for the purpose, e.g. due to agents' reactivity, hence enabling a test agent to immediately react to game events and changing state. Many games nowadays are multi-player. This opens up an interesting possibility to deploy multiple cooperative test agents to test such a game, for example to speed up the execution of multiple testing tasks. This paper offers a cooperative multi-agent testing approach and a study of its performance based on a case study on a 3D game called Lab Recruits.

Today, using Large-scale generative Language Models (LLMs) it is possible to simulate free responses to interview questions like those traditionally analyzed using qualitative research methods. Qualitative methodology encompasses a broad family of techniques involving manual analysis of open-ended interviews or conversations conducted freely in natural language. Here we consider whether artificial "silicon participants" generated by LLMs may be productively studied using qualitative methods aiming to produce insights that could generalize to real human populations. The key concept in our analysis is algorithmic fidelity, a term introduced by Argyle et al. (2023) capturing the degree to which LLM-generated outputs mirror human sub-populations' beliefs and attitudes. By definition, high algorithmic fidelity suggests latent beliefs elicited from LLMs may generalize to real humans, whereas low algorithmic fidelity renders such research invalid. Here we used an LLM to generate interviews with silicon participants matching specific demographic characteristics one-for-one with a set of human participants. Using framework-based qualitative analysis, we showed the key themes obtained from both human and silicon participants were strikingly similar. However, when we analyzed the structure and tone of the interviews we found even more striking differences. We also found evidence of the hyper-accuracy distortion described by Aher et al. (2023). We conclude that the LLM we tested (GPT-3.5) does not have sufficient algorithmic fidelity to expect research on it to generalize to human populations. However, the rapid pace of LLM research makes it plausible this could change in the future. Thus we stress the need to establish epistemic norms now around how to assess validity of LLM-based qualitative research, especially concerning the need to ensure representation of heterogeneous lived experiences.

A business executive, entrepreneur and a team builder, Amit has been managing business operations and fund raising, while steering technology companies into global markets. As an OpenSource enthusiast with deep domain expertise in the DevOps and DevSecOps segments, he enjoys the challenge of bringing a fresh and unique approach to solve market inefficiencies at scale. He is the CEO of Kubiya.ai, a platform that leverages conversational AI to turn complex operations into simple conversations – powering the world of AI DevOps Workflow Automation. In an interview, he speaks on an array of topics. Kubiya provides a unique'embedded' AI experience for devops and end-users alike.

As the complexity of customer churn grows, retention approaches are also evolving to tackle the churn risk and protect customer revenue--and AI can play an instrumental role in that. For many leading recurring revenue businesses, AI is transforming retention by leveraging customer data, advanced analytics and machine learning to extract actionable intelligence and drive multichannel retention actions. In this article, I will look at the five strategic enablers of an AI-powered customer retention transformation. Leveraging customer data properly can unlock valuable insights into your customers and enable you to personalize their experience, improving your relationship with them and increasing their likelihood to stay with you. However, the biggest barrier that companies often face while looking for data is that it is siloed.

Cloud, says Neetan Chopra, is one of the foundational enablers of any enterprise transformation or disruption. Chopra is the chief digital and information officer at IndiGo, India's largest passenger airline. Prior to joining Indigo earlier this year, he held similar technology and digital roles at Dubai Holding and Emirates Airlines. A transformation, he says, means speed and velocity. It means business model experimentation.

Federated learning (FL) was proposed to facilitate the training of models in a distributed environment. It supports the protection of (local) data privacy and uses local resources for model training. Until now, the majority of research has been devoted to "core issues", such as adaptation of machine learning algorithms to FL, data privacy protection, or dealing with the effects of uneven data distribution between clients. This contribution is anchored in a practical use case, where FL is to be actually deployed within an Internet of Things ecosystem. Hence, somewhat different issues that need to be considered, beyond popular considerations found in the literature, are identified. Moreover, an architecture that enables the building of flexible, and adaptable, FL solutions is introduced.

Previously, it was the norm for several data-oriented tools, products, and offerings were to be used to address different requirements. Even in the IBM portfolio, enterprises turned to Planning Analytics, Cognos Analytics, and Watson for specific purposes. In some enterprises, this created a situation where there were individual instances of these powerful tools running in the tech ecosystem. While the tools offer great value in themselves, the sense was always "What if we could get all this goodness together?" That's when IBM created a new all-around offering in the form of Cloud Pak for Data.

As the superintendent of Vistra Corp's Luminant Martin Lake Power Plant, Wayne Brown is an expert in power generation. Vistra is the largest competitive power producer in the United States, operating power plants in 12 states and producing more than 39 gigawatts of electricity--enough to power nearly 20 million homes. The company has been on a journey to drive operational excellence across its generation portfolio. Launched in 2016, its Operational Performance Initiative has driven a step-change improvement in the efficiency of its assets, generating hundreds of millions in incremental EBITDA along the way. This article is a collaborative effort by Duane S. Boning, Vijay D'Silva, Pete Kimball, Bruce Lawler, Retsef Levi, and Ingrid Millan, representing views from McKinsey's Operations Practice and the Massachusetts Institute of Technology's Machine Intelligence for Manufacturing and Operations program. To maintain and improve its position, Vistra is continually looking for the tools, technologies, and approaches that will help it achieve the next level of performance. Most recently, the company has turned to digital and analytics, including machine intelligence (MI). It measures how much electricity is generated for each ton of fuel consumed by the plant.

Much as we use our brains to think, perceive, accept and reject a matter, Artificial Intelligence (AI) has been ghost-thinking for us ever since we invented computer science. And if you are still not clear about how AI is so every-day in our lives, you might want to pause for a while, relax and ask Alexa to play your favourite song. The general belief is that Artificial Intelligence is a concept complicated enough to understand, leave alone learn. But in reality, it is not rocket science. AI is all-pervading, whether we choose to accept that truth or not. One cannot wish away the fact that most of the products that we use at home, workplace, educational institutions or in public these days are spiked with a fair dose of AI.