The Dafny verifier provides strong correctness guarantees but often requires numerous manual helper assertions, creating a significant barrier to adoption. We investigate the use of Large Language Models (LLMs) to automatically infer missing helper assertions in Dafny programs, with a primary focus on cases involving multiple missing assertions. To support this study, we extend the DafnyBench benchmark with curated datasets where one, two, or all assertions are removed, and we introduce a taxonomy of assertion types to analyze inference difficulty. Our approach refines fault localization through a hybrid method that combines LLM predictions with error-message heuristics. We implement this approach in a new tool called DAISY (Dafny Assertion Inference SYstem). While our focus is on multiple missing assertions, we also evaluate DAISY on single-assertion cases. DAISY verifies 63.4% of programs with one missing assertion and 31.7% with multiple missing assertions. Notably, many programs can be verified with fewer assertions than originally present, highlighting that proofs often admit multiple valid repair strategies and that recovering every original assertion is unnecessary. These results demonstrate that automated assertion inference can substantially reduce proof engineering effort and represent a step toward more scalable and accessible formal verification.

Dafny is a popular verification language, which automates proofs by outsourcing them to an SMT solver. This automation is not perfect, however, and the solver often requires guidance in the form of helper assertions creating a burden for the proof engineer. In this paper, we propose Laurel, a tool that uses large language models (LLMs) to automatically generate helper assertions for Dafny programs. To improve the success rate of LLMs in this task, we design two domain-specific prompting techniques. First, we help the LLM determine the location of the missing assertion by analyzing the verifier's error message and inserting an assertion placeholder at that location. Second, we provide the LLM with example assertions from the same codebase, which we select based on a new lemma similarity metric. We evaluate our techniques on a dataset of helper assertions we extracted from three real-world Dafny codebases. Our evaluation shows that Laurel is able to generate over 50% of the required helper assertions given only a few attempts, making LLMs a usable and affordable tool to further automate practical program verification.

In Multi-Agent Reinforcement Learning, communication is critical to encourage cooperation among agents. Communication in realistic wireless networks can be highly unreliable due to network conditions varying with agents' mobility, and stochasticity in the transmission process. We propose a framework to learn practical communication strategies by addressing three fundamental questions: (1) When: Agents learn the timing of communication based on not only message importance but also wireless channel conditions. (2) What: Agents augment message contents with wireless network measurements to better select the game and communication actions. (3) How: Agents use a novel neural message encoder to preserve all information from received messages, regardless of the number and order of messages. Simulating standard benchmarks under realistic wireless network settings, we show significant improvements in game performance, convergence speed and communication efficiency compared with state-of-the-art.

Directed energy is "the ability to create a high amount of energy in a controlled volume at a given distance in order to trigger physical reactions to study the interaction between the energy and the matter," says Dr. Chaouki Kasmi, who is the Chief Researcher at DERC, which is part of the Abu Dhabi government's Advanced Technology Research Council. The research at DERC reflects the multitude of applications that are possible using directed energy, but the research projects have at least one thing in common: the goal of solving real-world scientific or technical challenges. For example, one of DERC's recent developments is a landmine detection system – the ground-penetrating radar - designed to help developing or previously war-torn countries detect and neutralize unexploded landmines. They have their sights set much higher and further with projects focused on using lasers for communications on land, to the moon, and even underwater--truly making the entire world a better place with directed energy technology. "The disruptive innovation that we are bringing today is how we can make it affordable for developing countries. The idea is to create a technology that could really help solve a worldwide problem at low cost. And this is very important for us as we would like to have the system deployed at scale," says Dr. Kasmi.

"We call it single bottom-line sustainability, where I look at the single bottom line of all those elements, and I start attaching sustainability to it," Glickman says. "And I start looking at changes of value and then I can build a business case for change." As companies set sustainability goals--to be carbon neutral by 2050, for example--they're tackling complex challenges: regulations change, supply chains are complicated, especially during the current pandemic, and integrating new technologies into legacy systems is almost always a hurdle, technologically and culturally. Glickman suggests an incremental approach--he calls it micro change, embracing the fact that sustainability isn't a one-and-done paradigm shift. "These are things that can be done in a six-week period, eight-week period, that have tangible proof of concepts that can be measured, that can be done at different levels." Looking at current infrastructure investments, particularly in North America and Europe, as well as the increasing interest of stakeholders, the sustainability bar is expected to rise. "For the next three years you will see a lot of investment. You will see countries or businesses that want to be leading because they see an advantage," says Glickman. "Then you will see others have to move along in that direction also." This episode of Business Lab is produced in partnership with Infosys. Laurel: From MIT Technology Review, I'm Laurel Ruma, and this is Business Lab. The show that helps business leaders make sense of new technologies coming out of the lab and into the marketplace. Our topic today is sustainability, but on a global scale, from factories to supply chains to sustainable development goals for all the countries in the world. It's possible to design for sustainability, get a return on investment, and help fight climate change. My guest is Corey Glickman, who is the vice president and head of the sustainability and design business at Infosys. Corey is an expert in strategic design, digital transformation, customer experience strategy, and the use of visualization applied to the development of innovative products, processes, and services.

Democratizing data access is key to bolstering data inclusion and equity but requires sophisticated data organization and sharing that doesn't compromise privacy. Rights management governance and high levels of end-to-end security can help ensure that data is being shared without security risks, says Zdankus. Ultimately, improving digital inclusion and equity comes down to company culture. "It can't just be a P&L [profit and loss] decision. It has to be around thought leadership and innovation and how you can engage your employees in a way that's meaningful in a way to build relevance for your company," says Zdankus. Solutions need to be value-based to foster goodwill and trust among employees, other organizations, and consumers. "If innovation for equity and inclusion were that easy, it would've been done already," says Zdankus. The push for greater inclusion and equity is a long-term and full-fledged commitment. Companies need to prioritize inclusion within their workforce and offer greater visibility to marginalized voices, develop interest in technology among young people, and implement systems thinking that focuses on how to bring individual strengths together towards a common outcome. This episode of Business Lab is produced in association with Hewlett Packard Enterprises.

And it's more important than ever for companies to evaluate the new technologies teams are implementing to ensure they are facilitating the desired outcomes, as well as to assess a particular technology's potential application to other areas and teams in the company. "In a sales organization, for example, certain teams may have access to certain tools that increase their productivity. Other teams might be able to benefit from that as well," says Hughell. "It's important when we bring in new technologies that we negotiate our contracts such that they're flexible, so we can determine who needs the technology." When evaluating new technologies to drive and support distributed workforces, Hughell suggests paring up individuals, which not only helps people learn, but drives adoption of the new technology and helps the company assess whether it's bringing the expected results. "I always tell my leaders inspect what you expect. Don't just buy a piece of technology, roll it out and expect miracles to happen," she says. "You have to drive adoption and usage, and you might find that it was the wrong technology and it's not serving your desired outcome or purpose, at which point, make that decision as a leader to fast fail and move on." The most important best practice is to do what's necessary to empower your employees to succeed. Providing libraries of bite-size instruction videos, for instance, can help team members learn specific features of new technology related to their work, without having to sit through long training sessions. Creating the atmosphere of learning and collaboration is as important to a company's success as implementing the new technology. "At the end of the day," says Hughell, "if you can show someone that you're going to help empower their success and help increase their productivity and reduce friction in their day-to-day operation, not many people would argue with that."

From the adversity of almost two years of pedal-to-the-metal crisis-response, rose immense investment in business transformation and technologies across all industries. After such rapid transformation, enterprise leaders might be forgiven for wanting to take a pit stop. But this is no time to slow down. With soaring employee expectations, and competition to digitally innovate, transformation in 2022 will continue apace. Trend 1 – Enterprise technology will be forced to'level-up' and meet consumer tech standards Increasingly, workplace technology seems to be playing a losing game of catchup with the consumer devices and apps we use in our everyday lives.

Artificial intelligence helps build physical infrastructure like modular housing, skyscrapers, and factory floors. "…many problems that we wrestle with in all forms of engineering and design are very, very complex problems…those problems are beginning to reach the limits of human capacity," says Mike Haley, the vice president of research at Autodesk. But there's hope with AI capabilities, Haley continues "This is a place where AI and humans come together very nicely because AI can actually take certain very complex problems in the world and recast them." And where "AI and humans come together" is at the start of the process with generative design, which incorporates AI into the design process to explore solutions and ideas that a human alone might not have even considered. "You really want to be able to look at the entire lifecycle of producing something and ask yourself, 'How can I produce this by using the least amount of energy throughout?'" This kind of thinking will reduce the impact of, not just construction, but any sort of product creation on the planet. The symbiotic human-computer relationship behind generative design is necessary to solve those "very complex problems"--including sustainability. "We are not going to have a sustainable society until we learn to build products--from mobile phones to buildings to large pieces of infrastructure--that survive the long-term," Haley notes. The key, he says, is to start in the earliest stages of the design process. "Decisions that affect sustainability happen in the conceptual phase, when you're imagining what you're going to create." He continues, "If you can begin to put features into software, into decision-making systems, early on, they can guide designers toward more sustainable solutions by affecting them at this early stage."

Next-generation solutions and products are hitting a wall with wi-fi: it's not fast enough, and latency and connectivity issues mean it's not reliable enough. What's an innovator to do? Focus on what's next: 5G and software-defined networking. Nick McKeown, senior vice president and general manager of the network and edge group at Intel Corporation says this technical leap is what will make future innovation possible, "Once you've got a software platform where you can change its behavior, you can start introducing previously absurd-sounding ideas," including, he continues, "fanciful ideas of automatic, real-time, closed-loop control of an entire network." While nascent, these technological advancements are already showing promise in practical applications. For example, in industrial settings where there's more analysis happening at the edge, having greater observability into the network is allowing for fine timescale responses to mechanical errors and broken equipment. "Corrective action could be something as mundane as a broken link, a broken piece of equipment, but it could actually be a functional incorrectness in the software that is controlling it," says McKeown. Grad students and programmers are taking advantage of the advancements in network technology to try out new ideas through academic projects. "One of the key ideas," says McKeown, "is to verify in real time that the network is operating according to a specification, formally checking against that specification in real time, as packets fly around in the network. This has never been done before." And although this idea remains in the realm of research projects, McKeown believes it exemplifies the promise of a software-based 5G networking future. Software-defined 5G networking promises applications that we can't yet even imagine, says McKeown. "New IoT apps combined with both public and private 5G is going to create a'Cambrian explosion' of new ideas that will manifest in ways that if we were to try to predict, we would get it wrong." Laurel Ruma: From MIT Technology Review, I'm Laurel Ruma and this is Business Lab. The show that helps business leaders make sense of new technologies coming out of the lab and into the marketplace.