Large Language Models (LLMs) often struggle with generating truly innovative ideas, typically defaulting to high-probability, familiar concepts within their training data's "gravity wells." While advanced search-based methods like Tree of Thoughts (ToT) attempt to mitigate this, they are fundamentally limited by their reliance on unprincipled, inconsistent self-evaluation heuristics to guide exploration. To address this gap, we introduce \textbf{Magellan}, a novel framework that reframes creative generation as a principled, guided exploration of an LLM's latent conceptual space. At its core, Magellan employs Monte Carlo Tree Search (MCTS) governed by a hierarchical guidance system. For long-range direction, a "semantic compass" vector, formulated via orthogonal projection, steers the search towards relevant novelty. For local, step-by-step decisions, a landscape-aware value function replaces flawed self-evaluation with an explicit reward structure that balances intrinsic coherence, extrinsic novelty, and narrative progress. Extensive experiments demonstrate that Magellan significantly outperforms strong baselines, including ReAct and ToT, in generating scientific ideas with superior plausibility and innovation. Our work shows that for creative discovery, a principled, guided search is more effective than unconstrained agency, paving the way for LLMs to become more capable partners in innovation.

Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP). When such autotelic exploration is achieved by LLM agents trained with online RL in high-dimensional and evolving goal spaces, a key challenge for LP prediction is modeling one's own competence, a form of metacognitive monitoring. Traditional approaches either require extensive sampling or rely on brittle expert-defined goal groupings. We introduce MAGELLAN, a metacognitive framework that lets LLM agents learn to predict their competence and LP online. By capturing semantic relationships between goals, MAGELLAN enables sample-efficient LP estimation and dynamic adaptation to evolving goal spaces through generalization. In an interactive learning environment, we show that MAGELLAN improves LP prediction efficiency and goal prioritization, being the only method allowing the agent to fully master a large and evolving goal space. These results demonstrate how augmenting LLM agents with a metacognitive ability for LP predictions can effectively scale curriculum learning to open-ended goal spaces.

With disinformation and confusion about COVID-19 on the rise, effective patient engagement is taking on an even greater role. Studies have shown that engaged patients show improved health outcomes and that effective tools can enhance service delivery. Communicating with impact is the real key – and innovators and vendors are exploring the best ways to do so. Two such teams are mPulse Mobile and Magellan Rx Management, which recently collaborated to address social isolation and loneliness in nearly 1,800 people with chronic and specialty conditions across the United States. By using mPulse's conversational artificial intelligence platform, the companies say they were able to conduct dialogues via text messages with participants on a variety of health-related topics during a 45-day period.

As a good battle shonen should, One Piece has a variety of iconic fights that are complemented by some flashy and exciting finishing moves. A staple of any anime fight, the idea of the finishing move fuses both brutal power and explicit branding to create some of the most exciting and recognizable attacks ever seen in fiction. In One Piece's world, Devil Fruits, Haki, martial arts, robotic enhancements, and some very loose interpretations of physics all contribute to One Piece's own, colorful gallery of finishing moves. And while rating each one's power and effectiveness is a large discussion within its own right, it's also really fun just looking at which finishing moves are just the coolest and most memorable. Monkey D. Luffy's Gum-Gum Gatling doesn't have the awe-inspiring, simplistic appeal of a one-hit attack; but what it lacks in brevity, it more than makes up for with raw, visceral spectacle.

Entity matching (EM) finds data instances that refer to the same real-world entity. In 2015, we started the Magellan project at UW-Madison, jointly with industrial partners, to build EM systems. Most current EM systems are stand-alone monoliths. In contrast, Magellan borrows ideas from the field of data science (DS), to build a new kind of EM systems, which is ecosystems of interoperable tools for multiple execution environments, such as on-premise, cloud, and mobile. This paper describes Magellan, focusing on the system aspects. We argue why EM can be viewed as a special class of DS problems and thus can benefit from system building ideas in DS. We discuss how these ideas have been adapted to build PyMatcher and CloudMatcher, sophisticated on-premise tools for power users and self-service cloud tools for lay users. These tools exploit techniques from the fields of machine learning, big data scaling, efficient user interaction, databases, and cloud systems. They have been successfully used in 13 companies and domain science groups, have been pushed into production for many customers, and are being commercialized. We discuss the lessons learned and explore applying the Magellan template to other tasks in data exploration, cleaning, and integration. Entity matching (EM) finds data instances that refer to the same real-world entity, such as tuples (David Smith, UW-Madison) and (D. Smith, UWM). This problem, also known as entity resolution, record linkage, deduplication, data matching, et cetera, has been a long-standing challenge in the database, AI, KDD, and Web communities.2,6 As data-driven applications proliferate, EM will become even more important. For example, to analyze raw data for insights, we often integrate multiple raw data sets into a single unified one, before performing the analysis, and such integration often requires EM. To build a knowledge graph, we often start with a small graph and then expand it with new data sets, and such expansion requires EM. When managing a data lake, we often use EM to establish semantic linkages among the disparate data sets in the lake.

Ferdinand Magellan was a Portuguese explorer who launched a Spanish expedition that completed the first circumnavigation of the Earth. It is in this spirit that Magellan was used as the name of the end-to-end entity matching system that is developed at the University of Wisconsin. Entity matching (also known as entity resolution or reference reconciliation or deduplication) is a major task in the larger problem of data integration, a problem that is pervasive in many organizations. Despite being a subject of extensive research for many years, the entity matching problem is surprisingly simple to describe and understand. It is to determine whether two different representations refer to the same real-world entity. Doe, UWisc) and (John Doe, Univ. of Wisconsin)--refer to the same person.

Although technically a product breakout, the session on OpenText's Digital Accelerants product collection was presented to the entire audience as our last full-audience session before the afternoon breakouts. This was split into three sections: cloud, AI and analytics, and process automation. Jon Schupp, VP of Cloud GTM, spoke about how information is transforming the world: not just cloud, but a number of other technologies, a changing workforce, growing customer expectations and privacy concerns. Cloud, however, is the destination for innovation. Moving to cloud allows enterprise customers to take advantage of the latest product features, guaranteed availability, global reach and scalability while reducing their operational IT footprint.

Sharing emotion-driven narratives that resonate with other people is something humans are quite good at. We've been sitting around campfires telling stories for tens of thousands of years, and we still do it. One reason why is because it's an effective way to communicate: We remember stories. But what makes for good storytelling? Mark Magellan, a writer and designer at IDEO U, puts it this way: "To tell a story that someone will remember, it helps to understand his or her needs. The art of storytelling requires creativity, critical-thinking skills, self-awareness, and empathy."

With seven billion people on the planet, every one of them making choices and having opinions, it may seem odd to say there aren't enough people to make decisions, and that's why we need help from artificial intelligence. The increasing reach, power, and affordability of digital technology means more and more processes can be automated and theoretically made more efficient, producing more of the goods and services we want. But we don't live in a clockwork world where everything, once wound up, happens according to a plan etched on some master cylinder. In the real world, all these technological "servants" need to respond to a changing environment by learning from context and requesting instructions. They need examples and input so they can answer questions like: Should the store order more toothpaste?

It took Magellan's crew three years sailing ships to circumnavigate the earth. Today, at hypersonic speeds of 7,680 MPH, it takes just over three hours to circumnavigate the earth. Data on the Internet, however, travels at 670 million MPH, which means it only takes milliseconds to circumnavigate the earth. In this age of digital businesses and digital interactions, companies must digitally transform to work effectively in a world where mass information moves at these unimaginable speeds. It's not just IT systems that are impacted by the volume and speed of information.