Three-dimensional integrated circuits (3D ICs) have emerged as a promising solution to the scaling limits of two-dimensional designs, offering higher integration density, shorter interconnects, and improved performance. As design complexity increases, effective space planning becomes essential to reduce dead space and ensure layout quality. This study investigates the use of large language models (LLMs) for 3D IC space planning through a post-order slicing tree representation, which guarantees legal space plans while aiming to minimize dead space. Open-source LLMs were fine-tuned on large-scale synthetic datasets and further evaluated on MCNC-derived 3D benchmarks. Experimental results indicate that the proposed framework achieves a favorable balance between runtime efficiency, legality, and dead-space reduction, with zero-dead-space layouts obtained in a significant portion of test cases under practical runtime budgets. Beyond synthetic benchmarks, the method generalizes to MCNC cases such as ami33 and ami49, though larger and irregular instances remain challenging. The approach also shows potential for cross-domain applications, including logistics and 3D object placement, where spatial efficiency is critical. Overall, the results suggest that LLM-based space planning can serve as a data-driven complement to traditional electronic design automation (EDA) methods, providing new insights for scalable 3D layout generation.

Analog integrated circuit (IC) floorplanning is typically a manual process with the placement of components (devices and modules) planned by a layout engineer. This process is further complicated by the interdependence of floorplanning and routing steps, numerous electric and layout-dependent constraints, as well as the high level of customization expected in analog design. This paper presents a novel automatic floorplanning algorithm based on reinforcement learning. It is augmented by a relational graph convolutional neural network model for encoding circuit features and positional constraints. The combination of these two machine learning methods enables knowledge transfer across different circuit designs with distinct topologies and constraints, increasing the \emph{generalization ability} of the solution. Applied to $6$ industrial circuits, our approach surpassed established floorplanning techniques in terms of speed, area and half-perimeter wire length. When integrated into a \emph{procedural generator} for layout completion, overall layout time was reduced by $67.3\%$ with a $8.3\%$ mean area reduction compared to manual layout.

It's been a terrible year for game developers, but an amazing year for games. There were some missteps along the way -- if you'd asked me to predict this list a year ago, I would've mentioned both Redfall and Starfield -- but overall it's been a packed year unusually low on disappointment. We've never tried to name a single title as "the Game of the Year." Instead, it's become a tradition to get the whole team together to talk about our individual favorites. So here are those games, presented in alphabetical order to avoid hurting any of our writers' feelings. Feel free to sound off about what your favorites are in the comments; there are no wrong answers. I rarely have time to finish games these days, but I devoured Alan Wake 2 in just a few weeks. For me and my limited gaming time, that felt miraculous. I'll admit, I'm a mark for Remedy Entertainment. I've been following its work since the first Max Payne arrived on PCs in 2001, right as I was gearing up to head to college and building my first desktop PC. Yah, I was one of the cool kids on campus..) Max Payne blew me away with its fluid slow-motion gunplay mechanics and immersive narrative. As a lifelong console gamer until then, it was a big step forward from something like Tomb Raider.

Leaf through the history of independent video games and the pages are drenched in horror. It was there in the 1990s shareware era of Doom and Hugo's House of Horrors. It was there too in the Flash games of the early 2000s: Exmortis, the House series, the now lost Hotel 626. And it is here now, in the modern indie age. Lone coders and small development studios have always explored dark stories in haunted houses, lonely forests and seemingly abandoned spacecraft populated by demonic entities.

Going from research to production, especially for large and complex software systems, is fundamentally a hard problem. In large-scale game production, one of the main reasons is that the development environment can be very different from the final product. In this technical paper we describe an effort to add an experimental reinforcement learning system to an existing automated game testing solution based on scripted bots in order to increase its capacity. We report on how this reinforcement learning system was integrated with the aim to increase test coverage similar to [1] in a set of AAA games including Battlefield 2042 and Dead Space (2023). The aim of this technical paper is to show a use-case of leveraging reinforcement learning in game production and cover some of the largest time sinks anyone who wants to make the same journey for their game may encounter. Furthermore, to help the game industry to adopt this technology faster, we propose a few research directions that we believe will be valuable and necessary for making machine learning, and especially reinforcement learning, an effective tool in game production.

Originally released in 2008, Dead Space was EA's sci-fi riff on 2005's Resident Evil 4. It took the revolutionary design ideas of Shinji Mikami's horror masterpiece – the over-the-shoulder perspective, tense crowd-control combat and zombies that weren't really zombies – and launched them into a far-flung corner of the cosmos, switching virus-infected villagers for mutant alien necromorphs. The results were darkly thrilling, but couldn't fully escape the light of Resi 4's incandescent star. Fifteen years down the line, with so much more distance from Mikami's game, Dead Space is easier to appreciate on its own merits. This overhaul, from EA studio Motive, is a surprisingly restrained affair, resisting the temptation to supplement the game with modern adornments. Instead it streamlines the experience, altering the layout of doomed spaceship the USG Ishimura so that players may pass through it and its many horrors more smoothly. It's a remake that embraces the original's taut pacing and powerful forward-momentum, and is all the better for it.

Two beloved games from the past have been rereleased in the last week: 2008's nauseating sci-fi horror Dead Space has been resurrected with modern technology, and 1997's first-person-shooter gamechanger GoldenEye 007 (pictured above) has arrived on Nintendo Switch and Xbox, looking somewhat less fresh. Dead Space (pictured below) was not my thing – I'm too sensitive for horror (I sometimes cry at adverts). But GoldenEye 007 brings back a host of great memories for me, as it does for anyone who was playing games during the Nintendo 64 era. Try to find a millennial who doesn't have fond recollections of gathering at that one friend's house after school for split-screen death matches, or a Gen Xer who didn't nearly miss a university essay deadline because of it. My first thought, whenever a game such as this arrives anew, is always: what if it's terrible now?

In the split second before a necromorph slides its arm blades into Isaac Clarke's stomach, it looks like the massive monster is giving him a bloody, snarling, over-excited hug. This precise moment, frozen between horrific brutality and a comforting embrace, captures the essence of the Dead Space remake. As a fan of the 2008 game, playing the new Dead Space is a cozy experience, even amid all the terror, death and gore. The Dead Space remake is big, beautiful and better than the original, while maintaining the magic that made the first game an instant classic. Turns out, great game design is timeless.

The unfortunate Jacob Lee, The Callisto Protocol protagonist beset by the game's countless horrors. The unfortunate Jacob Lee, The Callisto Protocol protagonist beset by the game's countless horrors. Terrifying and brilliantly immersive, it showed how much a game could get us to tense up and squirm in our seats. Now, Dead Space's director, Glen Schofield, is back with The Callisto Protocol. He and his new studio took what worked for that classic and cranked it up to 11. "I asked them what type of game they were trying to create," says The Boys star Karen Fukuhara, who plays central character Dani Nakamura in the game.

The absence of the E3 expo in Los Angeles for the past two years has left a gigantic vacuum in the video game calendar. Last week, the industry did its best to fill that gaping content maw with three online events – the Summer Game fest, the Xbox and Bethesda showcase and the PC gaming show. They were underwhelming for many seasoned players. Major reveals included a remake of The Last of Us, a remake of Call of Duty: Modern Warfare II, Street Fighter 6, Final Fantasy XVI and news about the reimagining of the classic role-player System Shock. Even fresh titles seemed familiar.