Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and find that directly dropping LLMs into games cannot make an effective evaluation, for three reasons -- brittle vision perception, prompt sensitivity, and potential data contamination. We introduce lmgame-Bench to turn games into reliable evaluations. lmgame-Bench features a suite of platformer, puzzle, and narrative games delivered through a unified Gym-style API and paired with lightweight perception and memory scaffolds, and is designed to stabilize prompt variance and remove contamination. Across 13 leading models, we show lmgame-Bench is challenging while still separating models well. Correlation analysis shows that every game probes a unique blend of capabilities often tested in isolation elsewhere. More interestingly, performing reinforcement learning on a single game from lmgame-Bench transfers both to unseen games and to external planning tasks. Our evaluation code is available at https://github.com/lmgame-org/GamingAgent/lmgame-bench.

A Minecraft Movie has reportedly surpassed the record previously set by 2023's The Super Mario Bros. Movie for the biggest ever domestic box office opening of a video game adaptation. The new movie, which was released in theaters on Friday, raked in 157 million in the US in its opening weekend, according to The Hollywood Reporter. A Minecraft Movie is doing well internationally, too; THR reports that it's earned 301M altogether in its global debut. The Super Mario Bros. Movie pulled in 146 million in its domestic opening and 377 million globally. A Minecraft Movie stars Jack Black, Sebastian Hansen, Emma Myers, Jason Momoa, Danielle Brooks and Jennifer Coolidge.

It is a game about love and identity, but it also has forklift truck races. It is a game about bloody revenge, but while you're waiting to retaliate, you can buy lottery tickets and visit the arcade. When Bafta recently asked gamers to vote on the most influential game of all time, I'm not sure even the most ardent Sega fans would have gambled on the success of an idiosyncratic Dreamcast adventure from 1999. Yet the results, released on Thursday morning, show Shenmue at No 1, with perhaps more predictable contenders Doom and Super Mario Bros coming in second and third respectively. How has this happened, especially considering the game was considered a financial failure at the time of its release, falling short of recouping its then staggering development costs (a reported 70m, which would now get you about a third of Horizon Forbidden West or Star Wars Outlaws)?

Nintendo just announced the official release date of the live-action Legend of Zelda movie. It hits theaters on March 26, 2027, which is just about two years from now. The film was first announced back in 2023. The company dropped this bombshell on the official Nintendo Today! app that was surprise-released during a recent Direct livestream. The stream promised that the app would be a constant source of news and information. It looks like that promise was not hyperbole.

This paper introduces the Procedural Content Generation Benchmark for evaluating generative algorithms on different game content creation tasks. The benchmark comes with 12 game-related problems with multiple variants on each problem. Problems vary from creating levels of different kinds to creating rule sets for simple arcade games. Each problem has its own content representation, control parameters, and evaluation metrics for quality, diversity, and controllability. This benchmark is intended as a first step towards a standardized way of comparing generative algorithms. We use the benchmark to score three baseline algorithms: a random generator, an evolution strategy, and a genetic algorithm. Results show that some problems are easier to solve than others, as well as the impact the chosen objective has on quality, diversity, and controllability of the generated artifacts.

In recent years, Artificial Intelligence Generated Content (AIGC) has advanced from textto-image generation to text-to-video and multimodal video synthesis. However, generating playable games presents significant challenges due to the stringent requirements for realtime interaction, high visual quality, and accurate simulation of game mechanics. Existing approaches often fall short, either lacking real-time capabilities or failing to accurately simulate interactive mechanics. To tackle the playability issue, we propose a novel method called PlayGen, which encompasses game data generation, an autoregressive DiT-based diffusion model, and a comprehensive playability-based evaluation framework. Validated on well-known 2D and 3D games, PlayGen achieves real-time interaction, ensures sufficient visual quality, and provides accurate interactive mechanics simulation. Notably, these results are sustained even after over 1000 frames of gameplay on an NVIDIA RTX 2060 GPU. Our code is publicly available: here. Our playable demo generated by AI is: here.

One of Sega's most popular games, Shinobi, will be made into a movie in a joint project with Universal Pictures, the Japanese gamemaker announced Wednesday, aiming to emulate the success of "The Super Mario Bros. Movie." Sega did not give a target date for the release but said it had "started the development of a film production" with the Hollywood behemoth. Shinobi was originally created for Japanese arcades in 1987 and features a ninja character who fights to stop a criminal organization that kidnaps child ninjas. It is the latest effort to cash in on a video-game adaptation craze after "The Super Mario Bros. Movie" became the second-highest grossing film of 2023, following a 2020 adaptation of Sega's "Sonic the Hedgehog." "Shinobi is one of Sega's most popular series worldwide, along with Sonic the Hedgehog," Sega said on Wednesday.

Last month, Google's GameNGen AI model showed that generalized image diffusion techniques can be used to generate a passable, playable version of Doom. Now, researchers are using some similar techniques with a model called MarioVGG to see whether AI can generate plausible video of Super Mario Bros. in response to user inputs. The results of the MarioVGG model--available as a preprint paper published by the crypto-adjacent AI company Virtuals Protocol--still display a lot of apparent glitches, and it's too slow for anything approaching real-time gameplay. But the results show how even a limited model can infer some impressive physics and gameplay dynamics just from studying a bit of video and input data. The researchers hope this represents a first step toward "producing and demonstrating a reliable and controllable video game generator" or possibly even "replacing game development and game engines completely using video generation models" in the future.

Hollywood has really begun flexing its video game adaptation muscle in the wake of the spectacular success of the Fallout TV show and The Super Mario Bros. Movie. Even indie publishers are getting some of those sweet, sweet development contracts. The hit third-person shooter El Paso, Elsewhere is being adapted into a feature length film, as reported by Deadline. Academy Award nominee LaKeith Stanfield is in talks to both star and produce. Stanfield is known for a slew of great films, like Sorry to Bother You, Judas and the Black Messiah and The Book of Clarence, among others.

One of the more amusing TikToks that followed the announcement of the forthcoming Legend of Zelda movie riffs on a scene from the animated series Drawn Together. In it, the blue-caped Captain Hero sits in a wheelchair at the bottom of a staircase next to the text "Zelda fans when the movie was announced." One beat later, the words "it's live action" appear, and Captain Hero screams. Another beat, then "it's produced by Avi Arad (Morbius)" flashes up, this time to a louder scream. Finally, "It was written by the writer of Batman v Superman, Rise of Skywalker, and Jurassic Worlld [sic]," and Captain Hero unleashes one last wounded wail.