Who cares about kids when adult collectors are willing to pay top dollar? From the moment a pixelated Gengar and Nidorino faced off in the opening animation of the first games on the original Game Boy back in 1996, the franchise has been a perennial favorite of kids and adults alike. With 2026 marking 30th anniversary, Lego's first-ever collaboration with the enduringly popular monster-catching megahit is perfectly timed--a crossover of pop culture titans with just one problem: Anyone who isn't an ultra-fan with cavernously deep pockets isn't invited. The recent announcement of a line of Lego Pokémon wasn't a surprise--the Danish brick brand first revealed it had entered into a "multi-year partnership" with The Pokémon Company back in March 2025 --but the makeup of the range itself was. Despite the mass appeal, Lego is launching with just three sets, and every single one is age-rated 18+.

Why the World's Best AI Systems Are Still So Bad at Pokémon Pillay is an editorial fellow at TIME. Pillay is an editorial fellow at TIME. Right now, live on Twitch, you can watch three of the world's smartest AI systems-- GPT 5.2, Claude Opus 4.5, and Gemini 3 Pro --doing their best to beat classic Pokémon games. At least by human standards, they are not very good. The systems are slow, overconfident, and often confused.

Competitive Pokémon Singles (CPS) is a popular strategy game where players learn to exploit their opponent based on imperfect information in battles that can last more than one hundred stochastic turns. AI research in CPS has been led by heuristic tree search and online self-play, but the game may also create a platform to study adaptive policies trained offline on large datasets. We develop a pipeline to reconstruct the first-person perspective of an agent from logs saved from the third-person perspective of a spectator, thereby unlocking a dataset of real human battles spanning more than a decade that grows larger every day. This dataset enables a black-box approach where we train large sequence models to adapt to their opponent based solely on their input trajectory while selecting moves without explicit search of any kind. We study a progression from imitation learning to offline RL and offline fine-tuning on self-play data in the hardcore competitive setting of Pokémon's four oldest (and most partially observed) game generations. The resulting agents outperform a recent LLM Agent approach and a strong heuristic search engine. While playing anonymously in online battles against humans, our best agents climb to rankings inside the top 10% of active players. All agent checkpoints, training details, datasets, and baselines are available at https://metamon.tech.

We introduce Pok\'eChamp, a minimax agent powered by Large Language Models (LLMs) for Pok\'emon battles. Built on a general framework for two-player competitive games, Pok\'eChamp leverages the generalist capabilities of LLMs to enhance minimax tree search. Specifically, LLMs replace three key modules: (1) player action sampling, (2) opponent modeling, and (3) value function estimation, enabling the agent to effectively utilize gameplay history and human knowledge to reduce the search space and address partial observability. Notably, our framework requires no additional LLM training. We evaluate Pok\'eChamp in the popular Gen 9 OU format. When powered by GPT-4o, it achieves a win rate of 76% against the best existing LLM-based bot and 84% against the strongest rule-based bot, demonstrating its superior performance. Even with an open-source 8-billion-parameter Llama 3.1 model, Pok\'eChamp consistently outperforms the previous best LLM-based bot, Pok\'ellmon powered by GPT-4o, with a 64% win rate. Pok\'eChamp attains a projected Elo of 1300-1500 on the Pok\'emon Showdown online ladder, placing it among the top 30%-10% of human players. In addition, this work compiles the largest real-player Pok\'emon battle dataset, featuring over 3 million games, including more than 500k high-Elo matches. Based on this dataset, we establish a series of battle benchmarks and puzzles to evaluate specific battling skills. We further provide key updates to the local game engine. We hope this work fosters further research that leverage Pok\'emon battle as benchmark to integrate LLM technologies with game-theoretic algorithms addressing general multiagent problems. Videos, code, and dataset available at https://sites.google.com/view/pokechamp-llm.

A metagame is a collection of knowledge that goes beyond the rules of a game. In competitive, team-based games like Pok\'emon or League of Legends, it refers to the set of current dominant characters and/or strategies within the player base. Developer changes to the balance of the game can have drastic and unforeseen consequences on these sets of meta characters. A framework for predicting the impact of balance changes could aid developers in making more informed balance decisions. In this paper we present such a Meta Discovery framework, leveraging Reinforcement Learning for automated testing of balance changes. Our results demonstrate the ability to predict the outcome of balance changes in Pok\'emon Showdown, a collection of competitive Pok\'emon tiers, with high accuracy.

Role-playing games (RPGs) provide players with a rich, interactive world to explore. Dialogue serves as the primary means of communication between developers and players, manifesting in various forms such as guides, NPC interactions, and storytelling. While most games rely on written scripts to define the main story and character personalities, player immersion can be significantly enhanced through casual interactions between characters. With the advent of large language models (LLMs), we introduce a dialogue filler framework that utilizes LLMs enhanced by knowledge graphs to generate dynamic and contextually appropriate character interactions. We test this framework within the environments of Final Fantasy VII Remake and Pokemon, providing qualitative and quantitative evidence that demonstrates GPT-4's capability to act with defined personalities and generate dialogue. However, some flaws remain, such as GPT-4 being overly positive or more subtle personalities, such as maturity, tend to be of lower quality compared to more overt traits like timidity. This study aims to assist developers in crafting more nuanced filler dialogues, thereby enriching player immersion and enhancing the overall RPG experience.

The biggest story of the year so far in games has been Palworld, the "Pokémon-with-guns" early access game that broke and rebroke concurrent player records on PC. It's showing a few signs of being unsustainable, as those player numbers have dropped off in recent weeks and the developers reveal the eye-watering cost of keeping servers online for so many people (almost 6m a year), but it's still in with a shot of being 2024's biggest game in terms of pure revenue. There's something a little unsavoury about Palworld that has other developers and critics wrinkling their noses. It's not just the ick of turning guns on creatures that are, unlike Minecraft's blocky animals, designed to look cute. Its character designs are so close to Pokémon's that it has sparked allegations of plagiarism, with some 3D models of the game's creatures aligning improbably closely with those from recent Pokémon games.

We introduce \textsc{Pok\'eLLMon}, the first LLM-embodied agent that achieves human-parity performance in tactical battle games, as demonstrated in Pok\'emon battles. The design of \textsc{Pok\'eLLMon} incorporates three key strategies: (i) In-context reinforcement learning that instantly consumes text-based feedback derived from battles to iteratively refine the policy; (ii) Knowledge-augmented generation that retrieves external knowledge to counteract hallucination and enables the agent to act timely and properly; (iii) Consistent action generation to mitigate the \textit{panic switching} phenomenon when the agent faces a powerful opponent and wants to elude the battle. We show that online battles against human demonstrates \textsc{Pok\'eLLMon}'s human-like battle strategies and just-in-time decision making, achieving 49\% of win rate in the Ladder competitions and 56\% of win rate in the invited battles. Our implementation and playable battle logs are available at: \url{https://github.com/git-disl/PokeLLMon}.

The first thing you need to know about Palworld, a new video game developed and published by the Japanese studio Pocketpair, is that it is ludicrously popular. According to data scraped from Steam, a digital storefront for PC games, Palworld became the second game ever after 2017's PlayerUnknown's Battlegrounds to breach 2 million concurrent players last week. Palworld arrived on Jan. 19, so that growth laps some of the most commercially solvent franchises in the industry--the server concentrations of Counter-Strike and Grand Theft Auto V can eat their hearts out. All this is to say that Pocketpair has a genuine phenomenon on its hands: Palworld, much like Fortnite or Minecraft before it, is poised to dominate the corridors of elementary schools for the rest of 2024, for better or worse. This is unfortunate news for me, and, really, anyone else who cares about the virtues of interactive entertainment, because Palworld's appeal is totally inscrutable.

The new year has barely begun but it seems we already have 2024's biggest game – and it's not a multi-million dollar sci-fi extravaganza set in a vast universe created by a gigantic publisher. It's a survival adventure released by a small company in Japan, which had only previously released one game. It's called Palworld, and it's being accurately described as "Pokémon with guns". And if that sounds horrible to you, it seems you are very much alone. Within three days of its release on 18 January, it had sold 5m copies.