Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then.
We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search.
We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment with these skills in mind. Self-play ensures that the environment is always the right difficulty for an AI to improve.
arXiv:2604. 20209v2 Announce Type: replace Abstract: LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve together.
We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3. 4-month doubling time (by comparison, Moore’s Law had a 2-year doubling period)[^footnote-correction].
AREX-2 is a new approach that enhances the self‑improving ability of large language model agents by combining reflection—producing better solutions—and long‑horizon execution—maintaining effectiveness over many iterations. The method synthesizes improvement trajectories from machine‑learning and algorithmic programming tasks, providing verifiable feedback and sustained iteration. Trained on this data, an agent based on Qwen3.8‑27B achieves strong performance across multiple benchmarks and continues to improve as more iterative rounds are allowed.
arXiv:2604. 02721v2 Announce Type: replace Abstract: Competitive programming remains one of the last few human strongholds in coding against AI.
arXiv:2609.09094v1 Announce Type: new Abstract: Combining search with function approximation has driven major advances in game-playing programs, making self-play algorithms more competitive than ever...
Self-Play Search Distillation (SPSD) is a framework that generates superhuman synthetic data by having MuZero-like networks play board games in executable environments. The search records are converted into structured reasoning chains that serve as environment‑grounded supervision for training large language models. When applied to Qwen3‑4B‑Base, SPSD improves performance on six mathematics benchmarks from 24.1 to 36.6 and raises the win rate on unseen games from 15% to 45%.
arXiv:2502. 08829v2 Announce Type: replace Abstract: Federated learning (FL) with non-IID data often degrades client performance below local training baselines.
arXiv:2510. 23216v4 Announce Type: replace Abstract: While several high profile video games have served as testbeds for Deep Reinforcement Learning (DRL), this technique has rarely been employed by the game industry for crafting authentic AI behaviors.
arXiv:2606. 20210v1 Announce Type: new Abstract: Immersion in video games depends not only on graphics, audio, and game mechanics, but also on the quality of in-game characters.