The PokeAgent Challenge: Competitive and Long-Context Learning at Scale

TL;DR

The PokeAgent Challenge introduces a large-scale Pokemon-based benchmark for decision-making research, addressing partial observability, game-theoretic reasoning, and long-horizon planning through two tracks, fostering advancements in AI capabilities.

Contribution

It presents the first comprehensive Pokemon-based benchmark with extensive datasets, standardized evaluation frameworks, and a NeurIPS 2025 competition to advance AI research in complex, realistic environments.

Findings

Over 100 teams participated, showing significant gaps between AI and human performance.

Pokemon battling capabilities are orthogonal to existing LLM benchmarks.

The benchmark reveals new AI challenges in partial observability and long-horizon planning.

Abstract

We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environment. Partial observability, game-theoretic reasoning, and long-horizon planning remain open problems for frontier AI, yet few benchmarks stress all three simultaneously under realistic conditions. PokeAgent targets these limitations at scale through two complementary tracks: our Battling Track, which calls for strategic reasoning and generalization under partial observability in competitive Pokemon battles, and our Speedrunning Track, which requires long-horizon planning and sequential decision-making in the Pokemon RPG. Our Battling Track supplies a dataset of 20M+ battle trajectories alongside a suite of heuristic, RL, and LLM-based baselines capable of high-level competitive play. Our Speedrunning Track provides the first standardized evaluation framework for RPG speedrunning, including an open-source multi-agent orchestration system for modular, reproducible comparisons of harness-based LLM approaches. Our NeurIPS 2025 competition validates both the quality of our resources and the research community's interest in Pokemon, with over 100 teams competing across both tracks and winning solutions detailed in our paper. Participant submissions and our baselines reveal considerable gaps between generalist (LLM), specialist (RL), and elite human performance. Analysis against the BenchPress evaluation matrix shows that Pokemon battling is nearly orthogonal to standard LLM benchmarks, measuring capabilities not captured by existing suites and positioning Pokemon as an unsolved benchmark that can drive RL and LLM research forward. We transition to a living benchmark with a live leaderboard for Battling and self-contained evaluation for Speedrunning at https://pokeagentchallenge.com.