PuzzleJAX: A Benchmark for Reasoning and Learning

arXiv:2508.16821 · cs.AI, cs.LG · Submitted 2025-08-22 · Read on arXiv

cs.AI, cs.LG

Submitted: 2025-08-22

Updated: 2026-10-06

Code: https://github.com/smearle/script-doctor

Project page: https://auroriax.github.io/PuzzleScript

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Domain-Specific Language (DSL) — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• TALES: Text Adventure Learning Environment Suite
• GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps
• Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction
• Dota 2 with Large Scale Deep Reinforcement Learning
• Playing Atari with Deep Reinforcement Learning
• Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning
• Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks
• Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
• Benchmarking the Spectrum of Agent Capabilities
• Open-Ended Learning Leads to Generally Capable Agents
• SmartPlay: A Benchmark for LLMs as Intelligent Agents
• DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments
• GAVEL: Generating Games Via Evolution and Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems