The Token Games: Evaluating Language Model Reasoning with Puzzle Duels
cs.AI
Submitted: 2026-02-19
Updated: 2026-10-12
Project page: https://token-games.ai
Terminology
Sources
- Copilot Arena: A Platform for Code LLM Evaluation in the Wild
- ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
- FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
- OpenAI o1 System Card
- PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- Humanity's Last Exam
- TextQuests: How Good are LLMs at Text-Based Video Games?
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- SmartPlay: A Benchmark for LLMs as Intelligent Agents
- Absolute Zero: Reinforced Self-play Reasoning with Zero Data
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