Chopsticks

Description

Chopsticks is an ORS environment for evaluating agents on playing Chopsticks, a hand game involving finger arithmetic and strategic redistribution, against an LLM opponent. This environment wraps the Chopsticks implementation from TextArena, a framework for text-based game environments.

Capabilities

• Arithmetic reasoning with modulo-5 finger counting
• Strategic attack and split decision making
• Forward planning to eliminate opponent's hands
• Competitive two-player gameplay against an LLM opponent

Compute Requirements

Chopsticks does not require a sandbox. It has minimal compute requirements.

License

MIT.

Tasks

There are two splits: train (450 tasks) and test (450 tasks). Each split contains 50 tasks across each of 9 variants:

• Chopsticks-v0
• Chopsticks-v0-long
• Chopsticks-v0-long-raw
• Chopsticks-v0-long-train
• Chopsticks-v0-medium
• Chopsticks-v0-medium-raw
• Chopsticks-v0-medium-train
• Chopsticks-v0-raw
• Chopsticks-v0-train

Each task is seeded for reproducibility.

Reward Structure

This is a sparse reward environment. Rewards are mapped from TextArena's native range of {-1, 0, 1} to {0.0, 0.5, 1.0} via (raw + 1) / 2.

We do not use LLM graders for this environment; reward is determined programmatically.

Data

Game state is generated procedurally by the TextArena engine using seeded randomness. No external data files are required.

Tools

Agents are given two tools:

• attack(my_hand, opponent_hand): Attack: tap one of your hands on one of the opponent's hands to add your fingers to theirs. my_hand: 0=left, 1=right. opponent_hand: 0=left, 1=right.
• split(left, right): Split: redistribute your total fingers between your two hands. left and right must sum to your current total.

Time Horizon

Chopsticks is a multi-turn environment.

Environment Difficulty

Easy

Other Environment Requirements

This environment requires an OpenAI API key (passed via secrets) to power the LLM opponent.

Safety

Agents in Chopsticks interact only with a hand game and have no access to external systems, the internet, or sensitive data. The environment does not present safety risks.

Citations

@software{textarena2024,
  author    = {Guertler, Leon and Banting, Wilfried and Pignatelli, Eduardo},
  title     = {TextArena},
  year      = {2024},
  publisher = {GitHub},
  url       = {https://github.com/LeonGuertler/TextArena}
}