DontSayIt

Description

DontSayIt is an ORS environment for evaluating agents on playing Don't Say It, a conversational deception game where players try to make opponents say secret words, against an LLM opponent. This environment wraps the DontSayIt implementation from TextArena, a framework for text-based game environments.

Capabilities

• Natural language conversation generation
• Strategic topic steering and manipulation
• Deceptive reasoning to avoid revealing secret words
• Competitive two-player gameplay against an LLM opponent

Compute Requirements

DontSayIt 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:

• DontSayIt-v0
• DontSayIt-v0-hardcore
• DontSayIt-v0-hardcore-raw
• DontSayIt-v0-hardcore-train
• DontSayIt-v0-raw
• DontSayIt-v0-train
• DontSayIt-v0-unlimited
• DontSayIt-v0-unlimited-raw
• DontSayIt-v0-unlimited-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 a single tool:

• send_message(message): Send a conversational message to the other player.

Time Horizon

DontSayIt is a multi-turn environment.

Environment Difficulty

Hard

Other Environment Requirements

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

Safety

Agents in DontSayIt interact only with a conversational 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}
}