CharacterConclave

Description

CharacterConclave is an ORS-based environment for evaluating agents on persuasive communication and impression management in a social competition. This environment wraps the CharacterConclave implementation from TextArena, a framework for text-based game environments.

Capabilities

• Persuasive writing and communication
• Strategic resource allocation (character budget)
• Impression management and self-presentation
• Comparative evaluation of communication quality

Compute Requirements

CharacterConclave 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:

• CharacterConclave-v0
• CharacterConclave-v0-train
• CharacterConclave-v0-raw
• CharacterConclave-v0-long
• CharacterConclave-v0-long-train
• CharacterConclave-v0-long-raw
• CharacterConclave-v0-extreme
• CharacterConclave-v0-extreme-train
• CharacterConclave-v0-extreme-raw

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 message to impress others, or vote for a player with [player_id].

Time Horizon

CharacterConclave is a multi-turn environment.

Environment Difficulty

Medium. Agents must craft impressive messages within a 1000-character budget to win votes from other players. Success requires balancing message quality, quantity, and strategic timing across 3 players.

Other Environment Requirements

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

Safety

Agents in CharacterConclave interact only with a social communication 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}
}