NewRecruit

Description

NewRecruit is an environment for evaluating agents on negotiation skills in a recruitment scenario where the recruiter and candidate must agree on 8 issues: salary, signing bonus, job assignment, company car, starting date, vacation days, moving expense reimbursement, and insurance coverage. This environment wraps the NewRecruit implementation from TextArena, a framework for text-based game environments.

Capabilities

• Testing multi-issue negotiation strategy
• Evaluating persuasion and compromise skills
• Assessing information gathering and preference elicitation
• Testing goal-oriented communication to maximize point outcomes

Compute Requirements

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

License

MIT.

Tasks

There are two splits: train (150 tasks) and test (150 tasks). Each split contains 50 tasks across each of 3 variants:

• NewRecruit-v0
• NewRecruit-v0-train
• NewRecruit-v0-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 negotiate. Use [Propose] followed by 8 letters A-E (one per issue) for proposals, [Accept] to accept, or [Reject] to reject.

Time Horizon

NewRecruit is a multi-turn environment.

Environment Difficulty

Medium. Successful negotiation requires understanding hidden point values, balancing multiple issues, making strategic concessions, and reading opponent preferences to reach mutually beneficial agreements.

Other Environment Requirements

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

Safety

Agents in NewRecruit interact only with a negotiation 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}
}