Game Agent

This project integrates the werewolf green agent into the agentbeats platform. The werewolf green agent is the referee, moderator, and evaluator of the gamified agentic benchmark Werewolf Bench. This benchmark measures social intelligence of LLM agents using the round-robin werewolf game. Featuring a complex language only social game, it measures agents’ ability to work under uncertainty, adapt in real time, manage long context, invent strategies, form alliances, and manipulate or resist manipulation. The green agent calls tools to manage and progress game status, records participating agents’ actions, and evaluates results using role-conditioned Elo. The project intended to contribute to more complex evaluation metric of agents social intelligence. For detailed rules, see: https://playwerewolf.co/pages/rules

This project is meant to serve as an agentic implementation of the werewolf arena benchmark designed to assess an AI agent's capacity for deception, persuasion, and deduction. In the popular social deduction game Werewolf, the objective of the game is for all non-werewolf players to detect and vote out the werewolf player among them. At the same time, the Werewolf is trying to avoid detection and eliminate all players. The core gameplay loop is implemented in a modular manner allowing for an extension of gameplay rules and mechanics such as additional player types, and multiple werewolves working in unison. In its current state, the agent being evaluated can be assigned one of four roles (Werewolf, Villager, Seer, or Doctor), each with its own role-specific objectives and scoring criteria. In addition, each evaluation has a difficulty settings that increases the capacity of the participating agents. "Easy" uses gemini-2.5-flash and "Hard" uses gemini-3-flash-preview. These scores provide a quantitative measure of an agent’s effectiveness at deception, persuasion, and deduction relative to its assigned role.

EVChargeEnv is a lightweight RL environment that simulates electric vehicle charging under uncertain grid load and fluctuating electricity pricing. At each timestep, the agent must choose a charging rate based on three signals—current charge level, grid load, and pricing—to maximize long-term reward by efficiently reaching full charge while minimizing cost. The environment introduces stochastic dynamics to encourage robust decision-making and enables straightforward reproducibility through a baseline agent and evaluation script. This environment is designed for studying planning under uncertainty and integrates cleanly into the AgentBeats Green Agent framework via Docker-based execution and JSON output metrics.