lechmazur/step_game

Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a move (1, 3, or 5 steps). Whenever two or more players choose the same number, all colliding players fail to advance.

7 best points · 1 comments · 2 Hacker News posts · 93 GitHub stars · View on GitHub

Hacker News discussions

• Multi-Agent Step Race Benchmark: LLM Collaboration and Deception Under Pressure (7 points, 1 comments, by zone411, 2025-01-22)
• Step-Game: Assessing LLM Collaboration and Deception Under Pressure (2 points, 0 comments, by amichail, 2025-02-03)