Among LLMs
Among LLMs is a game-like OpenEnv benchmark where attacker, defender, and overseer agents interact in sabotage-style workplace tasks.
Core trick
Attacker, defender, and overseer agents play sabotage-style workplace episodes with replayable seeds, and failed rollouts are archived to harden later curricula.
Description
Among LLMs is a game-like OpenEnv benchmark where attacker, defender, and overseer agents interact in sabotage-style workplace tasks.
It starts with deterministic, replayable episodes and reward signals, then scales into self-evolving multi-agent curricula through mutation, archival failures, and harder rollouts.
The goal is to train robust oversight that detects manipulation, localizes root causes, and improves continuously via self-play-style adaptation