Can LLMs predict future observations in multi-agent event worlds?
What happened
LLMs try to predict future observations in multi-agent event worlds
AI-written from the coverage · updated 2026-10-23
Coverage timeline
Follow the coverage to see the story from different sides.
- arXiv Game World Models & GenerationPickCan LLMs serve as event world models? A study from single-actor environments to multi-actor event worlds
A paper asks whether large language models can predict future observations from event logs and the actions an agent plans to take, using benchmarks built from human Diplomacy games and real Polymarket trades. When only the agent's own actions are given and other actors strongly shape outcomes, model predictions fall well short, and larger models and longer histories help only modestly. When the recorded actions of all actors are provided, fine-tuning and more data improve predictions, but models still overestimate the success rate of planned actions, while imagined experience from world models still improves policy learning.