The World Leaks the Future: Harness Evolution for Future Prediction Agents

ArXi:2604.15719v1 Announce Type: new Many consequential decisions must be made before the relevant outcome is known. Such problems are commonly framed as \emph{future prediction}, where an LLM agent must form a prediction for an unresolved question using only the public information available at the prediction time. The setting is difficult because public evidence evolves while useful supervision arrives only after the question is resolved, so most existing approaches still improve mainly from final outcomes.