Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting

The paper introduces DeepEvolve, an agent system grounded in future event prediction that interacts with a dynamically evolving environment to improve from its own experience, a capacity it calls recursive self-improvement. A living environment synthesizes verifiable tasks, and a recursive-evolution engine converts prediction reasoning trajectories into capability via parameter-level learning and reusable skill distillation. The authors report that their self-improved forecaster ranked first on the weekly-updated FutureX leaderboard for three consecutive weeks, with up to a 195% rating improvement, and ranked among the top three across four base LLMs on their own synthesized evaluation.

Why it matters

It proposes a path for AI systems to keep improving after deployment without external retraining, and addresses information leakage in open-world evaluation.

Read with care

Source claims not independently checked; results rely partly on the authors' own synthesized evaluation.