RESEARCH · RESEARCH · #1854
EvoBelief: falsifiable world-model paper for self-improving frozen LLM agents (arXiv v1)
EvoBelief is a self-evolving world model that represents environment knowledge as falsifiable hypotheses: unexpected outcomes trigger hypothesis formation and controlled validation before rules are used for prediction or planning while the language model weights remain frozen. Evaluated on ALFWorld, MiniGrid, and DiscoveryWorld Reactor Lab, EvoBelief improves ALFWorld success over a matched Frozen World Model by 23.9% with Claude Haiku 4.5 and 31.3% with GPT-5.4, adapts to hidden dynamics on MiniGrid, and discovers validated quantitative laws in DiscoveryWorld (83.3% Normal-tier, 58.3% Challenge-tier vs 0% for baselines).
KEY POINTS
- EvoBelief is a self-evolving world model that represents environment knowledge as falsifiable hypotheses: unexpected outcomes trigger hypothesis formation and controlled validation before rules are used for prediction or planning while the language model weights remain frozen.
- Evaluated on ALFWorld, MiniGrid, and DiscoveryWorld Reactor Lab, EvoBelief improves ALFWorld success over a matched Frozen World Model by 23.9% with Claude Haiku 4.5 and 31.3% with GPT-5.4, adapts to hidden dynamics on MiniGrid, and discovers validated quantitative laws in DiscoveryWorld (83.3% Normal-tier, 58.3% Challenge-tier vs 0% for baselines).
- Shows a practical alternative for agent self-improvement by accumulating testable, revisable environment rules (instead of model-parameter updates), improving robustness and cross-task rule reuse.
WHY IT MATTERS
Shows a practical alternative for agent self-improvement by accumulating testable, revisable environment rules (instead of model-parameter updates), improving robustness and cross-task rule reuse.