A source-linked collection of theoretical open problems. Explore challenges in AI safety, learning theory, transformers, world models, optimization, memory and inference. Each entry gives a precise research target, assumptions and known progress. Open status is provisional; broader programs explicitly need a framework. Sources & methodology ↗
Aggressive or persistent updates can keep cycling yet learn efficiently in self-play. This problem asks whether shrinking the learning rate is unnecessary throughout a concrete higher-dimensional game family. Efficiency payoff: Keep a productive fixed update scale in coupled learning when diminishing steps are unnecessary.
Passing hidden states can save decoding work, but successful communication requires the receiver to interpret the sender's representation and preserve information relevant to its own task. Efficiency payoff: Save decode/prefill work while paying for alignment, adapter training and message bandwidth.
An agent team needs enough communication to avoid redundant or conflicting work, but dense graphs are costly and links can fail. A fixed game model turns topology choice into a measurable efficiency question. Efficiency payoff: Reduce communication links while retaining a coordination guarantee under failures.
Agents may contribute too little or duplicate work because of incentives and incomplete knowledge. This model makes the cost of coordinating them through information a precise worst-case quantity.
One model can create useful starting points while another refines them well. Their relative benefit depends on the node and the remaining budget, not only on global average score. Efficiency payoff: Allocate cheaper and more capable models by marginal search value per paid resource, including context growth and evaluation cost.