amortized-optimization

Codebook Agent introduces a vector-quantized autoencoder method to design query-adaptive communication topologies for LLM multi-agent systems, improving accuracy and reducing token consumption on multiple benchmarks.

This paper proposes CC-AOS, a structured amortized solver for finite-horizon optimal stopping problems that handles varying costs and horizons without retraining. It incorporates theoretical properties into the model architecture and demonstrates improved performance on benchmark tasks.