Shuang Yang

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance across diverse tasks.

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving token efficiency.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.