-
An Overview of Classic RL Paradigms Liao Jiayi #AI#LLM#Agent As foundation models scale in data and parameter count, the barrier to entry keeps rising, making pretraining increasingly difficult to participate in. Alignment for different scenarios and applications in post-training is becoming ever more important.
-
Personal Agents and Memory Liao Jiayi #AI#LLM#Agent A survey of Agent Memory techniques and industry practice—from external memory and in-model state to parameter updates—and how memory can make agents intelligent and personalized.