Less is More: Benchmarking LLM Based Recommendation Agents
We benchmark LLM-based recommendation agents and show that minimal context achieves similar recommendation quality to large context windows, with significant cost savings across …
An example preprint / working paper
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.