RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution
This work addresses the challenge of automating retrieval algorithm design for information retrieval practitioners, offering a novel approach that could reduce reliance on human intuition and parameter tuning.
The paper tackled the problem of improving lexical retrieval algorithms by using a large language model with evolutionary search to automatically discover new algorithms, achieving promising transfer performance across multiple IR benchmarks including BEIR, BRIGHT, and TREC DL.
Retrieval algorithms like BM25 and query likelihood with Dirichlet smoothing remain strong and efficient first-stage rankers, yet improvements have mostly relied on parameter tuning and human intuition. We investigate whether a large language model, guided by an evaluator and evolutionary search, can automatically discover improved lexical retrieval algorithms. We introduce RankEvolve, a program evolution setup based on AlphaEvolve, in which candidate ranking algorithms are represented as executable code and iteratively mutated, recombined, and selected based on retrieval performance across 12 IR datasets from BEIR and BRIGHT. RankEvolve starts from two seed programs: BM25 and query likelihood with Dirichlet smoothing. The evolved algorithms are novel, effective, and show promising transfer to the full BEIR and BRIGHT benchmarks as well as TREC DL 19 and 20. Our results suggest that evaluator-guided LLM program evolution is a practical path towards automatic discovery of novel ranking algorithms.