RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908840487813120 |
|---|---|
| author | Nian, Jinming Li, Fangchen Park, Dae Hoon Fang, Yi |
| author_facet | Nian, Jinming Li, Fangchen Park, Dae Hoon Fang, Yi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16932 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution Nian, Jinming Li, Fangchen Park, Dae Hoon Fang, Yi Information Retrieval Artificial Intelligence 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. |
| title | RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2602.16932 |