EvoX: Meta-Evolution for Automated Discovery
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910054525960192 |
|---|---|
| author | Liu, Shu Agarwal, Shubham Maheswaran, Monishwaran Cemri, Mert Li, Zhifei Mang, Qiuyang Naren, Ashwin Boneh, Ethan Cheng, Audrey Pan, Melissa Z. Du, Alexander Keutzer, Kurt Cheung, Alvin Dimakis, Alexandros G. Sen, Koushik Zaharia, Matei Stoica, Ion |
| author_facet | Liu, Shu Agarwal, Shubham Maheswaran, Monishwaran Cemri, Mert Li, Zhifei Mang, Qiuyang Naren, Ashwin Boneh, Ethan Cheng, Audrey Pan, Melissa Z. Du, Alexander Keutzer, Kurt Cheung, Alvin Dimakis, Alexandros G. Sen, Koushik Zaharia, Matei Stoica, Ion |
| contents | Recent work such as AlphaEvolve has shown that combining LLM-driven optimization with evolutionary search can effectively improve programs, prompts, and algorithms across domains. In this paradigm, previously evaluated solutions are reused to guide the model toward new candidate solutions. Crucially, the effectiveness of this evolution process depends on the search strategy: how prior solutions are selected and varied to generate new candidates. However, most existing methods rely on fixed search strategies with predefined knobs (e.g., explore-exploit ratios) that remain static throughout execution. While effective in some settings, these approaches often fail to adapt across tasks, or even within the same task as the search space changes over time. We introduce EvoX, an adaptive evolution method that optimizes its own evolution process. EvoX jointly evolves candidate solutions and the search strategies used to generate them, continuously updating how prior solutions are selected and varied based on progress. This enables the system to dynamically shift between different search strategies during the optimization process. Across nearly 200 real-world optimization tasks, EvoX outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23413 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EvoX: Meta-Evolution for Automated Discovery Liu, Shu Agarwal, Shubham Maheswaran, Monishwaran Cemri, Mert Li, Zhifei Mang, Qiuyang Naren, Ashwin Boneh, Ethan Cheng, Audrey Pan, Melissa Z. Du, Alexander Keutzer, Kurt Cheung, Alvin Dimakis, Alexandros G. Sen, Koushik Zaharia, Matei Stoica, Ion Machine Learning Computation and Language Neural and Evolutionary Computing Recent work such as AlphaEvolve has shown that combining LLM-driven optimization with evolutionary search can effectively improve programs, prompts, and algorithms across domains. In this paradigm, previously evaluated solutions are reused to guide the model toward new candidate solutions. Crucially, the effectiveness of this evolution process depends on the search strategy: how prior solutions are selected and varied to generate new candidates. However, most existing methods rely on fixed search strategies with predefined knobs (e.g., explore-exploit ratios) that remain static throughout execution. While effective in some settings, these approaches often fail to adapt across tasks, or even within the same task as the search space changes over time. We introduce EvoX, an adaptive evolution method that optimizes its own evolution process. EvoX jointly evolves candidate solutions and the search strategies used to generate them, continuously updating how prior solutions are selected and varied based on progress. This enables the system to dynamically shift between different search strategies during the optimization process. Across nearly 200 real-world optimization tasks, EvoX outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks. |
| title | EvoX: Meta-Evolution for Automated Discovery |
| topic | Machine Learning Computation and Language Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2602.23413 |