EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
EvoDuet co-evolves candidate solutions and web-search queries to improve LLM scientific discovery.
EvoDuet keeps model parameters fixed and co-evolves candidate solutions with web-search queries. A retrieval gate lets the model fetch new documents, reuse stored ones, or proceed without retrieval, while an inner loop ranks documents by predicted solution scores. Across 21 tasks with one candidate per iteration, it raises OpenEvolve's normalized discovery gain from 74.1% to 78.0% with GPT-5.6-Luna and from 61.3% to 82.3% with Gemini-3.8-Flash; Qwen3.5-9B does not benefit. The best runs exceed previously reported best scores on eight tasks, including Swap Reduction on Q20 and Rosetta, and match them on three more.
- Fixed weights; solutions and queries co-evolve each iteration
- Retrieval gate can fetch, reuse, or skip documents
- Gemini-3.8-Flash discovery gain rises from 61.3% to 82.3%
- Qwen3.5-9B does not benefit; eight tasks beat prior bests
- Products
- OpenEvolve
From the original article
1 min read at huggingface.coEvolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents helps, but simply adding web search tool can keep returning the same pages as solutions change. We introduce EvoDuet, a bi-level optimization method that co-evolves solutions and search queries with fixed model parameters.
By Young-Jun Lee, Jinheon Baek, Soyeong Jeong · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.