Skip to content
NewA calmer, faster ZeroHour

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

Hugging Face daily papersby Young-Jun Lee, Jinheon Baek, Soyeong Jeong ()1 min read3 · 1 read
AI summary · grok-4.7Summaries by Vani AI

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.

Key facts
  • 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
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Evolutionary 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.

Hugging Face daily papers

By Young-Jun Lee, Jinheon Baek, Soyeong Jeong · huggingface.co

Read the full article at Hugging Face daily papers

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.