arXiv 2609.40340 · cs.CL · 2026-09-30
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Young-Jun Lee, Jinheon Baek, Soyeong Jeong, Minki Kang, Seungyeon Jwa, Jonghyun Choi, Seungho Han, Dongyeop Kang
Minnesota NLP
在最新榜 #141 本站收录于 2026-10-21
一句话要点
EvoDuet 让解法和搜索查询双层协同进化，帮助大模型进化搜索在需要外部知识时不再停滞。
EvoDuet co-evolves solutions and web-search queries in a bilevel loop so LLM evolutionary search doesn't stall for lack of knowledge.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：AI for Science
- Scaling Parameter-Efficient Fine-Tuning for Brain Encoding ▲237
- Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts ▲103
- PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs ▲65
- From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research ▲53
- Does Learning Protein Folding Generalize to Broader Reasoning? ▲51
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。