Tag
该论文提出 ActLim-Bench，利用前向引用构建可操作的论文局限性生成监督数据，并设计三阶段后训练流程（SFT、验证器过滤拒绝采样、在线稠密奖励 RL），在前沿模型上取得最佳召回率并提升下游自动研究构思系统。
This comment highlights survivorship bias in evaluating LLM-generated research ideas against published human baselines, suggesting that the observed human–LLM gap may be due to selective publication rather than inherent LLM limitations.
IDEAgent introduces a multi-agent framework that treats research ideation as a Quality-Diversity search, jointly optimizing idea quality and diversity through lineage evolution, outperforming baselines by 3.89x on a novel joint metric.
ResearchStudio-Idea is a skill suite that combines literature search, novelty checking, and pattern-guided generation to produce traceable research proposals, built from analysis of 1,947 machine learning conference papers.