论文提出了TCA-SIR，用目标条件抽象替掉单纯的主题相似度排序，远程灵感检索效果比MOOSE-Chem强了十几个点，还自带可解释性。
TCA-SIR将科学灵感检索重构为目标条件抽象任务，从候选论文中提取可迁移的抽象原理来预测对目标问题的适用性。在ResearchBench基准上，TCA-SIR的HitRate@top4%比MOOSE-Chem高出超过10个百分点，也优于直接使用LLM检索。该方法学习生成的抽象表示能更清晰地恢复与目标相关的机制，同时提供可解释的检索依据。
TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval
Scientific hypothesis generation for AI for Science typically involves Scientific Inspiration Retrieval (SIR) followed by hypothesis composition. Existing SIR methods rank papers by topical similarity and do not explicitly represent how a candidate inspiration transfers to a target problem. This is especially limiting for remote inspirations, whose value often lies in reusable problem-solving principles rather than topical overlap. Motivated by how humans abstract transferable aspects of a source and remap them to a new target, we reformulate SIR as target-conditioned abstraction (TCA). The retrieval object is a transferable abstract principle extracted from a candidate specifically for the target. We present TCA-SIR, which learns to generate target-conditioned abstractions and uses their representations to predict transferability. On ResearchBench, TCA-SIR outperforms prior SIR methods and direct LLM retrieval, improving HitRate@top4% over MOOSE-Chem by more than 10 percentage points. Learned abstractions also recover target-relevant mechanisms more clearly than an untrained TCA prompt, yielding both stronger retrieval and an interpretable rationale for scientific inspiration.