# TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval

arXiv: https://arxiv.org/abs/2607.28498 · HTML: https://mlsanity.com/paper/2607.28498/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition](https://mlsanity.com/paper/2503.21248/) (2025)
- [Accelerating Innovation Through Analogy Mining](https://mlsanity.com/paper/1706.05585/) (2017)
- [RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems](https://mlsanity.com/paper/2510.02263/) (2025)
- [LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research](https://mlsanity.com/paper/2412.14141/) (2024)
- [Abstraction-of-Thought Makes Language Models Better Reasoners](https://mlsanity.com/paper/2406.12442/) (2024)
- [Automating Exploratory Proteomics Research via Language Models](https://mlsanity.com/paper/2411.03743/) (2024)
- [MIR: Methodology Inspiration Retrieval for Scientific Research Problems](https://mlsanity.com/paper/2506.00249/) (2025)
- [Towards Autonomous Hypothesis Verification via Language Models with Minimal Guidance](https://mlsanity.com/paper/2311.09706/) (2023)
- [CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation](https://mlsanity.com/paper/2505.20779/) (2025)
- [Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration](https://mlsanity.com/paper/2603.12226/) (2026)

## Built on by (most cited first, 1 of 1)

- [IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation](https://mlsanity.com/paper/2610.04074/) (2026)

## Abstract (arXiv)

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.