# AI Can Learn Scientific Taste

arXiv: https://arxiv.org/abs/2603.14473 · HTML: https://mlsanity.com/paper/2603.14473/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 77 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 30 of 48)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [MARG: Multi-Agent Review Generation for Scientific Papers](https://mlsanity.com/paper/2401.04259/) (2024)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [The Invisible Leash: Why RLVR May or May Not Escape Its Origin](https://mlsanity.com/paper/2507.14843/) (2025)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning](https://mlsanity.com/paper/2508.20751/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [The Logic of Graph Neural Networks](https://mlsanity.com/paper/2104.14624/) (2021)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)

## Built on by (most cited first, 11 of 11)

- [ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration](https://mlsanity.com/paper/2605.03042/) (2026)
- [SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?](https://mlsanity.com/paper/2605.30329/) (2026)
- [GIANTS: Generative Insight Anticipation from Scientific Literature](https://mlsanity.com/paper/2604.09793/) (2026)
- [ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes](https://mlsanity.com/paper/2607.04439/) (2026)
- [Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science](https://mlsanity.com/paper/2603.28361/) (2026)
- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution](https://mlsanity.com/paper/2605.07208/) (2026)
- [mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers](https://mlsanity.com/paper/2609.00453/) (2026)
- [Reinforcing Agentic Creativity in Scientific Ideation with Night Science](https://mlsanity.com/paper/2609.35706/) (2026)
- [TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts](https://mlsanity.com/paper/2610.06824/) (2026)
- [Learning Individual Scientific Taste with Privileged Hindsight Distillation](https://mlsanity.com/paper/2610.19719/) (2026)

## Abstract (arXiv)

Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with the potential for long-term scientific impact. Scientific taste is largely concentrated among highly experienced researchers, whose expertise is usually limited to a few specialised fields. If AI could learn scientific taste, it could reduce reliance on human experts and accelerate scientific discovery. Whether AI can learn this ability remains an open question. We introduce Reinforcement Learning from Community Feedback (RLCF) to learn judgement and ideation. Scientific Judge learns from community feedback, such as citations. Scientific Thinker learns to propose research ideas with high potential impact. Experiments show that Scientific Judge outperforms strong LLM baselines and that learned judgement generalises to future-year papers, other community metrics, and unseen fields. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than those proposed by baselines. These results suggest that AI can learn scientific taste, marking an important step towards AI systems that could help accelerate scientific discovery.