AI Can Learn Scientific Taste

• URL: http://arxiv.org/abs/2603.14473v1
• Date: Sun, 15 Mar 2026 16:31:51 GMT
• Title: AI Can Learn Scientific Taste
• Abstract summary: Great scientists have strong judgement and foresight, closely tied to what we call scientific taste.<n>Here, we use the term to refer to the capacity to judge and propose research ideas with high potential impact.<n>Our findings show that AI can learn scientific taste, marking a key step toward reaching human-level AI scientists.
• Score: 123.03470627335189
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Great scientists have strong judgement and foresight, closely tied to what we call scientific taste. Here, we use the term to refer to the capacity to judge and propose research ideas with high potential impact. However, most relative research focuses on improving an AI scientist's executive capability, while enhancing an AI's scientific taste remains underexplored. In this work, we propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem. For preference modeling, we train Scientific Judge on 700K field- and time-matched pairs of high- vs. low-citation papers to judge ideas. For preference alignment, using Scientific Judge as a reward model, we train a policy model, Scientific Thinker, to propose research ideas with high potential impact. Experiments show Scientific Judge outperforms SOTA LLMs (e.g., GPT-5.2, Gemini 3 Pro) and generalizes to future-year test, unseen fields, and peer-review preference. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than baselines. Our findings show that AI can learn scientific taste, marking a key step toward reaching human-level AI scientists.

Related papers

• AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era [55.37558486468993]
  We introduce AgentIdeaBench, a benchmark that evaluates scientific ideation under two matched settings, static observation and active exploration.<n>We report matched Static-Active evaluations for 33 LLMs across 40 densely scored subfields spanning five disciplines.<n>Active exploration reveals considerably more capability headroom, and that headroom is unevenly distributed across models.
  arXiv  Detail & Related papers  (2026-09-07T15:19:13Z)
• Can LLMs Discover Scientific Laws in Real and Parallel Worlds? [58.76147897928744]
  We introduce SCILAWS-BENCH, a benchmark for scientific law discovery built from published research and real scientific data.<n>It comprises 118 problems drawn from 381 scientific papers, covering 291 candidate laws and roughly 8M real data points across six scientific disciplines.<n>We find that predictive fit can diverge from scientific validity, memorization shapes whether models reproduce or move beyond published formulas, and our best-of-N study reveals a selection bottleneck.
  arXiv  Detail & Related papers  (2026-09-01T17:17:59Z)
• Contemporary AI lacks the imagination to diverge or negate in science [4.024882945191284]
  Authors of 121,640 recent preprints across biology, medicine, chemistry, and the social sciences invited to judge ideas that large language models generated from context and puzzles of their own papers.<n> 6,749 scientists returned 25,139 sets of ratings on novelty, empirical feasibility, probability of being true, and favorability of adoption.<n>Second, scientists reward ideas that resemble their own and prize probability over novelty, though social scientists tolerate risk more readily than life scientists.<n>Third, automated evaluators on which the community currently relies agree only weakly with expert judgment, and retrieval augmentation and scientist persona prompting yield only marginal gains.
  arXiv  Detail & Related papers  (2026-06-06T16:39:28Z)
• Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery [23.774769836398036]
  A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery.<n>This position paper argues that although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery.
  arXiv  Detail & Related papers  (2026-05-09T13:52:23Z)
• Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics [82.55776608452017]
  Large language models (LLMs) provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics.<n>This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle.<n>We identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents.
  arXiv  Detail & Related papers  (2025-10-10T22:26:26Z)
• How Far Are AI Scientists from Changing the World? [30.483767443654504]
  We focus on the central question: How far are AI scientists from changing the world and reshaping the scientific research paradigm?<n>We provide a prospect-driven review that comprehensively analyzes the current achievements of AI Scientist systems.<n>We hope this survey will contribute to a clearer understanding of limitations of current AI Scientist systems.
  arXiv  Detail & Related papers  (2025-07-31T06:32:06Z)
• Scaling Laws in Scientific Discovery with AI and Robot Scientists [72.3420699173245]
  An autonomous generalist scientist (AGS) concept combines agentic AI and embodied robotics to automate the entire research lifecycle.<n>AGS aims to significantly reduce the time and resources needed for scientific discovery.<n>As these autonomous systems become increasingly integrated into the research process, we hypothesize that scientific discovery might adhere to new scaling laws.
  arXiv  Detail & Related papers  (2025-03-28T14:00:27Z)
• AI Expands Scientists' Impact but Contracts Science's Focus [15.771625061196927]
  We show accelerated adoption of AI among scientists and consistent professional advantages associated with AI use.<n>Scientists who engage in AI-augmented research publish 3.02 times more papers, receive 4.84 times more citations.<n>By contrast, AI research shrinks the collective volume of scientific topics studied by 4.63%.
  arXiv  Detail & Related papers  (2024-12-10T18:24:17Z)
• Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System [62.832818186789545]
  Virtual Scientists (VirSci) is a multi-agent system designed to mimic the teamwork inherent in scientific research.<n>VirSci organizes a team of agents to collaboratively generate, evaluate, and refine research ideas.<n>We show that this multi-agent approach outperforms the state-of-the-art method in producing novel scientific ideas.
  arXiv  Detail & Related papers  (2024-10-12T07:16:22Z)
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery [14.465756130099091]
  This paper presents the first comprehensive framework for fully automatic scientific discovery. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, and describes its findings. In principle, this process can be repeated to iteratively develop ideas in an open-ended fashion, acting like the human scientific community.
  arXiv  Detail & Related papers  (2024-08-12T16:58:11Z)
• Interesting Scientific Idea Generation using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders [0.6906005491572401]
  We introduce SciMuse, which uses 58 million research papers and a large-language model to generate research ideas.<n>We conduct a large-scale evaluation in which over 100 research group leaders ranked more than 4,400 personalized ideas based on their interest.<n>This data allows us to predict research interest using (1) supervised neural networks trained on human evaluations, and (2) unsupervised zero-shot ranking with large-language models.
  arXiv  Detail & Related papers  (2024-05-27T11:00:51Z)
• Interactive Visual Reasoning under Uncertainty [29.596555383319814]
  We devise the IVRE environment for evaluating artificial agents' reasoning ability under uncertainty. IVRE is an interactive environment featuring rich scenarios centered around Blicket detection.
  arXiv  Detail & Related papers  (2022-06-18T13:32:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.