Pith. sign in

REVIEW 7 cited by

AI Can Learn Scientific Taste

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2603.14473 v2 pith:A4TIKN42 submitted 2026-03-15 cs.CL

AI Can Learn Scientific Taste

classification cs.CL
keywords scientificjudgeideaslearncommunityimpactpotentialresearch
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with potential for long-term scientific impact. Whether AI can learn this ability remains an open question. Here we provide evidence that artificial intelligence can learn judgement and ideation. We introduce Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale signals from scientific community as supervision. We first train Scientific Judge on field- and time-matched pairs of high- vs. low-citation papers to judge ideas. We then train a Scientific Thinker, to propose research ideas with high potential impact. Experiments show that the 30B Scientific Judge variant outperforms strong LLM baselines (e.g., GPT-5.4 Thinking), while Scientific Judge generalizes across future-year papers, unseen fields, and other community metrics. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than baselines. These results suggest that AI can learn scientific taste, marking an important step towards AI systems that could help accelerate scientific discovery.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GIANTS: Generative Insight Anticipation from Scientific Literature

    cs.CL 2026-04 unverdicted novelty 8.0

    GIANTS-4B, trained with RL on a new 17k-example benchmark of parent-to-child paper insights, achieves 34% relative improvement over gemini-3-pro in LM-judge similarity and is rated higher-impact by a citation predictor.

  2. Measuring the Gap Between Human and LLM Research Ideas

    cs.CL 2026-07 unverdicted novelty 7.0

    LLM-generated research ideas cluster more around bridge-like opportunities and synthesis methods than the broader distribution seen in human papers.

  3. SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?

    cs.LG 2026-05 conditional novelty 6.0

    SoundnessBench shows frontier LLMs exhibit pervasive optimism bias when rating the soundness of ML research proposals, frequently calling low-soundness ideas sound under standard prompts.

  4. GraphReview: Scientific Paper Evaluation via LLM-Based Graph Message Passing

    cs.CL 2026-05 unverdicted novelty 6.0

    GraphReview models paper evaluation as LLM-driven message passing on a semantic paper graph that links intrinsic quality, contemporaneous papers, and prior work, then applies Personalized PageRank for ranking and revi...

  5. FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution

    cs.LG 2026-05 unverdicted novelty 6.0

    FAME models scientific topic trajectories in continuous time to forecast paper impact more accurately than LLMs by aligning manuscripts with field momentum in a dynamic latent space.

  6. ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment

    cs.AI 2026-05 unverdicted novelty 5.0

    ForeSci is a temporally controlled benchmark with 500 tasks for assessing LLM agents on forward-looking AI research judgments in four domains using cutoff-aligned knowledge bases.

  7. ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

    cs.SE 2026-05 unverdicted novelty 4.0

    ARIS is a three-layer open-source system that uses cross-model adversarial collaboration plus claim-auditing pipelines to make LLM-driven research workflows more reliable.