arXiv Computation and Language October 16, 2026 By Manya Wadhwa, Pranav Narayanan Venkit, Hiroaki Hayashi, Yu Li, Tuhin Chakrabarty, Chien-Sheng Wu

Training Reasoning Models to Generate Diverse Scientific Ideas

Read the original on arXiv Computation and Language →

The paper introduces a method for training large language models to generate diverse, high‑quality scientific ideas grounded in input documents. By using a set‑level reinforcement learning objective that rewards ideas for being distinct from earlier ones, the authors train an 8B model that outperforms Claude Opus 4.8 and GPT‑6 Astra on a contamination‑free benchmark. Human experts rate the model’s idea sets as equally promising while containing slightly more unique ideas, and automated experiments show comparable executability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jul 2

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

arXiv:2606. 25198v2 Announce Type: replace Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning.

By Antonis Antoniades, Deepak Nathani, Ritam Saha, Alfonso Amayuelas, Ivan Bercovich, Zhaotian Weng, Vignesh Baskaran, Kunal Bhatia, William Yang Wang

llms agents reinforcement-learning

arXiv AI

Sep 15

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

arXiv:2609.14896v1 Announce Type: cross Abstract: A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at infer...

By Jiayi Yuan, Hangoo Kang, James Jihao Liu, Yejin Choi, Vikram Iyer, Liwei Jiang, Natasha Jaques

llms agents reinforcement-learning benchmarks safety

arXiv AI

Jul 21

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

arXiv:2505. 20161v2 Announce Type: replace-cross Abstract: Effective generalization in language models depends critically on the diversity of their training data.

By Jaehun Jung, Seungju Han, Ximing Lu, Skyler Hallinan, David Acuna, Shrimai Prabhumoye, Mostafa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi

llms benchmarks

arXiv AI

Aug 10

CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity

arXiv:2608. 07460v1 Announce Type: cross Abstract: While post-training improves the capabilities of large language models (LLMs), it generally lowers their output diversity and creativity, negatively impacting tasks that explicitly require creativity (e.

By Ananya Sahu, Mohit Bansal, Elias Stengel-Eskin

llms reinforcement-learning safety

arXiv Computation and Language

Sep 1

PaperGym: Rubric-Centered Evolution for Research-Plan Generation

PaperGym is a framework that transforms each research paper into a training environment for AI research planning, using rubrics extracted from the paper’s method and experiments as a critic. It synthesizes research questions from the goal and background, and derives evaluation criteria from the method and experiments, reducing criterion leakage to 3.7%. Experiments with Qwen models show that training with PaperGym’s rubric improves benchmark performance by up to 5.6 points and outperforms existing datasets and fine‑tuning baselines.

By Yuhan Wang, Zhengxi Lu, Yuchen Yan, Kaitao Song, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

reinforcement-learning fine-tuning benchmarks

arXiv AI

Oct 7

IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas

arXiv:2610.08781v1 Announce Type: cross Abstract: Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training...

By Ziyu Chen, Yilun Zhao, Jiashuo Sun, Yiling Ma, Manasi Patwardhan, Arman Cohan

llms reinforcement-learning efficiency

One email a morning, machine-written

Related stories

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity

PaperGym: Rubric-Centered Evolution for Research-Plan Generation

IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas