arXiv AI

IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation

arXiv:2607. 10144v1 Announce Type: new Abstract: Scientific research is a complex, multi-stage workflow rather than a single act of text generation.

arXiv AI

Jul 1

Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents

arXiv:2606. 31229v1 Announce Type: new Abstract: Ideation plays a pivotal role in scientific discovery.

By Keyu Zhao, Lingyan Kong, Fengli Xu, Yong Li

llms agents benchmarks

Hugging Face Trending Papers

Aug 31

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experimentation, and report generation. However, open-end...

llms agents

arXiv AI

Aug 19

AutoResearch: Insight In, Hallucination Out

AutoResearch is a two‑stage autonomous research system that links Idea Generation with Idea Execution. In the generation phase it blends new research signals with existing domain knowledge, identifies transferable mechanistic insights, and produces grounded, testable research plans through multi‑model generation and cross‑review. The execution phase then decomposes these plans into experiments, iteratively implements and diagnoses them, and uses independent evidence‑based review to accept or revise conclusions, thereby turning ideas into measurable progress while minimizing hallucinations.

By Yiming Ren, Xiang Liu, Qumeng Sun, Xiao Zhang, Jiahao Li, Haoyang Zhang, Junjie Wang

agents multimodal benchmarks safety

arXiv AI

Sep 1

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

arXiv:2608.31076v1 Announce Type: cross Abstract: Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experi...

By Xuehai Wang, Haowei Qin, Tongxin Liu, Junkai Li, Buqiang Xu, Jintian Zhang, Yijun Chen, Zirui Xue, Shumin Deng

llms agents

arXiv AI

Jun 4

SciDER: Scientific Data-centric End-to-end Researcher

arXiv:2603. 01421v3 Announce Type: replace Abstract: While large language models accelerate scientific discovery, existing agents face severe limitations in adaptability, domain generalization, and multimodal scalability, often struggling to autonomously process raw, domain-specific experimental data.

By Ke Lin, Owais Aijaz, Yilin Lu, Yiyang Luo, Xuehang Guo, Preslav Nakov

llms agents fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 17

Idea2Plan: Exploring AI-Powered Research Planning

arXiv:2510. 24891v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields.

By Jin Huang, Silviu Cucerzan, Sujay Kumar Jauhar, Ryen W. White

llms agents benchmarks

arXiv AI

Jul 7

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

arXiv:2607. 04439v1 Announce Type: new Abstract: Large language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions.

By Qihao Zhao, Yangyu Huang, Yalun Dai, Lingao Xiao, Jianjun Gao, Xin Zhang, Wenshan Wu, Scarlett Li, Yang He, Yan Lu, Yap Kim Hui

llms

arXiv AI

Jul 20

SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery

arXiv:2607. 16038v1 Announce Type: new Abstract: Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state.

By SciForge Team, Zhangyang Gao, Minghao Fang, Yifei Liu, Hanhui Yang, Xinyu Gu, Shixiang Tang, Siqi Sun, Lei Bai, Cheng Tan, Mengdi Liu, Hao Wu, Shuizhou Chen

agents multimodal

arXiv AI

Aug 3

Scaling Scientific Discovery Environments for Turn-Level Agentic RL

arXiv:2607. 28990v1 Announce Type: new Abstract: Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim.

By Yucheng Xu, Keyi Zhang, Yuyang Yu, Min Zhang, Shiyuan Meng, Pei Chu, Zhongying Tu

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 1

Paper Pilot: A Human-in-the-Loop Expert System for Evidence-Traceable Scientific Manuscript Generation in Applied Sciences

arXiv:2608.28596v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly embedded in scientific workflows for literature analysis, drafting, and review. Existing systems adv...

By Nidhi Jha, Siddharth Chaudhary, Ajinkya Kulkarni

llms agents benchmarks safety

arXiv AI

Jun 9

DN-Hypo-Pipeline: An AI-Driven Workflow for Hypothesis Generation via Large Language Models and Scientific Explanations

arXiv:2606. 08532v1 Announce Type: new Abstract: A scientific hypothesis is the first step in research and undergoes experimental validation, yet it also reflects a deep understanding of and reasoning about scientific phenomena.

By Lei Lin, Ronghao Wang, Chunbao Zhou, Jue Wang, Yangang Wang

llms

arXiv AI

Jul 17

Building Agent Harnesses for Scientific Curation from Multimodal Sources

arXiv:2606. 21005v2 Announce Type: replace Abstract: Scientific discovery workflows often depend on structured curation from the literature.

By Sheng Zhang, Qin Liu, Renqian Luo, Shufang Xie, Reuben Tan, Sean Hayes, Gregory Bryman, Wendong Ge, Ruilian Zhang, Oluwaseun Egbelowo, Kelly Yee, Hoifung Poon

agents multimodal

Related stories