← Back to all news
arXiv AI

Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output

The paper introduces SciSense, a framework that structures scientific ideation into eight cognitive stages and a dataset, SciSense-Traj, of 120K citation-conditioned research trajectories in both hindsight and foresight modes. It presents SciSense-LM, a family of LLMs trained on these trajectories, showing that hindsight-trained models yield higher-quality, more novel outputs and improve downstream coding agents’ research artifacts. The study demonstrates that outcome-anchored ideation reduces cognitive load for downstream agents, enabling more creative exploration.

Related stories

arXiv AI
Oct 23

SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery

SpecEvo is a multi‑Large Language Model framework that uses lightweight models to generate and refine candidate programs while an Advisor consolidates evidence from successes and failures. At sparse checkpoints, a frontier‑model Navigator intervenes with synthesis or refinement to address search stagnation. Across 176 tasks in scientific and algorithmic domains, SpecEvo matches or surpasses frontier‑model baselines, cuts API cost by up to 80%, and improves evaluation efficiency and benchmark performance.

By Ha Minh Hieu, Tongyao Zhu, Do Xuan Long, Min-Yen Kan
llms
More like this →
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
agentsmultimodalbenchmarkssafety
More like this →
arXiv AI
Oct 21

Modeling Authentic Research Trajectories: A Graph View of Research Ideation

The paper introduces the Research Progress Graph (RPG), a framework that captures the full, evidence‑driven evolution of research ideas through a closed‑loop process of experimentation, insight, challenge identification, literature exploration, and revision. Unlike current large‑language‑model agents that only record the final idea, the RPG records each research state, its temporal order, and the reasoning that links successive states, providing a complete, authentic trajectory. The authors compare thirty‑five existing agents to the RPG, showing that none fully preserves the evolving record, and argue that future agents should predict next research states, evaluate ideas as trajectories, and use authentic trajectories as training data.

By Ruochen Li, Zhiyu Chen
llmsagents
More like this →
Hugging Face Trending Papers
Jul 29

SciDataSailor: Deep Scientific Data Exploring

Scientific datasets are commonly organized as hierarchical repositories containing heterogeneous and interdependent files, making their inspection, integration, and analysis labor-intensive and reliant on domain expertise. Although large language model (LLM) agents have advanced substantially in planning, reasoning, and tool use, existing research has largely overlooked their ability to interact with real scientific data assets through executable environments.

llmsagentsnlpfine-tuning
More like this →
arXiv Computation and Language
Oct 27

Rethinking Scientific Discovery in the Agentic Era

arXiv:2607.03863v3 Announce Type: replace Abstract: Artificial intelligence has advanced scientific discovery, but most AI4Science systems remain fragmented tools that rely on humans to coordinate pr...

By Yining Zheng, Yuxin Wang, Jiahao Lu, Shicheng Fang, Weiyi Wang, Yongzhuo Yang, Bowen Li, Haochen Ma, Chen Hu, Bowen Chen, Yang Wang, Huanhui Chen, Yitong Chen, Jiajun Chen, Zhiyuan Li, Yanlin Li, Zhuo Yang, Qifeng Wu, Jiaying He, Zhijie Jinluo, Xiaohu Xu, Yi Feng, Juncheng Qian, Yizhou Chen, Yang Cheng, Tong Zhu, Tianlei Ying, Hongyu Yu, Hongjun Xiang, Xipeng Qiu
agents
More like this →