English
Related papers

Related papers: FlowPIE: Test-Time Scientific Idea Evolution with …

200 papers

Generative flow networks (GFlowNets), as an emerging technique, can be used as an alternative to reinforcement learning for exploratory control tasks. GFlowNet aims to generate distribution proportional to the rewards over terminating…

Machine Learning · Computer Science 2023-03-07 Yinchuan Li , Shuang Luo , Haozhi Wang , Jianye Hao

Automated scientific idea generation systems have made remarkable progress, yet the automatic evaluation of idea novelty remains a critical and underexplored challenge. Manual evaluation of novelty through literature review is…

Information Retrieval · Computer Science 2025-06-30 Simra Shahid , Marissa Radensky , Raymond Fok , Pao Siangliulue , Daniel S. Weld , Tom Hope

Tree search has become as a representative framework for test-time reasoning with large language models (LLMs), exemplified by methods such as Tree-of-Thought and Monte Carlo Tree Search. However, it remains difficult to provide instant and…

Artificial Intelligence · Computer Science 2026-03-02 Jiaxi Li , Yucheng Shi , Xiao Huang , Jin Lu , Ninghao Liu

In automated UI design generation, a key challenge is the lack of support for iterative processes, as most systems focus solely on end-to-end output. This stems from limited capabilities in interpreting design intent and a lack of…

Human-Computer Interaction · Computer Science 2025-10-30 Mingyue Yuan , Jieshan Chen , Yongquan Hu , Sidong Feng , Mulong Xie , Gelareh Mohammadi , Zhenchang Xing , Aaron Quigley

What underlies intuitive human thinking? One approach to this question is to compare the cognitive dynamics of humans and large language models (LLMs). However, such a comparison requires a method to quantitatively analyze AI cognitive…

Computation and Language · Computer Science 2025-05-02 Makoto Sato

Recent advancements in large language models (LLMs) have shown remarkable potential in various complex tasks requiring multi-step reasoning methods like tree search to explore diverse reasoning paths. However, existing methods often suffer…

Artificial Intelligence · Computer Science 2025-06-10 Sungjae Lee , Hyejin Park , Jaechang Kim , Jungseul Ok

Evaluating AI-generated research ideas typically relies on LLM judges or human panels -- both subjective and disconnected from actual research impact. We introduce HindSight, a time-split evaluation framework that measures idea quality by…

Computation and Language · Computer Science 2026-03-18 Bo Jiang

Generative Flow Networks (GFlowNets) offer a powerful framework for sampling graphs in proportion to their rewards. However, existing approaches suffer from systematic biases due to inaccuracies in state transition probability computations.…

Machine Learning · Statistics 2025-10-17 Hohyun Kim , Seunggeun Lee , Min-hwan Oh

The growing availability of generative AI technologies such as large language models (LLMs) has significant implications for creative work. This paper explores twofold aspects of integrating LLMs into the creative process - the divergence…

Human-Computer Interaction · Computer Science 2024-03-04 Orit Shaer , Angelora Cooper , Osnat Mokryn , Andrew L. Kun , Hagit Ben Shoshan

Effective research ideation is a critical step for scientific research. However, the exponential increase in scientific literature makes it challenging for researchers to stay current with recent advances and identify meaningful research…

Artificial Intelligence · Computer Science 2024-10-31 Long Li , Weiwen Xu , Jiayan Guo , Ruochen Zhao , Xingxuan Li , Yuqian Yuan , Boqiang Zhang , Yuming Jiang , Yifei Xin , Ronghao Dang , Deli Zhao , Yu Rong , Tian Feng , Lidong Bing

Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin. The `AIGENIE` R package implements the AI-GENIE framework…

Artificial Intelligence · Computer Science 2026-03-31 Lara Russell-Lasalandra , Hudson Golino , Luis Eduardo Garrido , Alexander P. Christensen

Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs), yet standard outcome-based approaches often suffer from reward sparsity and inefficient credit assignment. In this…

Artificial Intelligence · Computer Science 2026-02-03 Xiangwei Wang , Wei Wang , Ken Chen , Nanduni Nimalsiri , Saman Halgamuge

We introduce MCTS-RAG, a novel approach that enhances the reasoning capabilities of small language models on knowledge-intensive tasks by leveraging retrieval-augmented generation (RAG) to provide relevant context and Monte Carlo Tree…

Computation and Language · Computer Science 2025-10-09 Yunhai Hu , Yilun Zhao , Chen Zhao , Arman Cohan

Scientific writing involves retrieving, summarizing, and citing relevant papers, which can be time-consuming processes in large and rapidly evolving fields. By making these processes inter-operable, natural language processing (NLP)…

Computation and Language · Computer Science 2023-11-07 Nianlong Gu , Richard H. R. Hahnloser

LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for designing their individual components and provide no guarantee that the search converges.…

Artificial Intelligence · Computer Science 2026-05-18 Jiachen Jiang , Huminhao Zhu , Zhihui Zhu

Question Answer (QA) systems for biomedical experiments facilitate cross-disciplinary communication, and serve as a foundation for downstream tasks, e.g., laboratory automation. High Information Density (HID) and Multi-Step Reasoning (MSR)…

Artificial Intelligence · Computer Science 2026-01-09 Haofei Hou , Shunyi Zhao , Fanxu Meng , Kairui Yang , Lecheng Ruan , Qining Wang

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection Siyuan Cheng, Bozhong Tian, Yanchao Hao, Zheng Wei Published: 06 Apr 2026, Last Modified: 06 Apr 2026 ACL 2026 Findings Conference, Area Chairs, Reviewers,…

Artificial Intelligence · Computer Science 2026-04-08 Siyuan Cheng , Bozhong Tian , YanChao Hao , Zheng Wei

In many text-generation problems, users may prefer not only a single response, but a diverse range of high-quality outputs from which to choose. Quality-diversity (QD) search algorithms aim at such outcomes, by continually improving and…

The rapid growth of scientific publishing has made it increasingly difficult to track how fast-moving areas evolve. Search engines and LLM-based assistants retrieve or summarize papers, but often hide how the corpus was selected, organized,…

Information Retrieval · Computer Science 2026-05-28 Bernardo A. Denkvitts , Nitin Gupta , Biplav Srivastava