AutoSci is a memory-centric agentic system designed to automate the entire scientific research lifecycle by integrating structured memory, multi-stage execution, and continuous self-improvement.

This paper presents Clarus, a collaboration infrastructure for coordinating autonomous research agents towards web-scale scientific collaboration.

This paper investigates how PhD students in software engineering perceive and navigate science communication, revealing motivations, communication channels, and barriers.

This paper proposes Evolutionary Intelligence (EI) for scientific discovery, which links candidate refinement with experience retention across evolutionary cycles.

This paper investigates the ability of large language models to assist in scientific project planning and proposal evaluation, finding that human reviewers rate human- and AI-written proposals similar…

The paper proposes a taxonomy for AI-human collaboration in scientific evaluation and introduces the Paper Assistant Tool (PAT) to accelerate verification and review process in scientific research.

PaperPilot is an interactive literature search agent that constructs an executable DAG of paper-search operators based on user queries and feedback, improving search results and reducing errors.

This paper investigates the correlation between gender diversity and the scientific impact of papers in Natural Language Processing (NLP) and Library and Information Science (LIS) domains.

This paper proposes Workflow Cognition as a theoretical framework for explaining expertise as a dynamic cognitive phenomenon.

PAPERCLAW is a multi-agent system that autonomously curates a domain, generates ideas, and writes venue-compliant papers using large language models and a stoppable hypothesis map.

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.

The paper introduces KnowledgeGain, a novel metric that measures the actual knowledge gained by readers from science news, and demonstrates its use in optimizing news generation to improve reader lear…

FARS is a fully automated AI-for-AI research system that generated and advanced 166 complete research papers across 67 topics in a large-scale public deployment, with evaluations from 282 reviews.

This paper systematically analyzes 2.7 million arXiv submissions to demonstrate that nearly every preprint unintentionally discloses sensitive or unnecessary information through its source files, prop…

The paper introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…

The paper evaluates the gap between LLM-generated research ideas and human research ideas by building an evaluation framework and observing a distributional gap.

Authors of 44 meta-analyses preferred a single pass by a frontier model over two multi-agent debate tools for improving their papers, despite the tools spending roughly thirty times the tokens.

This paper identifies eight competencies required for researchers and graduate students to use Large Language Models critically and responsibly, based on a review of 40 articles.

This paper compares sparse and dense retrieval models for scientific claim-source retrieval on the CheckThat! 2026 benchmark. Translating claims into English and incorporating publication metadata imp…