The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

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 AIBuildAI-2, a knowledge-enhanced agent that significantly improves the automatic building of AI models by integrating an external, evolving knowledge system, achieving state-of-t…

The study compares agentic data retrieval using unstructured web data versus structured, semantically-annotated datasets, concluding that semantic metadata remains essential for high-precision, reliab…

ResearchLoop introduces an evidence-gated control plane to manage and audit the state of AI-assisted computational research, mitigating the risk of unverified claims.

The paper outlines the potential for using generative AI to conduct large-scale, simulation-based experiments in literary studies, demonstrating initial results in generating constrained literary text…

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

The paper introduces extsc{Ptah}, a multi-agent harness designed to improve verifiable multimodal deep research by orchestrating the entire report generation process, ensuring factual grounding and v…

This paper presents EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery.

This survey provides a comprehensive analysis of Reasoning Language Model (RLM) adoption across 28 scientific disciplines, revealing significant disparities in RLM maturity across different scientific…

The paper introduces a Deep Research pipeline that significantly improves literature search recall and demonstrates that human-curated citation lists are often unreliable and do not serve as a true gr…

The paper develops a theoretically grounded framework for evaluating multilingual LLMs in Social Sciences and Humanities, moving beyond traditional NLP benchmarks to assess interpretive validity and c…

The paper proposes MACAT, a Multi-Agent Culture-Aware Translation framework, to selectively translate culture-loaded words in ancient Chinese texts, achieving superior performance over existing method…

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

DeepSurvey is an agentic system that significantly enhances automated survey generation by extracting deep, structured knowledge from full-text papers and rigorously validating citations, achieving su…

The paper introduces COMPOSE, a dual-graph framework that generates plausible future mathematical theorems by simultaneously conditioning a language model on both the scientific citation context and t…

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

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…

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.

The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…