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 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…

The paper introduces CITETRACE, a large-scale dataset and evaluation framework that systematically measures structural citation failures in search-augmented LLMs, revealing a pattern called Verified M…

The paper introduces TaDaS, a framework that analyzes large-scale text archives to measure professional sentiment, finding that while AI discussion among economists is initially negative, the trend sh…

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.

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…

The paper demonstrates that deep-research agents are vulnerable to poisoning attacks where an adversary can inject malicious content into a single, frequently retrieved user-generated page to compromi…

The paper systematically evaluates advanced retrieval-augmented generation (RAG) architectures for Cyber Threat Intelligence (CTI), demonstrating that a hybrid graph-text approach significantly improv…

The paper introduces SPIRE, a multi-agent framework designed to extend LLM research capabilities to the humanities by enabling evidence-grounded interpretive reasoning over primary sources.

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 advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

The paper introduces Ryze, an automated system that synthesizes evidence-enriched Question-Answering (QA) pairs from raw biomedical papers, resulting in a specialized VLM (BioVLM-8B) that significantl…

Critic-R introduces a novel framework that uses a critic model to provide natural language introspective feedback, significantly improving the performance of agentic search systems by optimizing retri…

The paper introduces SciIntBench, an adversarial benchmark that reveals that LLMs' adherence to research integrity norms is highly sensitive to how the misconduct is framed, often failing when the mis…

The paper introduces SciIntBench, an adversarial benchmark that reveals that LLMs' adherence to research integrity norms is highly sensitive to how the misconduct is framed, failing particularly when…

The paper introduces I-WebGenBench, a framework and benchmark that converts static scientific papers into executable, interactive web systems, allowing users to dynamically explore the paper's mechani…

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 a novel, scalable framework to monitor and classify dataset usage within research literature, addressing the current lack of infrastructure for tracking data citations.

The paper empirically investigates whether AI-generated reviews can improve the drafting process of academic papers, finding that AI reviews cover many human-identified issues but also introduce novel…

This paper shows that large language models can automate reproducibility assessments in the social and behavioral sciences.