The paper introduces IDRBench, a framework designed to evaluate how well large language models (LLMs) can integrate knowledge across disciplines for interdisciplinary research. It comprises datasets and tasks—IDR Paper Identification, IDR Idea Integration, and IDR Idea Recommendation—to benchmark LLM performance. The authors analyze ten mainstream LLMs, offering a comprehensive assessment and establishing baselines for future studies.
arXiv:2506. 03922v4 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains.
arXiv:2607. 06482v1 Announce Type: cross Abstract: Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings.
arXiv:2608. 13136v1 Announce Type: cross Abstract: With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention.
arXiv:2603. 03322v2 Announce Type: replace-cross Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery.
arXiv:2605. 16902v2 Announce Type: replace Abstract: Scientific artifacts such as models and datasets are foundations for research.
arXiv:2601.17020v3 Announce Type: replace-cross Abstract: With the rising popularity of interdisciplinary work and increasing institutional incentives in this direction, there is a growing need to un...
arXiv:2510. 24891v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields.
arXiv:2607. 26670v1 Announce Type: cross Abstract: The rapid growth of scholarly literature has made identifying relevant publications increasingly difficult, and conventional search systems still depend heavily on manually formulated queries and effortful manual inspection.
arXiv:2602. 14367v2 Announce Type: replace-cross Abstract: The rapid evolution of Large Language Models has catalyzed a surge in scientific idea production, yet this leap has not been accompanied by a matching advance in idea evaluation.
arXiv:2605. 29475v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show remarkable potential in scientific hypothesis discovery.
arXiv:2602. 20459v2 Announce Type: replace Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow?
The paper introduces SGHA, a fully automated system that discovers research problems by structuring scientific literature into evidence-linked objects and a typed evidence graph. SGHA operates entirely on a local 9B open‑weight language model, avoiding proprietary frontier‑model APIs, and outputs traceable research‑problem families with assumptions, objectives, success criteria, and ambiguities. Comparative experiments in five machine‑learning domains show that SGHA’s corpus‑first, evidence‑constrained approach yields inspectable research‑problem formulation without relying on external models.