首个评估大模型科学推理可靠性的基准，直击AI代理在无下游验证场景中的信任危机。
arXiv:2608.11415v1 Announce Type: cross Abstract: Large language models are being proposed as agents in scientific workflows, in domains where no down…
LLM代理自主操控氮空位中心量子传感实验，实现科学推理自动化，前沿跨界研究实测方案。
arXiv:2607.25145v1 Announce Type: cross Abstract: We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous e…
科学推理图提取新方法PEARL，实现可审计的图修复，提升透明度和可靠性
arXiv:2607.17917v1 Announce Type: new Abstract: Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, eviden…
全新基准测试揭示大模型在科学假设发现前的推理能力，填补前瞻性评估空白。
arXiv:2607.15766v1 Announce Type: new Abstract: Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate…
前沿科学推理新突破：ScOrch让多个专家LLM协同工作，显著提升多模态任务表现，超越单一模型局限。
arXiv:2606.15872v1 Announce Type: new Abstract: Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even t…
首个专门评估LLM Agent多步骤科学工具使用的交互环境，填补领域空白。
arXiv:2602.12984v2 Announce Type: replace Abstract: Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-spec…
首个面向有限元科学推理的代码生成基准，精准衡量LLM在结构化场景下的多步推导与代码编写能力。
arXiv:2512.20732v2 Announce Type: replace-cross Abstract: As LLMs advance their reasoning capabilities about the physical world, the absence of rigoro…
AI在科学推理中竟会忽略证据，一场对619个任务的研究揭示了信任危机。
Article URL: https://www.sciencenews.org/article/ai-ignore-evidence-trust-science Comments URL: https://news.ycombinator.com/item?id=48345857 Points: …
该研究证明了LLM在因果发现任务上的根本性失败，并提出介入式代理作为突破路径，是AI推理领域的一道硬核证据。
arXiv:2605.27567v1 Announce Type: new Abstract: Causal discovery is a cornerstone of scientific reasoning, yet whether large language models can perfo…
8B参数模型专用生物实验protocol生成，步骤顺序不乱、剂量无幻觉，超越GPT-4o，已登ICLR2026。
超越GPT-4o