ScholarPulse 日报 2026-08-12

2026-08-12 学术简报：2 篇。AI通过人机协作在数学研究中成功改进了Grothendieck常数的界，其见解被领域专家认定为创新性突破。

今日速览

序号	标题	来源	日期	主题	推荐等级
1	Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration	arXiv	2026-08-11	AI-Agent	高
2	Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives	arXiv	2026-08-11	AI-Agent	高

重点论文与技术动态

1. Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration

来源：arXiv
日期：2026-08-11
作者/机构：Alan Li, Rahul Saha, Anton Xue, Swarat Chaudhuri, Adam Klivans, Pravesh K Kothari
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.AI, cs.CC, cs.HC, math.FA

一句话结论

AI通过人机协作在数学研究中成功改进了Grothendieck常数的界，其见解被领域专家认定为创新性突破。

核心内容

AI系统与人类合作将Grothendieck常数 ( K_G ) 的界收紧至 ( \frac{6\pi}{11} \leq K_G \leq \frac{\pi}{2\log(1+\sqrt{2})} - 10^{-4} )，该常数衡量组合问题与连续松弛的难度。
该AI系统生成的见解被领域专家确认为新颖且具有突破性，推动了数学研究进展。
研究深入探讨了AI在数学研究中的优势、劣势及创造突破性见解的理想条件。

方法与数据

摘要未明确具体方法与数据。

价值判断

值得关注：AI在数学研究中的人机协作模式为解决长期未决问题提供了新范式，展示了AI辅助研究的潜力。
可复用点：构建理想环境以激发AI创新见解的策略可推广至其他数学或科学领域。
局限/待核查：摘要未明确具体局限。

摘要

AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck constant $K_G$, which captures the hardness between combinatorial problems and their continuous relaxations. Specifically, while the precise value of $K_G$ is not known, we recently tightened the best known bounds to \[ \frac{6π}{11} \;\le\; K_G \;\le\; \fracπ{2\log(1+\sqrt2)} - 10^{-4}. \] Crucially, these improvements were achieved using an AI research system that could arrive at insights deemed novel by domain experts. We give a detailed discussion of our experience using AI for mathematics research, particularly touching upon its strengths and weaknesses, as well as our experience with creating ideal conditions for AI to arrive at breakthrough insights.

2. Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives

来源：arXiv
日期：2026-08-11
作者/机构：Francesco Musicco, Danilo Danese, Giuseppe Fasano, Angela Lombardi, Alberto Carlo Maria Mancino, Tommaso Di Noia
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.MA

一句话结论

XstrAI框架通过多智能体系统实现受众感知的XAI叙事，有效解决医疗AI中患者、临床医生和数据科学家对模型解释的差异化需求，避免数值输出的不足。

核心内容

XstrAI将局部解释编码为不可变结构化表示，确保所有受众共享相同证据基础，避免解释偏差。
生成过程由三个专用LLM智能体分工：受众感知规划、语言实现和验证（涵盖接地、归因一致性、沟通风险及受众适当性），含边界修订循环处理不一致。
评估显示XstrAI在临床医生和患者受众上显著优于所有基线，数据科学家场景下表现竞争性，且叙事被独立法官一致分配至目标受众。

方法与数据

方法：基于三个LLM智能体的多智能体框架处理受众感知叙事。
数据：在糖尿病和中风风险预测任务上评估，摘要未明确具体数据集。

价值判断

值得关注：解决XAI中受众差异问题，提升解释的可理解性与信任度，尤其适用于医疗等高风险场景。
可复用点：多智能体框架设计可迁移至其他需多受众沟通的AI系统，如金融或教育领域。
局限/待核查：摘要未明确具体局限，但数据科学家场景下特定基线表现更优，需进一步验证。

摘要

Feature-attribution methods such as SHAP provide useful evidence about individual model predictions, but their numerical outputs are rarely sufficient for audiences with different expertise, goals, and risks of misinterpretation. In medical AI, the same local explanation must reach patients, clinicians, and data scientists through markedly different forms of communication, and naive verbalization through large language models (LLMs) is prone to weak grounding, conflation of attribution with causal language, and outputs that are persuasive without being faithful to the underlying model evidence. We introduce XstrAI, an audience-aware multi-agent framework that treats local explanations as fixed evidence and structures how it is communicated to each target reader. Each prediction case is encoded as an immutable structured representation, shared identically across audiences so the underlying evidence remains fixed. Generation is factored into three specialized LLM agents responsible for audience-aware planning, linguistic realization, and validation for grounding, attribution consistency, communicative risk, and audience appropriateness, with a bounded revision loop triggered on detected inconsistencies. We evaluate XstrAI on diabetes and stroke risk prediction against 11 baselines, ranging from direct verbalization to a re-implementation of a state-of-the-art narrator. The evaluation combines an intra-narrative regime measuring fidelity to SHAP evidence with an extra-narrative regime assessing audience appropriateness through reference corpora, multi-family LLM judges, and a survey with target readers. In both evaluations, XstrAI's narratives are consistently assigned to their intended audience by independent judges, and preferred over all baselines on Clinician and Patient audiences, with competitive performance on Data Scientist, where audience-conditioned single-prompt baselines lead.