ScholarPulse 日报 2026-06-22

2026-06-22 学术简报：2 篇。AI经济学家代理框架通过整合RAG、知识图谱与LLM代理，显著提升经济分析报告的经济连贯性与可追溯性。

今日速览

序号	标题	来源	日期	主题	推荐等级
1	AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models	arXiv	2026-06-18	RAG	高
2	When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents	arXiv	2026-06-18	AI-Agent	高

重点论文与技术动态

1. AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models

来源：arXiv
日期：2026-06-18
作者/机构：Masahiro Kato
主题标签：RAG, arXiv
推荐等级：高
分类：econ.GN, cs.AI, cs.LG, q-fin.GN

一句话结论

AI经济学家代理框架通过整合RAG、知识图谱与LLM代理，显著提升经济分析报告的经济连贯性与可追溯性。

一段话：该框架避免直接依赖LLM生成定量声明，转而通过AI代理规划分析流程、检索经济理论与数据证据、选择模型并生成基于显式模型计算的叙述，确保报告与真实经济场景紧密关联，从而增强可信度。

核心内容

利用知识图谱（含经济数据与理论）和LLM代理构建经济分析框架，支持理论与数据驱动的分析。
AI代理执行分析规划、证据检索、模型选择及报告生成，避免直接LLM输出导致的理论脱节。
在美国通胀持久性报告和美联储政策分析等应用中，框架提升报告的经济连贯性与可追溯性。

方法与数据

框架基于RAG和知识图谱，但摘要未明确具体数据集。

价值判断

值得关注：有效解决LLM经济报告缺乏理论与数据支撑的行业痛点。
可复用点：agentic框架与RAG集成方法可推广至其他经济分析任务（如政策报告生成）。
局限/待核查：摘要未提及局限。

摘要

We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, economists are often required to make economic claims grounded by economic theory and real-world data. Based on this motivation, this study proposes an RAG-based AI economist, which utilizes knowledge graphs including economic data and theory and LLM-based agents to plan the analysis, retrieve relevant evidence, select appropriate models, and generate reports. In our framework, we do not produce quantitative claims directly with the language model alone; instead, we generate narratives grounded in explicit model-based computations and linked to the retrieved evidence via AI agents. We refer to our framework as an AI economist agent. We evaluate the AI economist agent in two applications: economist report generation for U.S. inflation persistence and Federal Reserve policy, and bank stress-test narrative generation for U.S. commercial real estate refinancing stress. The results illustrate how grounding the generated reports improves their economic coherence and traceability.

2. When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

来源：arXiv
日期：2026-06-18
作者/机构：Kaiyue Yang, Yuyan Bu, Jingwei Yi, Yuchi Wang, Biyu Zhou, Juntao Dai
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.SE, cs.AI, cs.CL

一句话结论

主流LLM代理普遍存在选择高权限工具而非足够低权限替代方案的问题，特权感知后训练防御能有效减少不必要的高权限使用。

核心内容

实验在八领域和五风险模式下发现，主流LLM代理常选择高权限工具而非足够低权限替代方案，且临时工具故障会进一步放大此问题。
通用安全对齐无法可靠转移到最小权限工具选择，提示级控制在临时故障下缓解效果有限。
提出特权感知后训练防御机制，教导代理优先选择足够低权限工具，仅在必要时升级，实验验证其显著降低高权限滥用率。

方法与数据

引入ToolPrivBench评估工具选择，覆盖八领域和五风险模式。

价值判断

值得关注：LLM代理权限选择安全风险突出，高权限工具滥用可能导致数据泄露或系统破坏。
可复用点：特权感知防御框架可推广至其他安全对齐任务，提升代理权限管理能力。
局限/待核查：提示级控制在临时故障下缓解效果有限，需结合其他方法优化防御机制。

摘要

As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leaving privilege-sensitive choices underexplored. To address this gap, we study over-privileged tool selection, in which an agent selects or escalates to a higher-privilege tool despite a sufficient lower-privilege alternative. We introduce ToolPrivBench to evaluate whether agents choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures. Across eight domains and five recurring risk patterns, we find that over-privileged tool selection is common among mainstream LLM agents and is further amplified by transient failures. We further find that general safety alignment does not reliably transfer to least-privilege tool choice, while prompt-level controls provide only limited mitigation under transient failures. We therefore introduce a privilege-aware post-training defense that teaches agents to prefer sufficient lower-privilege tools and escalate only when necessary. Our mitigation experiments show that this defense substantially reduces unnecessary high-privilege tool use while preserving general capabilities.