构建面向社会公益的可信图智能体检索增强生成：架构、故障传播与构造即保证
Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction
浏览论文内容
中文总结 AI 辅助
本文针对社会公益场景，提出图智能体RAG的故障链分析及含五接口契约的构造即保证框架，并给出评估议程。
中文摘要 AI 辅助
图智能体检索增强生成将结构化证据与自适应控制器相结合，后者能够规划检索、遍历关系、验证中间主张、委派子任务并使用工具。当答案依赖于跨文档、实体、时间或机构的关系时，这种组合非常有用，但它也产生了耦合的故障路径：图构建中的缺陷可能成为检索到的证据，改变后续的控制决策，并向具有重大影响的最终结果传播。我们考察了在社会公益场景中应如何设计和评估此类系统，在这些场景中，新鲜度、授权、可追溯性、监督和追索权与答案质量同等重要。我们按图基座、图生命周期、智能体功能、协调模式和权限边界对文献进行组织，并区分基于图的检索与依赖观测的图控制。然后，我们将已报告的风险综合为一条从证据到行动的故障链，并提出一个构造即保证的蓝图，该蓝图包含五个接口契约，分别针对证据、检索、推理、能力与委派以及结果。这些契约在系统边界上明确规定了来源、时间有效性、授权、不确定性和可恢复性。一个示例性的公共利益信息设计展示了该框架如何约束图结构、权限、弃权（不执行）和操作权限。最后，我们推导出一项评估议程，涵盖图断言、轨迹、主张、协调和结果。
英文摘要
Graph-agentic retrieval-augmented generation combines structured evidence with adaptive controllers that can plan retrieval, traverse relations, verify intermediate claims, delegate subtasks, and use tools. This combination is useful when answers depend on relations across documents, entities, time, or institutions, but it also creates coupled failure paths: a defect in graph construction can become retrieved evidence, alter later control decisions, and propagate toward a consequential outcome. We examine how such systems should be designed and evaluated for social-good settings in which freshness, authorization, traceability, oversight, and recourse matter alongside answer quality. We organize the literature by graph substrate, graph lifecycle, agent function, coordination pattern, and authority boundary, and distinguish graph-based retrieval from observation-dependent graph control. We then synthesize reported risks as an evidence-to-action failure chain and propose an assurance-by-construction blueprint comprising five interface contracts for evidence, retrieval, reasoning, capability and delegation, and outcome. These contracts make provenance, temporal validity, authorization, uncertainty, and recoverability explicit at system boundaries. An illustrative public-benefit information design shows how the framework constrains graph structure, permissions, abstention, and operating authority. Finally, we derive an evaluation agenda spanning graph assertions, trajectories, claims, coordination, and outcomes.
发表机构
- IIITDM Kancheepuram（印度信息技术与设计制造学院坎奇普拉姆校区）
机构由 AI 辅助整理，请以论文原文为准。
