Graph-Agentic RAG for Social Good
Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction
The framework provides concrete contracts for building trustworthy AI systems in social-good settings, addressing traceability and oversight concerns.
This paper examines graph-agentic retrieval-augmented generation systems that combine structured evidence with adaptive controllers.
The research identifies coupled failure paths where defects in graph construction can propagate to consequential outcomes.
The authors propose an assurance-by-construction blueprint with five interface contracts for evidence, retrieval, reasoning, capability and delegation, and outcome.
Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction
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.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Graph-Agentic RAG, RAG, graph neural networks.
Source attribution: curated from arXiv cs.AI (@Vijay Bommireddy, Raviteja Bommireddy).
