发表机构
The Chinese University of Hong Kong; Wuhan University of Technology; The Hong Kong University of Science and Technology; Huawei Noah’s Ark Lab（香港中文大学; 武汉理工大学; 香港科技大学; 华为诺亚方舟实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ACE-GraphRAG针对分层GraphRAG的表示-推理差距，提出两种自适应上下文策略，在多任务基准上优于现有RAG和GraphRAG基线，验证了动态上下文构建策略的有效性。
AI 中文摘要
分层图检索增强生成（GraphRAG）以多粒度层级组织语料库知识，但固定上下文构建可能无法将这些多分辨率表示转换为适配当前查询的上下文，我们将这种不匹配称为表示-推理差距。我们提出ACE-GraphRAG，这是一种推理时的上下文策略层，用于补充和调整初始上下文以生成内容。ACE-GraphRAG将上下文构建表述为针对感知差距的细化、检索分支和任务条件适配的策略。并行差异检索从面向深度的事实分支和面向广度的语义分支获取补充证据，这些证据增量会在保留来源和抽象层级的前提下与初始上下文合并。Full-ACE在每个任务族中统一应用完整策略，而Adaptive-ACE则为单个查询选择特定于任务和拓扑的策略。我们在HotpotQA、2WikiMultiHopQA以及四个UltraDomain子集上针对多跳问答和查询聚焦摘要任务评估ACE-GraphRAG，Full-ACE在两个任务族上均优于所评估的RAG和GraphRAG基线，而Adaptive-ACE进一步提升了多跳问答性能，且在所有四个UltraDomain子集上均比Full-ACE更受青睐。消融实验和拓扑分析支持将上下文构建视为依赖查询和任务的推理策略，而非固定过程。
英文摘要
Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context construction may fail to translate these multi-resolution representations into a context suited to the current query. We identify this mismatch as the representation--inference gap. We propose Agentic Context Engineering for Hierarchical GraphRAG (ACE-GraphRAG), an inference-time context policy layer that supplements and adapts the initial context for generation. ACE-GraphRAG formulates context construction as a policy over gap-aware refinement, retrieval branches, and task-conditioned adaptation. Parallel Differential Retrieval acquires supplementary evidence from depth-oriented factual and breadth-oriented semantic branches. These evidence increments are consolidated with the initial context while preserving provenance and abstraction levels. Full-ACE applies the full policy uniformly within each task family, whereas Adaptive-ACE selects task- and topology-specific policies for individual queries. We evaluate ACE-GraphRAG on HotpotQA, 2WikiMultiHopQA, and four UltraDomain subsets across multi-hop QA and query-focused summarization. Full-ACE outperforms the evaluated RAG and GraphRAG baselines across both task families, while Adaptive-ACE further improves multi-hop QA and is preferred over Full-ACE on all four UltraDomain subsets. Ablation and topology analyses support treating context construction as a query- and task-dependent inference policy rather than a fixed procedure.
CommentsWithdrawn because the manuscript was posted prematurely before completion of the required internal review and release authorization
