PersonalAI 2.0：用规划机制增强个性化 LLM 智能体的知识图谱遍历与检索
PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
PersonalAI 2.0（PAI-2）框架通过提取实体、匹配图顶点和生成线索查询，实现自适应迭代的信息搜索，以增强 LLM 对外部知识图谱的利用。
Authors:Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov, Alina Bogdanova, Mikhail Belkin, Ekaterina Lisitsyna, Artyom Sosedka, Victoria Dochkina, Ruslan Kostoev, Ilia Perepechkin, Evgeny Burnaev
Abstract:We introduce PersonalAI 2.0 (PAI-2), a novel framework designed to enhance LLM-based systems through integration of external knowledge graphs (KGs). The proposed approach addresses key limitations of existing Graph Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage pipeline. The central point of the PAI-2 design is its ability to perform adaptive, iterative information search, guided by extracted entities, matched graph vertices and generated clue-queries. Conducted evaluation on five benchmarks (Natural Questions, TriviaQA, HotpotQA, 2WikiMultihopQA and MuSiQue) demonstrates an improvement in the factual correctness of generated answers compared to baseline methods (LightRAG, RAPTOR, HippoRAG 2 and PAI-1). PAI-2 achieves a 9 percentage points (pp) average gain by LLM-as-a-Judge on 2WikiMultihopQA and MuSiQue benchmarks, and attains comparable accuracy to HippoRAG 2 on the TriviaQA and HotpotQA benchmarks with Qwen2.5 7B and multilingual-e5-large reflecting its effectiveness in reducing hallucination rates and increasing recall. We show that enabled search plan enhancement mechanism gain in average a 18 pp boost compared to disabled one by LLM-as-a-Judge across five benchmarks. In addition, an ablation study reveals that PAI-2 achieves superior result on the MINE-1 benchmark, obtaining an 89\% information-retention score with Qwen2.5 7B and multilingual-e5-large. Collectively, these findings underscore the potential of PAI-2 to serve as a reusable component for personalized AI applications, which require context-aware knowledge-representation and reasoning capabilities. The source code of PAI-2 is available at the following link: this https URL.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.13481 [cs.CL] |
| (or arXiv:2605.13481v4 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13481 arXiv-issued DOI via DataCite |
Submission history
From: Mikhail Menschikov [view email]
[v1]
Wed, 13 May 2026 13:06:30 UTC (6,109 KB)
[v2]
Thu, 17 Sep 2026 05:06:02 UTC (7,444 KB)
[v3]
Fri, 18 Sep 2026 10:22:40 UTC (7,444 KB)
[v4]
Wed, 21 Oct 2026 13:13:03 UTC (7,197 KB)
来源：arXiv cs.CL · arxiv.org