PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
Summary
PersonalAI 2.0 introduces a framework that enhances LLM-based systems by integrating external knowledge graphs with dynamic multistage query processing and adaptive planning mechanisms, achieving reductions in hallucination rates and improved precision across multiple benchmarks.
View Cached Full Text
Cached at: 05/14/26, 12:18 PM
Paper page - PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
Source: https://huggingface.co/papers/2605.13481 Authors:
,
,
,
,
,
,
,
,
,
Abstract
PersonalAI 2.0 enhances LLM-based systems through external knowledge graph integration with dynamic multistage query processing and adaptive information search mechanisms.
We introduce PersonalAI 2.0 (PAI-2), a novel framework, designed to enhancelarge language model(LLM) based systems through integration of externalknowledge graphs(KG). The proposed approach addresses key limitations of existingGraph Retrieval-Augmented Generation(GraphRAG) methods by incorporating a dynamic, multistage query processing pipeline. The central point of 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 over six benchmarks (Natural Questions, TriviaQA, HotpotQA, 2WikiMultihopQA, MuSiQue and DiaASQ) demonstrates improvement in factual correctness of generating answers compared to analogues methods (LightRAG, RAPTOR, and HippoRAG 2). PAI-2 achieves 4% average gain byLLM-as-a-Judgeacross four benchmarks, reflecting its effectiveness in reducing hallucination rates and increasing precision. We show that use ofgraph traversal algorithms(e.g.BeamSearch,WaterCircles) gain superior results compared to standard flatten retriever on average 6%, while enabledsearch plan enhancementmechanism gain 18% boost compared to disabled one byLLM-as-a-Judgeacross six datasets. In addition, ablation study reveals that PAI-2 achieves the SOTA result on MINE-1 benchmark, achieving 89%information-retention score, using LLMs from 7-14B tiers. Collectively, these findings underscore the potential of PAI-2 to serve as a foundational model for next-generation personalized AI applications, requiring scalable, context-aware knowledge representation and reasoning capabilities.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.13481
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.13481 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.13481 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.13481 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
IBM Research explores how agent logic—software primitives like knowledge graphs and program analysis—can guide LLM-based agents to efficiently handle complex enterprise workflows, reducing hallucinations and costs while improving outcomes.
Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
This paper introduces Grounded Iterative Language Planning (GILP), a method that combines a small parameterized world model with LLM-based reasoning to reduce hallucination propagation in LLM agents. Experiments show GILP reduces hallucinated-state rate from 0.176 to 0.035 and raises task success from 0.668 to 0.838 on graph-structured planning benchmarks.
PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection
This paper identifies the planning phase in multi-agent LLM systems as a critical attack surface, introducing PlanFlip—a framework of four planning-phase prompt injection attacks that achieve cascade amplification across downstream agents. Evaluations on nine frontier LLMs reveal that stronger models like GPT-5 are more vulnerable, while reasoning-augmented models like DeepSeek-R1 resist attacks, and proposed defenses achieve high detection rates.
Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment
MetaKGEnrich is a fully automated pipeline that uses graph metrics to detect knowledge gaps in LLM applications, retrieves web evidence, and improves answer quality by 80-87% across three benchmark datasets.
APeB: Benchmarking Personalization Ability of Large Language Model Agents
Introduces APeB, a benchmark for evaluating personalization in LLM agents, focusing on inferring user intent and preferences from raw queries and interaction histories. Finds that current models struggle with early-stage queries and that history-aware refinement can help.