PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents

• URL: http://arxiv.org/abs/2605.13481v1
• Date: Wed, 13 May 2026 13:06:30 GMT
• Title: PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
• Abstract summary: We introduce PersonalAI 2.0 (PAI-2), a novel framework to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG)<n>The proposed approach addresses key limitations of existing Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage query processing pipeline.<n>We show that use of graph algorithms (e.g. BeamSearch, WaterCircles) gain superior results compared to standard flatten retriever on average 6%, while enabled search plan enhancement mechanism gain 18% boost compared to disabled one by LLM-as-a-Judge across six datasets.
• Score: 53.369140518949656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce PersonalAI 2.0 (PAI-2), a novel framework, designed to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG). The proposed approach addresses key limitations of existing Graph 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 by LLM-as-a-Judge across four benchmarks, reflecting its effectiveness in reducing hallucination rates and increasing precision. We show that use of graph traversal algorithms (e.g. BeamSearch, WaterCircles) gain superior results compared to standard flatten retriever on average 6%, while enabled search plan enhancement mechanism gain 18% boost compared to disabled one by LLM-as-a-Judge across 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.

Related papers

• SCIR: A Self-Correcting Iterative Refinement Framework for Enhanced Information Extraction Based on Schema [14.451987449547294]
  Large language Model (LLM)-powered information extraction systems have shown impressive capabilities.<n>We propose a novel universal IE paradigm, the Self-Correcting Iterative Refinement (SCIR) framework.<n>We show that SCIR outperforms state-of-the-art IE methods across three key tasks.
  arXiv  Detail & Related papers  (2025-12-13T14:07:25Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Efficient Knowledge Graph Construction and Retrieval from Unstructured Text for Large-Scale RAG Systems [0.06597195879147556]
  We propose a scalable and cost-efficient framework for deploying Graph-based Retrieval Augmented Generation (GraphRAG) in enterprise environments.<n>These results validate the feasibility of deploying GraphRAG systems in real-world, large-scale enterprise applications.
  arXiv  Detail & Related papers  (2025-07-04T00:05:55Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning [31.796328505473305]
  We propose UI-R1, the first framework to explore how rule-based RL can enhance the reasoning capabilities of multimodal large language models (MLLMs) for GUI action prediction tasks.<n>Specifically, UI-R1 introduces a novel rule-based action reward, enabling model optimization via policy-based algorithms such as Group Relative Policy Optimization (GRPO)<n>For efficient training, we curate a small yet high-quality dataset of 136 challenging tasks, encompassing five common action types on mobile devices.
  arXiv  Detail & Related papers  (2025-03-27T15:39:30Z)
• ROGRAG: A Robustly Optimized GraphRAG Framework [45.947928801693266]
  Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph for dynamic retrieval.<n>Existing pipelines involve complex engineering, making it difficult to isolate the impact of individual components.<n>We introduce ROGRAG, a Robustly Optimized GraphRAG framework, which integrates dual-level with logic form retrieval methods to improve robustness without increasing computational cost.
  arXiv  Detail & Related papers  (2025-03-09T06:20:24Z)
• Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning [55.6623318085391]
  Recent large language model (LLM) reasoning suffers from limited domain knowledge, susceptibility to hallucinations, and constrained reasoning depth.<n>This paper presents the first investigation into integrating step-wise knowledge graph retrieval with step-wise reasoning.<n>We propose KG-RAR, a framework centered on process-oriented knowledge graph construction, a hierarchical retrieval strategy, and a universal post-retrieval processing and reward model.
  arXiv  Detail & Related papers  (2025-03-03T15:20:41Z)
• GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation [83.72561905487447]
  We introduce GFM-RAG, a novel graph foundation model (GFM) for retrieval augmented generation.<n>GFM-RAG is powered by an innovative graph neural network that reasons over graph structure to capture complex query-knowledge relationships.<n>It achieves state-of-the-art performance while maintaining efficiency and alignment with neural scaling laws.
  arXiv  Detail & Related papers  (2025-02-03T07:04:29Z)
• Explainable AI-aided Feature Selection and Model Reduction for DRL-based V2X Resource Allocation [18.49800990388549]
  Artificial intelligence (AI) is expected to significantly enhance radio resource management (RRM) in sixth-generation (6G) networks.<n>The lack of explainability in complex deep learning (DL) models poses a challenge for practical implementation.<n>This paper proposes a novel explainable AI (XAI)-based framework for feature selection and model complexity reduction.
  arXiv  Detail & Related papers  (2025-01-23T10:55:38Z)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.