AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs

• URL: http://arxiv.org/abs/2607.09092v1
• Date: Fri, 10 Jul 2026 04:22:34 GMT
• Title: AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs
• Abstract summary: AgentKGV integrates dynamic routing and iterative query rewriting to verify knowledge graphs reliably at industrial scale.<n>Two-stage training strategy transfers reasoning ability from a large teacher model into a small model for stable query rewriting and reasoning.<n>Our framework improves macro-F1 over single-turn RAG by 5.5 %p, and two-stage training does it further by 9.4 %p.
• Score: 15.215103223762364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge graphs (KGs) are often automatically constructed from large-scale corpora, but they inevitably contain factual errors due to noisy sources and extraction failures, and verifying them reliably at industrial scale remains a critical challenge. To address this, we propose AgentKGV, the Agentic LLM-RAG framework for KG fact Verification, that integrates dynamic routing and iterative query rewriting, which handles surface-form mismatch in document-level retrieval. To make this framework more accurate and cost-efficient for industrial deployment, we further introduce a two-stage training strategy: turn-level distillation-based SFT that transfers reasoning ability from a large teacher model into a small model for stable query rewriting and reasoning, and trajectory-level GRPO that optimizes the search policy to reduce unnecessary retrieval at scale. On the long-tail-predicate split of the open-domain T-REx benchmark, our framework improves macro-F1 over single-turn RAG by 5.5 \%p, and two-stage training does it further by 9.4 \%p. GRPO also cuts the average number of search calls from 3.24 to 1.63 without lowering accuracy.

Related papers

• GR2 Technical Report [58.300302585605095]
  GR2 is an end-to-end framework that combines mid-training on semantic IDs with reasoning-trace distilled from a stronger teacher.<n> GR2 delivers +18.7% R@1, +7.1% R@3, and +9.6% N@3 over legacy baselines on industrial-scale traffic.
  arXiv  Detail & Related papers  (2026-06-30T17:22:22Z)
• Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking [18.698122955613584]
  InSemRAG is a framework for a retrieval-augmented generation (RAG) system.<n>IAR implements a dynamic hybrid retrieval method that adaptively weights the retrieval channels based on the query intent.<n>SPC performs detection and reparation to the damaged evidence chunks to preserve the semantic integrity.<n>Our method achieves significant gains on multi-hop and evidence-sensitive tasks, with a 2.65-point improvement in F1 on HotPotQA and a 1.5-point increase in accuracy on FEVER.
  arXiv  Detail & Related papers  (2026-05-31T13:42:36Z)
• BLAgent: Agentic RAG for File-Level Bug Localization [2.2917707112773593]
  BLAgent is a novel agentic RAG framework for file-level bug localization.<n> BLAgent attains over 78% Top-1 accuracy with open-source models.<n> BLAgent improves end-to-end repair success by over 20%.
  arXiv  Detail & Related papers  (2026-05-18T07:20:13Z)
• SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding [41.98672557723593]
  We introduce SWEQA-Pro, a benchmark constructed from diverse, long-tail repositories with executable environments.<n>We also propose a scalable synthetic data pipeline that powers a two-stage training recipe: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning from AI Feedback (RLAIF)<n> Empirically, a Qwen3-8B model trained with our recipe surpasses GPT-4o by 2.3 points on SWE-QA-Pro and substantially narrows the gap to state-of-the-art models.
  arXiv  Detail & Related papers  (2026-03-17T05:12:48Z)
• SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation [24.019381388104236]
  We propose SCoTER, a unified framework that treats pattern discovery and structure-aware transfer as a jointly optimized problem.<n>Specifically, SCoTER operationalizes this through two synergistic components: a GVM pipeline for automated pattern discovery and a structure-preserving integration architecture that transfers stepwise logic to efficient models.
  arXiv  Detail & Related papers  (2025-11-24T03:00:04Z)
• Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction [0.18907108368038208]
  Current methods lack the adaptive policies needed to dynamically debug queries based on real-time execution feedback.<n>This paper introduces a novel agentic framework where an LLM learns a resilient policy for the sequential process of iterative SPARQL construction.<n>We show that a compact 3B- parameter model, trained exclusively via outcome-driven Reinforcement Learning (GRPO), can learn effective policies for this task.
  arXiv  Detail & Related papers  (2025-11-14T08:44:58Z)
• 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)
• MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval [50.30107119622642]
  Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data.<n>Retrieval-Augmented Generation (RAG) addresses this issue by grounding LLMs in external knowledge.<n>MarAG-R1 is a reinforcement-learned multi-tool RAG framework that enables LLMs to dynamically coordinate multiple retrieval mechanisms.
  arXiv  Detail & Related papers  (2025-10-31T15:51:39Z)
• GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning.<n>Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate.<n>We propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision.
  arXiv  Detail & Related papers  (2025-06-19T08:49:13Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning [56.887047551101574]
  We present DS-Agent, a novel framework that harnesses large language models (LLMs) agent and case-based reasoning (CBR) In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which can flexibly capitalize on the expert knowledge from Kaggle. In the deployment stage, DS-Agent implements a low-resource deployment stage with a simplified CBR paradigm, significantly reducing the demand on foundational capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-02-27T12:26:07Z)

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.