DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning

• URL: http://arxiv.org/abs/2605.10488v1
• Date: Mon, 11 May 2026 12:48:31 GMT
• Title: DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
• Abstract summary: Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in downstream tasks.<n>Yet their quality is systematically limited by emphincompleteness, emphincorrectness, and emphredundancy
• Score: 60.35032268606525
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstream tasks. Yet their quality is systematically limited by \emph{incompleteness}, \emph{incorrectness}, and \emph{redundancy}, manifested as missing evidence or cross-document links, low-confidence or imprecise claims, and ambiguous or coreference resolution issues. Such defects compound under iterative use, degrading retrieval fidelity and downstream task performance. We present \textbf{DeepRefine}, a general LLM-based reasoning model for \emph{agent-compiled knowledge refinement} that improves the quality of any pre-constructed knowledge bases with user queries to make it more suitable for the downstream tasks. DeepRefine performs multi-turn interactions with the knowledge base and conducts abductive diagnosis over interaction history, localizes likely defects, and executes targeted refinement actions for incremental knowledge base updates. To optimize refinement policies of DeepRefine without gold references, we introduce a Gain-Beyond-Draft (GBD) reward and train the reasoning process end-to-end via reinforcement learning. Extensive experiments demonstrate consistent downstream gains over strong baselines.

Related papers

• GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion [2.729876880765472]
  Large language models frequently generate plausible but ungrounded claims.<n>We introduce GRACE, a framework that deconstructs responses into atomic claims and grounds them against trusted knowledge priors.<n>We evaluate GRACE across multiple language models and on datasets spanning both general and domain-specific knowledge.
  arXiv  Detail & Related papers  (2026-09-03T20:03:20Z)
• SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering [8.538563236020947]
  SAFE-G is a structure-Aware Faithful Evidence-guided Generation framework.<n>It enables precise evidence localization and trustworthy reasoning.<n>It outperforms prior methods by a margin of 8.9% and 3.5%.
  arXiv  Detail & Related papers  (2026-08-22T06:34:53Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• Hindsight Distillation Reasoning with Knowledge Encouragement Preference for Knowledge-based Visual Question Answering [55.368681418311894]
  Existing Knowledge-based Visual Question Answering (KBVQA) methods either utilize implicit knowledge in multimodal large language models (MLLMs) via in-context learning or explicit knowledge via retrieval augmented generation.<n>We provide a Hindsight Distilled Reasoning (HinD) framework with Knowledge Encouragement Preference Optimization (KEPO)<n> Experiments on OK-VQA and A-OKVQA validate the effectiveness of HinD, showing that HinD with elicited reasoning from 7B-size MLLM achieves superior performance without commercial model APIs or outside knowledge.
  arXiv  Detail & Related papers  (2025-11-14T10:03:23Z)
• TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs [10.861331756147477]
  We propose TruthfulRAG to resolve factual-level knowledge conflicts in RAG systems.<n>TruthfulRAG constructs Knowledge Graphs (KGs) by systematically extracting triples from retrieved content.<n>Extensive experiments reveal that TruthfulRAG outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-13T14:49:44Z)
• Improving Context Fidelity via Native Retrieval-Augmented Reasoning [35.50952279309109]
  Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information.<n>We propose CARE, a novel native retrieval-augmented reasoning framework that teaches LLMs to explicitly integrate in-context evidence within their reasoning process with the model's own retrieval capabilities.<n>Our method requires limited labeled evidence data while significantly enhancing both retrieval accuracy and answer generation performance through strategically retrieved in-context tokens in the reasoning chain.
  arXiv  Detail & Related papers  (2025-09-17T04:28:07Z)
• PropMEND: Hypernetworks for Knowledge Propagation in LLMs [82.99849359892112]
  We present a hypernetwork-based approach for knowledge propagation, named PropMEND.<n>We show almost 2x accuracy on challenging multi-hop questions whose answers are not explicitly stated in the injected fact.<n>We also introduce a new dataset, Controlled RippleEdit, to evaluate the generalization of our hypernetwork.
  arXiv  Detail & Related papers  (2025-06-10T15:44:19Z)
• ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation [91.20492150248106]
  We investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases.<n>We propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs.<n> Experimental results show that ParamMute significantly enhances faithfulness across both CoFaithfulQA and the established ConFiQA benchmark, achieving substantial reductions in reliance on parametric memory.
  arXiv  Detail & Related papers  (2025-02-21T15:50:41Z)
• Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG [24.660769275714685]
  Retrieval-Augmented Generation (RAG) has emerged as a prominent method for incorporating domain knowledge into Large Language Models (LLMs)<n>We present a novel framework that significantly enhances the fine-tuning process by augmenting the training data in two ways -- context augmentation and knowledge paraphrasing.
  arXiv  Detail & Related papers  (2025-02-12T12:39:51Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)

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.