Chart Deep Research in LVLMs via Parallel Relative Policy Optimization

• URL: http://arxiv.org/abs/2603.06677v1
• Date: Tue, 03 Mar 2026 14:50:33 GMT
• Title: Chart Deep Research in LVLMs via Parallel Relative Policy Optimization
• Abstract summary: Current chart data intelligence exhibits significant limitations in deep research capabilities.<n>We propose PRPO, which performs parallel optimization across reward dimensions and capability across data types.<n>We construct MCDR-Bench based on the error uniqueness principle," transforming subjective generation assessment into objective error identification.
• Score: 39.633965546999605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid advancement of data science, charts have evolved from simple numerical presentation tools to essential instruments for insight discovery and decision-making support. However, current chart data intelligence exhibits significant limitations in deep research capabilities, with existing methods predominantly addressing shallow tasks such as visual recognition or factual question-answering, rather than the complex reasoning and high-level data analysis that deep research requires. This limitation stems from two primary technical bottlenecks: at the training level, existing post-training techniques exhibit deficiencies in handling multi-dimensional reward signal interference and heterogeneous data gradient conflicts, preventing models from achieving balanced development across multiple capability dimensions; at the evaluation level, current methods remain limited to factual retrieval and basic computation, failing to assess end-to-end analytic reasoning and other deep research capabilities. To address the training challenge, we propose PRPO, which performs parallel optimization across reward dimensions and capability partitioning across data types, effectively disentangling conflicts between heterogeneous data and multi-dimensional reward signals while ensuring optimization stability. For the evaluation challenge, we construct MCDR-Bench based on the ``error uniqueness principle," transforming subjective generation assessment into objective error identification through controllable error injection, enabling quantifiable evaluation of deep research capabilities. Experimental validation confirms that the proposed PRPO and MCDR-Bench jointly establish a unified framework that systematically advances chart deep research through enhanced collaborative training and objective evaluation.

Related papers

• Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement [81.27196033392559]
  We propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis.<n>COME injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training.<n>Our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline.
  arXiv  Detail & Related papers  (2026-07-24T04:26:47Z)
• An explainable hybrid deep learning-enabled intelligent fault detection and diagnosis approach for automotive software systems validation [2.7082111912355877]
  An intelligent model was developed to analyze the recordings from the real-time validation process of ASSs.<n>The employment of explainable AI techniques, i.e., IGs, DeepLIFT, Gradient SHAP, and DeepLIFT SHAP, was instrumental in enabling model adaptation and facilitating the root cause analysis (RCA)
  arXiv  Detail & Related papers  (2026-03-09T09:46:28Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• Rethinking Evaluation of Infrared Small Target Detection [105.59753496831739]
  This paper introduces a hybrid-level metric incorporating pixel- and target-level performance, proposing a systematic error analysis method, and emphasizing the importance of cross-dataset evaluation.<n>An open-source toolkit has be released to facilitate standardized benchmarking.
  arXiv  Detail & Related papers  (2025-09-21T02:45:07Z)
• Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot [44.336297829718795]
  We introduce CATE-B, an open-source co-pilot system that uses large language models (LLMs) within an agentic framework to guide users through treatment effect estimation.<n>CATE-B assists in (i) constructing a structural causal model via causal discovery and LLM-based edge orientation, (ii) identifying robust adjustment sets through a novel Minimal Uncertainty Adjustment Set criterion, and (iii) selecting appropriate regression methods tailored to the causal structure and dataset characteristics.
  arXiv  Detail & Related papers  (2025-08-14T12:20:51Z)
• Anomaly Detection and Generation with Diffusion Models: A Survey [51.61574868316922]
  Anomaly detection (AD) plays a pivotal role across diverse domains, including cybersecurity, finance, healthcare, and industrial manufacturing.<n>Recent advancements in deep learning, specifically diffusion models (DMs), have sparked significant interest.<n>This survey aims to guide researchers and practitioners in leveraging DMs for innovative AD solutions across diverse applications.
  arXiv  Detail & Related papers  (2025-06-11T03:29:18Z)
• The role of data partitioning on the performance of EEG-based deep learning models in supervised cross-subject analysis: a preliminary study [37.69303106863453]
  Deep learning is advancing the analysis of electroencephalography (EEG) data by effectively discovering highly nonlinear patterns.<n>No comprehensive guidelines for proper data partitioning and cross-validation exist in the domain.<n>This paper thoroughly investigates the role of data partitioning and cross-validation in evaluating EEG deep learning models.
  arXiv  Detail & Related papers  (2025-05-19T12:05:28Z)
• Graph Neural Network-Driven Hierarchical Mining for Complex Imbalanced Data [0.8246494848934447]
  This study presents a hierarchical mining framework for high-dimensional imbalanced data.<n>By constructing a structured graph representation of the dataset and integrating graph neural network embeddings, the proposed method effectively captures global interdependencies among samples.<n> Empirical evaluations across multiple experimental scenarios validate the efficacy of the proposed approach.
  arXiv  Detail & Related papers  (2025-02-06T06:26:41Z)
• Precision Adaptive Imputation Network : An Unified Technique for Mixed Datasets [0.0]
  This study introduces the Precision Adaptive Imputation Network (PAIN), a novel algorithm designed to enhance data reconstruction.<n>PAIN employs a tri-step process that integrates statistical methods, random forests, and autoencoders, ensuring balanced accuracy and efficiency in imputation.<n>The findings highlight PAIN's superior ability to preserve data distributions and maintain analytical integrity, particularly in complex scenarios where missingness is not completely at random.
  arXiv  Detail & Related papers  (2025-01-18T06:22:27Z)
• Data Collaboration Analysis with Orthonormal Basis Selection and Alignment [2.928964540437144]
  Data Collaboration (DC) enables multiple parties to jointly train a model without exposing their private datasets.<n>Existing theory asserts that any target basis spanning the same subspace as the secret bases should suffice.<n>We introduce Orthonormal Data Collaboration (ODC), a novel DC framework that explicitly enforces orthonormality constraints on both the secret and target bases.
  arXiv  Detail & Related papers  (2024-03-05T08:52:16Z)
• Offline Reinforcement Learning with Instrumental Variables in Confounded Markov Decision Processes [93.61202366677526]
  We study the offline reinforcement learning (RL) in the face of unmeasured confounders. We propose various policy learning methods with the finite-sample suboptimality guarantee of finding the optimal in-class policy.
  arXiv  Detail & Related papers  (2022-09-18T22:03:55Z)

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.