Imagen de Portada

LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rahman, Mizanur, Bhuiyan, Amran, Islam, Mohammed Saidul, Laskar, Md Tahmid Rahman, Mahbub, Ridwan, Masry, Ahmed, Joty, Shafiq, Hoque, Enamul
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?
por: Laskar, Md Tahmid Rahman, et al.
Publicado: (2025)

Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization
por: Rahman, Mizanur, et al.
Publicado: (2026)

From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text
por: Mahbub, Ridwan, et al.
Publicado: (2025)

Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text
por: Rahman, Mizanur, et al.
Publicado: (2025)

Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices
por: Laskar, Md Tahmid Rahman, et al.
Publicado: (2025)

Lost in Translation: Do LVLM Judges Generalize Across Languages?
por: Laskar, Md Tahmid Rahman, et al.
Publicado: (2026)

The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language Models
por: Mahbub, Ridwan, et al.
Publicado: (2025)

Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs
por: Islam, Mohammed Saidul, et al.
Publicado: (2024)

DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
por: Islam, Mohammed Saidul, et al.
Publicado: (2024)

DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards
por: Kartha, Aaryaman, et al.
Publicado: (2025)

DATAREEL: Automated Data-Driven Video Story Generation with Animations
por: Mahbub, Ridwan, et al.
Publicado: (2026)

ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering
por: Masry, Ahmed, et al.
Publicado: (2025)

Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions
por: Hoque, Enamul, et al.
Publicado: (2024)

Evolution of ReID: From Early Methods to LLM Integration
por: Bhuiyan, Amran, et al.
Publicado: (2025)

A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations
por: Laskar, Md Tahmid Rahman, et al.
Publicado: (2024)

ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
por: Masry, Ahmed, et al.
Publicado: (2024)

BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP
por: Kabir, Mohsinul, et al.
Publicado: (2023)

ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
por: Masry, Ahmed, et al.
Publicado: (2024)

Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges
por: Wang, Jiajia, et al.
Publicado: (2024)

Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge
por: Laskar, Md Tahmid Rahman, et al.
Publicado: (2025)

Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models
por: Islam, Shayekh Bin, et al.
Publicado: (2024)

Future Mining: Learning for Safety and Security
por: Rahman, Md Sazedur, et al.
Publicado: (2026)

State and politics in the transitional era of globalization: Twisting and turning toward authoritarian and hybrid regimes
por: Hafijur Rahman, et al.
Publicado: (2024)

Impact of Salinisation on the Neighbour-based Spatial Diversity of Tree Species in the Sundarbans Mangrove of Bangladesh
por: Rahman, Md Mizanur
Publicado: (2026)

A Comprehensive Evaluation of Large Language Models on Benchmark Biomedical Text Processing Tasks
por: Jahan, Israt, et al.
Publicado: (2023)

Evaluating the Effectiveness of Cost-Efficient Large Language Models in Benchmark Biomedical Tasks
por: Jahan, Israt, et al.
Publicado: (2025)

Review-based Recommender Systems: A Survey of Approaches, Challenges and Future Perspectives
por: Hasan, Emrul, et al.
Publicado: (2024)

A Heterogeneous Two-Stream Framework for Video Action Recognition with Comparative Fusion Analysis
por: Rahaman, Md. Afzalur, et al.
Publicado: (2026)

A Review of Floating Photovoltaic Systems: Prospects, Challenges, and Sustainability Considerations
por: Moslema Hoque Oeishee, et al.
Publicado: (2026)

Digital Labor: Challenges, Ethical Insights, and Implications
por: Rahman, ATM Mizanur, et al.
Publicado: (2025)

SparseTransX: Efficient Training of Translation-Based Knowledge Graph Embeddings Using Sparse Matrix Operations
por: Anik, Md Saidul Hoque, et al.
Publicado: (2025)

Vision-Based Localization and LLM-based Navigation for Indoor Environments
por: Rahimi, Keyan, et al.
Publicado: (2025)

Toward Generalized Detection of Synthetic Media: Limitations, Challenges, and the Path to Multimodal Solutions
por: Hussain, Redwan, et al.
Publicado: (2025)

Assessing Generalisation Capability of Machine Learning Models for Intrusion Detection
por: Hossain, Md Zakir, et al.
Publicado: (2026)

Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care
por: Badawi, Abeer, et al.
Publicado: (2025)

Automated Toll Management System Using RFID and Image Processing
por: Ahmed, Raihan, et al.
Publicado: (2024)

Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles
por: Haque, Md Wasiul, et al.
Publicado: (2025)

DE-KAN: A Kolmogorov Arnold Network with Dual Encoder for accurate 2D Teeth Segmentation
por: Mustakim, Md Mizanur Rahman, et al.
Publicado: (2025)

su2-3d-lgt-metropolis: finite-volume stability and benchmark release for 3D SU(2) lattice gauge theory
por: Miraz, MD Mizanur Rahman
Publicado: (2026)

Grid2Guide: A* Enabled Small Language Model for Indoor Navigation
por: Haque, Md. Wasiul, et al.
Publicado: (2025)