Cover Image

Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Yuqi, Zhong, Yi, Zhang, Jintian, Zhang, Ziheng, Qiao, Shuofei, Luo, Yujie, Du, Lun, Zheng, Da, Zhang, Ningyu, Chen, Huajun
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Information Retrieval Machine Learning Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LightThinker: Thinking Step-by-Step Compression
by: Zhang, Jintian, et al.
Published: (2025)

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
by: Qiu, Zhisong, et al.
Published: (2026)

InnoGym: Benchmarking the Innovation Potential of AI Agents
by: Zhang, Jintian, et al.
Published: (2025)

LightThinker++: From Reasoning Compression to Memory Management
by: Zhu, Yuqi, et al.
Published: (2026)

Can We Predict Before Executing Machine Learning Agents?
by: Zheng, Jingsheng, et al.
Published: (2026)

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
by: Ren, Baochang, et al.
Published: (2025)

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science
by: Ou, Yixin, et al.
Published: (2025)

StructMem: Structured Memory for Long-Horizon Behavior in LLMs
by: Xu, Buqiang, et al.
Published: (2026)

What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations
by: Luo, Yujie, et al.
Published: (2025)

AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
by: Qiao, Shuofei, et al.
Published: (2024)

LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
by: Zhu, Yuqi, et al.
Published: (2023)

InstructIE: A Bilingual Instruction-based Information Extraction Dataset
by: Gui, Honghao, et al.
Published: (2023)

SkillX: Automatically Constructing Skill Knowledge Bases for Agents
by: Wang, Chenxi, et al.
Published: (2026)

A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine
by: Shi, Yunxiao, et al.
Published: (2024)

Making Language Models Better Tool Learners with Execution Feedback
by: Qiao, Shuofei, et al.
Published: (2023)

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
by: Zhu, Yuqi, et al.
Published: (2024)

Memp: Exploring Agent Procedural Memory
by: Fang, Runnan, et al.
Published: (2025)

Agent Planning with World Knowledge Model
by: Qiao, Shuofei, et al.
Published: (2024)

Scaling Generalist Data-Analytic Agents
by: Qiao, Shuofei, et al.
Published: (2025)

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification
by: Wang, Zhensheng, et al.
Published: (2026)

Multi-Agent Video Recommenders: Evolution, Patterns, and Open Challenges
by: Ranganathan, Srivaths, et al.
Published: (2026)

Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation
by: Wang, Jinze, et al.
Published: (2026)

Benchmarking Agentic Workflow Generation
by: Qiao, Shuofei, et al.
Published: (2024)

AgentSearchBench: A Benchmark for AI Agent Search in the Wild
by: Wu, Bin, et al.
Published: (2026)

SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
by: Qiao, Shuofei, et al.
Published: (2026)

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
by: Wu, Chuanjie, et al.
Published: (2026)

Osprey: Production-Ready Agentic AI for Safety-Critical Control Systems
by: Hellert, Thorsten, et al.
Published: (2025)

Behind the Prompt: The Agent-User Problem in Information Retrieval
by: Zerhoudi, Saber, et al.
Published: (2026)

CogPlanner: Unveiling the Potential of Agentic Multimodal Retrieval Augmented Generation with Planning
by: Yu, Xiaohan, et al.
Published: (2025)

TWICE: An LLM Agent Framework for Simulating Personalized User Tweeting Behavior with Long-term Temporal Features
by: Jin, Bingrui, et al.
Published: (2025)

LLMGreenRec: LLM-Based Multi-Agent Recommender System for Sustainable E-Commerce
by: Nguyen, Hao N., et al.
Published: (2026)

Ultra Low-Cost Two-Stage Multimodal System for Non-Normative Behavior Detection
by: Lu, Albert, et al.
Published: (2024)

Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis
by: Liang, Jason, et al.
Published: (2026)

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
by: Zhang, Jintian, et al.
Published: (2024)

AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
by: Jin, Jiarui, et al.
Published: (2026)

Knowledge Graph Enhanced Language Agents for Recommendation
by: Guo, Taicheng, et al.
Published: (2024)

LightMem: Lightweight and Efficient Memory-Augmented Generation
by: Fang, Jizhan, et al.
Published: (2025)

NutriOrion: A Hierarchical Multi-Agent Framework for Personalized Nutrition Intervention Grounded in Clinical Guidelines
by: Wu, Junwei, et al.
Published: (2026)

Minimizing Regret in Billboard Advertisement under Zonal Influence Constraint
by: Ali, Dildar, et al.
Published: (2024)

Nested Browser-Use Learning for Agentic Information Seeking
by: Li, Baixuan, et al.
Published: (2025)