Pith. sign in

REVIEW 23 cited by

Data Interpreter: An LLM Agent For Data Science

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.18679 v4 pith:GHUAI744 submitted 2024-02-28 cs.AI cs.LG

classification cs.AIcs.LG
keywords datainterpretersciencegenerationperformanceproblemstasksachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based agent designed to automatically solve various data science problems end-to-end. Our Data Interpreter incorporates two key modules: 1) Hierarchical Graph Modeling, which breaks down complex problems into manageable subproblems, enabling dynamic node generation and graph optimization; and 2) Programmable Node Generation, a technique that refines and verifies each subproblem to iteratively improve code generation results and robustness. Extensive experiments consistently demonstrate the superiority of Data Interpreter. On InfiAgent-DABench, it achieves a 25% performance boost, raising accuracy from 75.9% to 94.9%. For machine learning and open-ended tasks, it improves performance from 88% to 95%, and from 60% to 97%, respectively. Moreover, on the MATH dataset, Data Interpreter achieves remarkable performance with a 26% improvement compared to state-of-the-art baselines. The code is available at https://github.com/geekan/MetaGPT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration

    cs.AI 2025-11 conditional novelty 6.0 of 10

    A state-aware contrastive router that selects the most relevant agent at each step improves multi-agent LLM accuracy by up to 23.8% while using a fraction of the tokens of fixed-pipeline baselines.

  2. Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence

    cs.CR 2025-09 conditional novelty 6.0 of 10

    LLMs assisting cyber threat intelligence fail mainly due to spurious correlations, contradictory knowledge, and constrained generalization that stem from the threat landscape itself.

  3. Non-programmers Assessing AI-Generated Code: A Case Study of Business Users Analyzing Data

    cs.HC 2025-08 conditional novelty 6.0 of 10

    Non-programmer business users often fail to spot critical mistakes in AI-generated data analyses, even when explicitly warned and incentivized.

  4. MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines

    cs.AI 2025-07 conditional novelty 6.0 of 10

    An LLM-based framework that generates a tool-enabled, traceback-capable multi-agent system as a finite state machine from a task description, outperforming other automatic design methods on four benchmarks.

  5. G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

    cs.MA 2025-06 conditional novelty 6.0 of 10

    G-Memory stores past multi-agent teamwork in a three-tier graph and retrieves it to boost performance on five benchmarks.

  6. Large Language Models for Predictive Analysis: How Far Are They?

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Existing LLMs perform poorly on predictive analysis, with the best model scoring 24.11/28 and most models failing to generate executable code.

  7. MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

    cs.AI 2025-05 conditional novelty 6.0 of 10

    MM-Agent, a multi-stage LLM pipeline with a hierarchical modeling method library, is claimed to outperform prior agents and award-winning human solutions on a new 111-problem MCM/ICM-based mathematical modeling benchmark.

  8. Knowledge-Enhanced Program Repair for Data Science Code

    cs.SE 2025-02 conditional novelty 6.0 of 10

    DSrepair combines a knowledge graph of data science APIs with AST-level bug localization to repair LLM-generated code, fixing more DS-1000 tasks than five baseline repair methods.

  9. Memory Offloading for Large Language Model Inference with Latency SLO Guarantees

    cs.DC 2025-02 conditional novelty 6.0 of 10

    Select-N meets LLM latency SLOs by choosing and continuously adjusting an offloading interval that controls how much model state lives in CPU memory, increasing host memory usage and throughput versus prior offloading...

  10. A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility

    physics.acc-ph 2026-07 conditional novelty 5.5 of 10

    A deployed hybrid RAG for APS operations improves vital-nugget recall over BM25 mainly via cross-encoder reranking; graph and corrective loops help only marginally on a 50-question facility benchmark.

  11. SCTA: An Agentic Framework for Stable and Interpretable Target Gene Discovery from Single-Cell RNA Sequencing

    cs.LG 2026-07 conditional novelty 5.5 of 10

    Decision-centric multi-agent orchestration with structured biological evidence improves repeated-run stability of scRNA-seq therapeutic target gene shortlists versus general agents and ablations.

  12. StarCodex: Dynamic Coding Harness for Starlink Measurement Analysis and Experiment Automation

    eess.SY 2026-07 conditional novelty 5.0 of 10

    StarCodex uses Codex with multi-layer validation to convert evolving Starlink measurements into reusable analysis artifacts, matching supervised baselines while automating the workflow.

  13. AlphaCrafter: Harnessing Multi-Agent Workflows for Cross-Sectional Quantitative Trading

    cs.AI 2026-05 unverdicted novelty 5.0 of 10

    A three-agent LLM pipeline for daily cross-sectional equity trading reports robust returns on CSI 300 and S&P 500, but post-hoc trial filtering, best-backbone selection, and missing code/data undermine the headline.

  14. Large Language Model Agent for Structural Drawing Generation Using ReAct Prompt Engineering and Retrieval Augmented Generation

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A six-stage LLM agent chain converts natural-language descriptions of three beam types into Python code for AutoCAD drawings, with per-step success rates between 77% and 100% over 100 runs.

  15. Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security

    cs.CR 2025-07 conditional novelty 5.0 of 10

    CIRCLE is a 1,260-prompt benchmark that measures how often commercial LLM code interpreters refuse, execute, or time out on resource-exhaustion tasks, revealing large and inconsistent safety gaps.

  16. Agentomics-ML: Autonomous Machine Learning Experimentation Agent for Genomic and Transcriptomic Data

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Agentomics-ML, an LLM-based agent with reflection, produced working classification code for genomic benchmarks in 93% of runs and beat all compared AI methods on six datasets.

  17. SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models

    cs.LG 2025-05 conditional novelty 5.0 of 10

    SimuGen uses specialized LLM agents and a Simulink block database to convert diagram images into executable MATLAB/Simulink code, reporting 94.5% average accuracy on nine examples.

  18. Adaptive Plan-Execute Framework for Smart Contract Security Auditing

    cs.CR 2025-05 reject novelty 5.0 of 10

    SmartAuditFlow claims 100% detection on a standard smart contract benchmark and all 13 tested CVEs via a plan-execute LLM workflow, though the supporting evaluation has major reproducibility and validation gaps.

  19. DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation

    cs.AI 2025-05 conditional novelty 5.0 of 10

    Ordering data science problems easy-to-hard and accumulating their solutions in a memory buffer improves LLM agent pass rates on DSEval and QRData by up to 5.2%.

  20. Exploring Agentic Workflows for Generating High Quality Math Visual Aids

    cs.AI 2026-07 conditional novelty 4.0 of 10

    An exploratory agentic self-improvement loop for TikZ math diagrams yields modest human-rated gains but fails to fix many spatial and coverage errors.

  21. Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems

    cs.DB 2025-07 conditional novelty 4.0 of 10

    A position paper introducing a holistic 'Data Agent' architecture for autonomous Data+AI orchestration, with proposed iDataScience, data analytics, and DBA agents, but no empirical evaluation.

  22. LLM-Agent-Controller: A Universal Multi-Agent Large Language Model System as a Control Engineer

    cs.AI 2025-05 conditional novelty 4.0 of 10

    A nine-agent LLM system with RAG and 140+ Python Control Library tools solves textbook control-theory tasks with a reported 83% completion rate.

  23. Agentic Web: Weaving the Next Web with AI Agents

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A position paper defines the Agentic Web as the next web era and proposes a three-dimensional conceptual framework for understanding and building it.

Pith tools