Agentic-imodels: Evolving agentic interpretability tools via autoresearch
- URL: http://arxiv.org/abs/2605.03808v1
- Date: Tue, 05 May 2026 14:35:47 GMT
- Title: Agentic-imodels: Evolving agentic interpretability tools via autoresearch
- Abstract summary: Agentic-imodels is an agentic autoresearch loop that evolves data-science tools designed to be interpretable by agents.<n>The metric measures whether a fitted model's string representation is "simulatable" by an LLM.<n>We find that the evolved models jointly improve predictive performance and agent-facing interpretability.
- Score: 35.865162623438025
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current ADS systems use statistical tools designed to be interpretable by humans, rather than interpretable by agents. To address this, we introduce Agentic-imodels, an agentic autoresearch loop that evolves data-science tools designed to be interpretable by agents. Specifically, it develops a library of scikit-learn-compatible regressors for tabular data that are optimized for both predictive performance and a novel LLM-based interpretability metric. The metric measures a suite of LLM-graded tests that probe whether a fitted model's string representation is "simulatable" by an LLM, i.e. whether the LLM can answer questions about the model's behavior by reading its string output alone. We find that the evolved models jointly improve predictive performance and agent-facing interpretability, generalizing to new datasets and new interpretability tests. Furthermore, these evolved models improve downstream end-to-end ADS, increasing performance for Copilot CLI, Claude Code, and Codex on the BLADE benchmark by up to 73%
Related papers
- VESTA: Visual Exploration with Statistical Tool Agents [56.76643750765825]
We introduce VESTA: Visual Exploration with Statistical Tool Agents.<n>We show that VESTA's dynamic tool creation outperforms prior agentic pipelines.<n>We also introduce DAWN, a benchmark targeting distribution fitting and time series.
arXiv Detail & Related papers (2026-05-29T21:57:37Z) - ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration [68.89572566071575]
ETAgent is a training framework for calibrating agent's tool-use behavior.<n>It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors.
arXiv Detail & Related papers (2026-01-11T11:05:26Z) - Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents [3.344730946122235]
We propose an innovative pipeline utilizing Large Language Model (LLM) agents to automate data-driven modeling and analysis.<n>We evaluate two LLM-agent frameworks: a multi-agent system featuring specialized collaborative agents, and a single-agent system based on the Reasoning and Acting (ReAct) paradigm.
arXiv Detail & Related papers (2025-10-01T19:28:35Z) - Meta-Learning Linear Models for Molecular Property Prediction [3.9685594339912633]
We introduce LAMeL - a Linear Algorithm for Meta-Learning that preserves interpretability while improving the prediction accuracy across multiple properties.<n>Our method delivers performance improvements ranging from 1.1- to 25-fold over standard ridge regression, depending on the domain of the dataset.
arXiv Detail & Related papers (2025-09-16T20:41:45Z) - Agents of Discovery [17.016402322416994]
Large language models (LLMs) can jointly solve data analysis-based research problems.<n>We consider the task of anomaly detection via the publicly available and highly-studied LHC Olympics dataset.<n>The best agent-created solutions mirror the performance of human state-of-the-art results.
arXiv Detail & Related papers (2025-09-10T12:25:13Z) - LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback [121.78866929908871]
Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data.<n>We present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback.<n>Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive real-time feedback.
arXiv Detail & Related papers (2025-06-02T22:36:02Z) - IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
arXiv Detail & Related papers (2025-05-23T09:37:52Z) - DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation [10.390461679868197]
We introduce DatawiseAgent, a notebook-centric large language model (LLM) agent framework for adaptive and robust data science automation.<n>Inspired by how human data scientists work in computational notebooks, DatawiseAgent introduces a unified interaction representation and a multi-stage architecture.
arXiv Detail & Related papers (2025-03-10T08:32:33Z) - MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization [86.61052121715689]
MatPlotAgent is a model-agnostic framework designed to automate scientific data visualization tasks.
MatPlotBench is a high-quality benchmark consisting of 100 human-verified test cases.
arXiv Detail & Related papers (2024-02-18T04:28:28Z) - Evaluating and Explaining Large Language Models for Code Using Syntactic
Structures [74.93762031957883]
This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code.
At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes.
We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
arXiv Detail & Related papers (2023-08-07T18:50:57Z)
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.