Paper page - EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management

Source: https://huggingface.co/papers/2606.03841

Abstract

EvoDS introduces a self-evolving autonomous data science agent that enhances its capabilities through skill acquisition and adaptive context management via reinforcement learning.

Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their static action sets and lack of principled long-horizon context management, hindering their ability to accumulate reusable experience across tasks and operate reliably in multi-stage, iterative data science pipelines. To address these challenges, we introduce EvoDS, a self-evolving autonomous data science agent that learns to expand its skills and adaptively managing long-term context throughagentic reinforcement learning. Specifically, EvoDS introduces two key strategies: (1)Autonomous Skill Acquisition(ASA) mechanism, which enables agents to synthesize, validate, and reuse executable skills; and (2)Adaptive Context Compression(ACC) strategy, which treats context management as a learned control problem rather than passive truncation. These strategies are orchestrated within a two-stagemulti-agent trainingscheme, enabling EvoDS to autonomously improve over time. Theoretically, we prove that EvoDS’s hierarchical design reduces tool-selection error, and its optimization objective aligns with aninformation bottleneck principle, ensuring efficient context use. Empirically, EvoDS outperforms state-of-the-art open-source data science agents by an average of 28.9% across four diverse benchmarks while eliminating out-of-token failures. Our code and data are available at https://github.com/usail-hkust/EvoDS.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2606\.03841

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.03841 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.03841 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.03841 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.