{"slug": "ds-lighting-making-agent-harnesses-explicit-for-data-science-automation", "title": "DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation", "summary": "Researchers from HKUST introduced DS-Lighting, a unified harness toolkit that makes agent harness design explicit for data-science automation, decomposing it into four reusable layers: data, workflow, execution, and evaluation. The toolkit integrates multiple open-source benchmarks into an MLE-Bench-style format, and experiments show that explicit harness design improves reproducibility, comparability, and reliability while reducing system-level failures. The code is available on GitHub.", "body_md": "arXiv:2608.28590v1 Announce Type: new\nAbstract: Large Language Model (LLM) agents have shown promise for automating data-science workflows, yet their end-to-end performance depends critically on the agent harness that represents tasks, manages execution state, constrains output artifacts, and provides evaluation feedback. Existing data-science agents often leave this harness implicit, making results difficult to reproduce, compare, and attribute across heterogeneous tasks. We introduce DS-Lighting, a unified harness toolkit that makes harness design explicit for data-science automation. DS-Lighting decomposes the harness into four reusable layers: data, workflow, execution, and evaluation, and represents diverse agents as executable operator programs that support both predefined pipelines and adaptive search. We further integrate multiple open-source data-science benchmarks into an MLE-Bench-style task format, enabling controlled comparison under a shared task interface, sandboxed runtime, and metric protocol. Experiments across agents, harnesses, models, and ablations show that explicit harness design improves reproducibility, comparability, and reliability, while reducing avoidable system-level failures in end-to-end data-science workflows. Our code is available at https://github.com/usail-hkust/dslighting", "url": "https://wpnews.pro/news/ds-lighting-making-agent-harnesses-explicit-for-data-science-automation", "canonical_source": "https://arxiv.org/abs/2608.28590", "published_at": "2026-09-01 04:00:00+00:00", "updated_at": "2026-09-01 04:26:19.609183+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "ai-tools"], "entities": ["HKUST", "DS-Lighting", "MLE-Bench", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/ds-lighting-making-agent-harnesses-explicit-for-data-science-automation", "markdown": "https://wpnews.pro/news/ds-lighting-making-agent-harnesses-explicit-for-data-science-automation.md", "text": "https://wpnews.pro/news/ds-lighting-making-agent-harnesses-explicit-for-data-science-automation.txt", "jsonld": "https://wpnews.pro/news/ds-lighting-making-agent-harnesses-explicit-for-data-science-automation.jsonld"}}