Metraipolis › archive › dc_e9efce4d036c

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond — arXiv:2608.14354

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14354
License (as archived)
CC0-1.0
Archived
2026-10-19T02:20:47.637Z
SHA-256 of the archived text
e46f93722118175abb668dc42b2424794789edb22f42c99e05b85738d2cfa742
Stable URL of this page
https://metraipolis.com/documento/dc_e9efce4d036c

How to cite

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond — arXiv:2608.14354 — arXiv (en), https://arxiv.org/abs/2608.14354 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e9efce4d036c (Metraipolis archive dc_e9efce4d036c, sha256 e46f93722118175abb668dc42b2424794789edb22f42c99e05b85738d2cfa742)
BibTeX
@misc{dce9efce4d036c,
  title = {ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond — arXiv:2608.14354},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14354},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e9efce4d036c; sha256 e46f93722118175abb668dc42b2424794789edb22f42c99e05b85738d2cfa742},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14354. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources. Pioneering autoresearch agents, despite great success, still lack mechanisms for continuity, recovery from dead ends, and value-driven compute allocation, which inherently undermines overall search efficiency, wastes computational resources, and lowers the chance of ultimate success. To bridge this gap, we introduce ScienceFlow, an end-to-end autoresearch agent framework that organizes long-horizon research work into research segments grounded in executable workspaces. It represents research progress as recoverable executable states, enabling efficient exploration, revision, and execution. Transitions between research segments are governed by Executable-State Transition through Re-Anchoring (ESTRA), which selects either the live state or an archived state as the next anchor and determines whether to continue or redirect the research trajectory. An evidence-aware execution controller allocates resources to physical jobs based on resource availability, remaining budget, and validated progress. We evaluate ScienceFlow on tasks spanning machine learning, scientific modeling, and mathematical optimization. Results on diverse long-horizon benchmarks demonstrate its ability to sustain effective research processes, highlighted by a SOTA 70.22 percent Any-Medal score on the full MLE-bench within a 24-hour budget, outperforming prior reported results by 4.92 percentage points. The efficacy of ScienceFlow further demonstrates that efficient state management, adaptive exploration, and objective-aligned execution are critical for scaling autonomous research beyond short-horizon interactions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14354 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:02:02.808Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).