Metraipolis › archive › dc_70dc15bd7cd3
SRHarness: A Harness for Agentic Symbolic Regression — arXiv:2609.35501
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35501
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:58:50.619Z
- SHA-256 of the archived text
3647cd048b1db18e5e4824876df17634d94cf1993507b5f04035d095b0ff272c- Stable URL of this page
https://metraipolis.com/documento/dc_70dc15bd7cd3
How to cite
SRHarness: A Harness for Agentic Symbolic Regression — arXiv:2609.35501 — arXiv (en), https://arxiv.org/abs/2609.35501 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70dc15bd7cd3 (Metraipolis archive dc_70dc15bd7cd3, sha256 3647cd048b1db18e5e4824876df17634d94cf1993507b5f04035d095b0ff272c)
BibTeX
@misc{dc70dc15bd7cd3,
title = {SRHarness: A Harness for Agentic Symbolic Regression — arXiv:2609.35501},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35501},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70dc15bd7cd3; sha256 3647cd048b1db18e5e4824876df17634d94cf1993507b5f04035d095b0ff272c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35501. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent agentic symbolic regression approaches increasingly rely on large language models to analyze data, select scientific operations, and refine hypotheses over long search trajectories. In such systems, performance depends not only on the underlying model and search strategy, but also on the runtime infrastructure that supports scientific search. We introduce SRHarness, a domain-specific harness for agentic symbolic regression built around three mechanisms: composable scientific actions that provide a common interface over raw, transformed, and candidate-derived quantities; persistent scientific state that retains evaluated hypotheses and exposes compact model-facing views; and trajectory lifecycle management that coordinates continuation, branching, restart, and termination. On LLM-SRBench, SRHarness consistently improves both numerical generalization and symbolic recovery under matched LLM backbones. With DeepSeek-v4-flash-0731, it achieves 93.69% symbolic accuracy on LSR-Transform, compared with 62.16% for SR-Scientist, and retains 72.97% accuracy on an anonymized variant that removes scientific descriptions and variable semantics, versus 39.64% for SR-Scientist. Under the same DeepSeek-v4-flash-0731 backbone, SRHarness also substantially outperforms Codex (72.97% vs. 20.72%) and reaches performance comparable to Codex with GPT-5.5, while simply providing Codex with the same scientific tools does not reproduce this advantage. These results show that effective agentic symbolic regression depends not only on models or tools, but also on structured runtime support for organizing scientific actions, accumulated hypotheses, and long-horizon search. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Symbolic Computation (cs.SC). Pagina del lavoro: https://arxiv.org/abs/2609.35501 — 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 2026-10-07T20:29:01.872Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).