AutoSR: Automatic Symbolic Regression by Searching Research States

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Kejia Zhang, Youran Sun, Xinyu Ren, Chugang Yi, Haizhao Yang
• Venue: arXiv: cs.SC
• Published: 2026-08-17
• Collected: 2026-08-18
• URL: http://arxiv.org/abs/2608.16876v1
• PDF: https://arxiv.org/pdf/2608.16876v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The authors introduce AutoSR, a fully automated system that searches for persistent scientific investigations instead of isolated equations in symbolic regression. Unlike traditional methods, AutoSR preserves the reasoning, computational evidence, and independent review developed along each candidate equation's branch, storing this information as a Research State. The system uses progressive-widening Monte Carlo tree search (PW-MCTS) to allocate computation across competing investigations, ultimately synthesizing the findings into a final report.

What the Document Says

• AutoSR is an automatic symbolic regression system that searches for persistent scientific investigations.
• It uses progressive-widening Monte Carlo tree search (PW-MCTS) to allocate computation across competing investigations.
• The system preserves the reasoning, computational evidence, and independent review developed along each candidate equation's branch in a Research State.
• The accumulated research record is synthesized into a final report that explains the leading relation and the basis for its selection.

Key Concepts Mentioned

• Automatic Symbolic Regression
• Research-Space Symbolic Regression
• Progressive-widening Monte Carlo tree search (PW-MCTS)
• Research State
• Final Report

Claims Made by the Document

• AutoSR recovers algebraically equivalent relations in every case across nine selected challenges from two benchmark suites.
• AutoSR extends symbolic regression from equation-level search toward automated scientific investigation.

Evidence Used

• Results across nine selected challenges from two benchmark suites
• Description of AutoSR's methodology

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

We introduce Automatic Symbolic Regression (AutoSR), a fully automated system that instantiates Research-Space Symbolic Regression by searching persistent scientific investigations rather than isolated equations. Finite, noisy data often yield numerically competitive expressions that imply very different behavior outside the observed regime, making numerical fit and syntactic complexity insufficient measures of scientific credibility. Existing approaches largely focus on improving expressions, yet the search typically retains little beyond the resulting formula and score, losing the scientific record, such as motivations and probes, that inform what to try next. AutoSR preserves this record in a \textbf{Research State}, coupling each candidate equation with the reasoning, computational evidence, and independent review developed along its branch. Proposer--reviewer agents develop these states under progressive-widening Monte Carlo tree search (PW-MCTS), which allocates computation across competing investigations, while the accumulated research record is ultimately synthesized into a final report that explains the leading relation and the basis for its selection. Across nine selected challenges from two benchmark suites, AutoSR recovers algebraically equivalent relations in every case, including three cp3-bench problems that no published system recovers and six structurally diverse LSR-Transform problems. Overall, AutoSR extends symbolic regression from equation-level search toward automated scientific investigation, allowing scientific knowledge and accumulated evidence to shape both what is explored and how the resulting equation is justified.