Researchers have developed AutoSR, a novel system for automatic symbolic regression that searches through research states rather than isolated equations. This approach preserves the scientific record, including reasoning and computational evidence, to guide the search for credible expressions. AutoSR utilizes proposer-reviewer agents and Monte Carlo tree search to explore competing investigations, ultimately synthesizing the accumulated knowledge into a final report. The system has demonstrated success across various benchmark challenges, recovering algebraically equivalent relations and extending symbolic regression towards automated scientific investigation. AI
IMPACT This research advances automated scientific discovery by improving symbolic regression techniques.
RANK_REASON This is a research paper detailing a new method for symbolic regression. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
