PulseAugur
EN
LIVE 00:37:04

FormalEvolve enhances autoformalization with neuro-symbolic search

Researchers have developed FormalEvolve, a novel neuro-symbolic evolutionary search method for autoformalization. This approach tackles the challenge of translating informal mathematics into formal statements by recasting it as a budgeted test-time search problem. FormalEvolve maintains a compilation-feasible archive and generates diverse formal statements through LLM-driven mutation, crossover, and AST rewrites, significantly improving performance on benchmarks like CombiBench and ProofNet. AI

RANK_REASON This is a research paper detailing a new method for autoformalization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

FormalEvolve enhances autoformalization with neuro-symbolic search

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Haijian Lu, Wei Wang, Jing Liu ·

    FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization

    arXiv:2603.19828v3 Announce Type: replace Abstract: Autoformalization aims to produce formal statements that compile and faithfully preserve the intended meaning of informal mathematics. Yet standard single-output evaluation protocols collapse a many-to-many problem into a single…