공유 팩트 그래프(fact graph)를 전역 메모리 관리 메커니즘으로 활용하는 수학적 추론 오케스트레이션 시스템 Danus를 제안하며, 메인 에이전트의 조율 하에 병렬로 동작하는 다수의 워커 에이전트와 무상태 검증기가 협력하여 긴 수학적 증명을 단계적으로 구성한다. 대수기하학, 특이점 이론, 조합론 분야의 여섯 가지 연구 수준 사례 연구에서 팩트 그래프 기반 오케스트레이션이 장기 연구 문제에 대한 수학적 추론 에이전트의 확장에 효과적임을 입증했다.
Recent artificial intelligence (AI) systems have shown remarkable progress in mathematical reasoning. Many existing approaches, including large language models (LLMs), draw on human prior knowledge in the form of mathematical text, code, or theorem libraries. Although these approaches are highly effective in practice, it remains an open question whether an agent can autonomously discover useful theorems without such human priors. We study this question in a formal axiomatic system by developing an agent that starts from axioms and inference rules alone and gradually grows a library of useful theorems. Concretely, we propose a self-supervised theorem-discovery algorithm that alternates between proof search and useful-theorem extraction, building a theorem library whose entries are reused as lemmas for subsequent proof search. Experiments show that the agent discovers tens of thousands of theorems and finds proofs for human-written benchmark problems, suggesting that its discoveries include theorems meaningful from a human mathematical perspective. Furthermore, the discovered theorems improve LLM proof performance when provided as prompt lemmas, indicating that they can serve as external knowledge for LLM reasoning. Our results provide evidence that useful theorems can emerge from proof search without relying on human-provided theorem libraries. More broadly, they suggest a path toward self-evolving AI systems for mathematics whose discoveries remain formally verifiable.