AI 中文总结
针对理论驱动科学发现探索不足的问题，ReasFlow引入以推理为中心的自主智能体系统，通过内部验证循环和知识检索机制减少专家干预，能统一多项科研任务，从最少提示生成高质量论文，在开源基线中表现出色。
AI 中文摘要
大语言模型的进展推动了能处理复杂科学任务的自主人工智能智能体，但现有自动化研究系统主要集中在有定量基准的经验驱动领域，理论驱动发现，尤其是数学基础学科中需要严格证明和领域知识综合的部分，未被充分探索。关键挑战包括大规模验证理论推理困难、自主前沿探索推理能力不足、文献中程序启发法稀缺。我们引入ReasFlow，一个以推理为中心的科学发现的端到端自主智能体系统，采用协作范式，人类专家担任首席研究员，智能体作为有能力的研究生执行严格推导。ReasFlow包含强大的内部验证循环和自动知识检索与自我改进机制，减少专家干预。该系统统一了文献综合、算法设计、定理证明、实验和稿件准备。从最少提示自主生成五篇有严格理论和实证内容的完整研究论文，在基于大语言模型的评审标准下，ReasFlow在现有开源基线中始终获得最高评价分数。可通过ReasLab平台公开访问，提供人工智能辅助理论研究的协作工作区。
英文摘要
Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain predominantly focused on empirically driven domains with quantitative benchmarks, leaving theory-driven discovery, particularly in mathematically grounded disciplines requiring rigorous proofs and synthesis of domain knowledge, largely underexplored. Key challenges include the difficulty of verifying theoretical reasoning at scale, insufficient reasoning ability for autonomous frontier exploration, and a scarcity of procedural heuristics in the literature. We introduce ReasFlow, an end-to-end autonomous agent system for reasoning-centric scientific discovery that operationalizes a collaborative paradigm where the human expert acts as Principal Investigator while the agent executes rigorous derivations as a capable graduate student. ReasFlow incorporates (i) a robust internal verification loop that audits logical coherence and corrects fundamental errors prior to human inspection, and (ii) an automated knowledge retrieval and self-improvement mechanism that proactively surfaces both declarative facts and overlooked procedural heuristics, substantially reducing expert intervention. The system unifies literature synthesis, algorithm design, theorem proving, experimentation, and manuscript preparation in a single system. Deployed to autonomously generate five complete research papers with rigorous theoretical and empirical content from minimal prompts, ReasFlow consistently achieves the highest evaluation scores among state-of-the-art open-access baselines under a curated LLM-based review rubric. ReasFlow is publicly accessible via the ReasLab platform, providing a collaborative workspace for AI-assisted theoretical research. Github repo: https://github.com/reaslab/ReasFlow.git.
