提出统一推理运维框架，提升大模型推理的可信与可靠性。
ReasonOps: A Unified Operational Paradigm for Trustworthy Verified LLM Reasoning
- 将推理视为持续监控、可验证的运营流程，整合多阶段能力
- 在制动系统分析中实现逻辑一致性和运行时保障
- 适合安全关键型AI系统开发者和可信AI研究者
大型语言模型（LLMs）已将人工智能从生成系统转变为日益强大的推理代理。近年来，在定理证明、自动形式化、符号推理和工具增强语言模型方面的进展，显著推动了机器辅助形式推理的发展。然而，当前推理系统仍存在隐含逻辑不一致、符号转换幻觉、定理应用无支持及可靠性保证不足等问题。现有方法在形式验证、运行时保障、神经符号推理和可信AI研究领域间碎片化严重。本文提出ReasonOps——一种面向可信验证推理系统的统一操作范式。受DevOps和MLOps等运营生态启发，ReasonOps将推理视为持续监控、可验证、具备可靠性意识的运营过程，而非孤立的推理任务。该范式整合语义解析、自动形式化、符号推理、定理证明、运行时保障、概率可靠性估计与自适应修正，形成统一推理生命周期。论文进一步展示ReasonOps架构，并以自主制动系统分析为例说明其工作流，探讨其在未来安全关键型自主AI系统中的潜力。我们认为，类似ReasonOps的操作推理范式可能成为下一代可信AI生态系统的基础基础设施。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have transformed artificial intelligence from primarily generative systems into increasingly capable reasoning agents. Recent advances in theorem proving, autoformalization, symbolic reasoning, and tool-augmented language models demonstrate substantial progress toward machine-assisted formal reasoning. However, current reasoning systems still suffer from hidden logical inconsistencies, hallucinated symbolic transitions, unsupported theorem applications, and limited reliability guarantees. Existing approaches remain fragmented across formal verification, runtime assurance, neuro-symbolic reasoning and trustworthy Artificial Intelligence (AI) research communities. This paper introduces ReasonOps, a unified operational paradigm for trustworthy verified reasoning systems. Inspired by operational ecosystems such as DevOps and MLOps, ReasonOps treats reasoning as a continuously monitored, verifiable, reliability-aware operational process rather than an isolated inference task. The proposed paradigm integrates semantic interpretation, autoformalization, symbolic reasoning, theorem proving, runtime assurance, probabilistic reliability estimation, and adaptive correction into a unified reasoning lifecycle. The paper further presents the ReasonOps architecture, demonstrates its workflow using an autonomous braking system analysis example, and discusses its potential role in future safety-critical autonomous AI systems. We argue that operational reasoning paradigms such as ReasonOps may become foundational infrastructure for next-generation trustworthy AI ecosystems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。