让AI自动核对风投融资中的股权结构，提升法律尽调效率
Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital
- 构建世界模型，实现多文档法律文本的推理与证据追踪
- 现有智能体在严格证据链和确定性输出上仍不达标
- 为法律AI提供可落地的自动化基础，适合风控与法务团队
风投融资完成前，律师需进行尽职调查，包括核对资本结构表：验证每项证券（如股份、期权、认股权证）及发行条款（如归属计划、加速触发条件、转让限制）是否均有大量底层法律文件支持。尽管大语言模型在法律基准测试中持续进步，但像资本结构核对这类专业法律流程，即便对强大的智能体系统而言仍难以实现。该任务要求多文档推理、严格的证据溯源以及确定性输出，而当前方法无法可靠满足。本文将资本结构核对视为法律AI的真实世界基准，分析并比较现有智能体系统的性能，并提出一种面向核对自动化的世界模型架构——更广泛地，作为应用型法律智能的基础。
原文摘要 · Abstract (English)
Before closing venture capital financing rounds, lawyers conduct diligence that includes tying out the capitalization table: verifying that every security (for example, shares, options, warrants) and issuance term (for example, vesting schedules, acceleration triggers, transfer restrictions) is supported by large sets of underlying legal documentation. While LLMs continue to improve on legal benchmarks, specialized legal workflows, such as capitalization tie-out, remain out of reach even for strong agentic systems. The task requires multi-document reasoning, strict evidence traceability, and deterministic outputs that current approaches fail to reliably deliver. We characterize capitalization tie-out as an instance of a real-world benchmark for legal AI, analyze and compare the performance of existing agentic systems, and propose a world model architecture toward tie-out automation-and more broadly as a foundation for applied legal intelligence.
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。