Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital

TL;DR

This paper explores automating the legal process of capitalization tie-out in venture capital, addressing the challenges of multi-document reasoning and evidence traceability with a new world model architecture.

Contribution

It characterizes capitalization tie-out as a real-world legal AI benchmark, analyzes existing systems, and proposes a novel world model architecture for automation.

Findings

Existing systems struggle with multi-document reasoning.

The proposed architecture improves traceability and reliability.

Legal AI automation remains a challenging frontier.

Abstract

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.