Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication

Stanisław Sójka, Witold Kowalczyk

Keywords: Neuro-Symbolic AI, Legal NLP, Computational Law, Symbolic Execution, Structural Auditability, Contract Adjudication, Graph-Based Reasoning, Propositional Logic

TL;DR: We introduce a neuro-symbolic agentic architecture for reasoning on legal contracts that uses execution graphs at inference time, achieving 99.5% accuracy and reducing inference costs by over 90% compared to frontier LRMs.

Abstract: Legal texts often contain computational legal clauses—provisions whose understanding requires complex logic. While frontier Large Reasoning Models (LRMs) can describe such clauses, building production-ready systems is limited by reasoning errors and the high cost of inference. We propose Amortized Intelligence, a neuro-symbolic approach where we use an LLM once to translate a legal text into Deterministic Autonomous Contract Language (DACL): a typed graph intermediate representation. Adjudication then relies on deterministic graph executions with a visually auditable trace. In comparison against runtime LRM baselines (including GPT-5.2 and Gemini 3 Pro), our DACL-based Agent achieves near-perfect consistency and mitigates the "reasoning cliff" observed in probabilistic models. The system reduces compute costs by over 90% in high-volume workflows while satisfying the strict auditability requirements of legal adjudication.

Submission Type: Deployed

Submission Number: 355