# On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations

arXiv: https://arxiv.org/abs/2509.00710 · HTML: https://mlsanity.com/paper/2509.00710/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [Can LLMs Follow Simple Rules?](https://mlsanity.com/paper/2311.04235/) (2023)
- [Logically Consistent Language Models via Neuro-Symbolic Integration](https://mlsanity.com/paper/2409.13724/) (2024)
- [Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law](https://mlsanity.com/paper/2502.17638/) (2025)
- [Towards Ontology Construction with Language Models](https://mlsanity.com/paper/2309.09898/) (2023)
- [LLMs Provide Unstable Answers to Legal Questions](https://mlsanity.com/paper/2502.05196/) (2025)
- [Chain of Logic: Rule-Based Reasoning with Large Language Models](https://mlsanity.com/paper/2402.10400/) (2024)
- [Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection](https://mlsanity.com/paper/2405.02318/) (2024)
- [LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning](https://mlsanity.com/paper/2209.06120/) (2022)
- [Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration](https://mlsanity.com/paper/2410.02507/) (2024)
- [Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System](https://mlsanity.com/paper/2507.02170/) (2025)
- [Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation](https://mlsanity.com/paper/2507.21969/) (2025)
- [Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data](https://mlsanity.com/paper/2412.10654/) (2024)
- [Teaching AI to Handle Exceptions: Supervised Fine-Tuning with Human-Aligned Judgment](https://mlsanity.com/paper/2503.02976/) (2025)
- [Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law](https://mlsanity.com/paper/2410.04949/) (2024)

## Built on by (most cited first, 18 of 18)

- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Towards Trustworthy Legal AI through LLM Agents and Formal Reasoning](https://mlsanity.com/paper/2511.21033/) (2025)
- [LLM Agents in Law: Taxonomy, Applications, and Challenges](https://mlsanity.com/paper/2601.06216/) (2026)
- [Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning](https://mlsanity.com/paper/2602.18916/) (2026)
- [Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning Capabilities](https://mlsanity.com/paper/2512.24572/) (2025)
- [Multi-Agent Dialectical Refinement for Enhanced Argument Classification](https://mlsanity.com/paper/2603.27451/) (2026)
- [Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory](https://mlsanity.com/paper/2604.03588/) (2026)
- [Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integration](https://mlsanity.com/paper/2601.01609/) (2026)
- [PYTHEN: A Flexible Framework for Legal Reasoning in Python](https://mlsanity.com/paper/2603.15317/) (2026)
- [Formally Verified Patent Analysis via Dependent Type Theory: Machine-Checkable Certificates from a Hybrid AI + Lean 4 Pipeline](https://mlsanity.com/paper/2604.18882/) (2026)
- [HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document](https://mlsanity.com/paper/2607.24861/) (2026)
- [Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication](https://mlsanity.com/paper/2605.02472/) (2026)
- [Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law](https://mlsanity.com/paper/2605.16052/) (2026)
- [Maat: The Agentic Legal Research Assistant for Competition Protection](https://mlsanity.com/paper/2605.27331/) (2026)
- [Explainable Belief Harmonization under Dynamic Epistemic Partitions](https://mlsanity.com/paper/2607.21210/) (2026)
- [On Measuring Semantic Preservation in Legal Ontology Learning](https://mlsanity.com/paper/2608.12326/) (2026)
- [Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems](https://mlsanity.com/paper/2609.05928/) (2026)
- [More Claims, Less Evidence: Bounded Verification of AI-Generated Digital Knowledge Artifacts](https://mlsanity.com/paper/2610.05547/) (2026)

## Abstract (arXiv)

Legal reasoning requires both precise interpretation of statutory language and consistent application of complex rules, presenting significant challenges for AI systems. This paper introduces a modular multi-agent framework that decomposes legal reasoning into distinct knowledge acquisition and application stages. In the first stage, specialized agents extract legal concepts and formalize rules to create verifiable intermediate representations of statutes. The second stage applies this knowledge to specific cases through three steps: analyzing queries to map case facts onto the ontology schema, performing symbolic inference to derive logically entailed conclusions, and generating final answers using a programmatic implementation that operationalizes the ontological knowledge. This bridging of natural language understanding with symbolic reasoning provides explicit and verifiable inspection points, significantly enhancing transparency compared to end-to-end approaches. Evaluation on statutory tax calculation tasks demonstrates substantial improvements, with foundational models achieving 76.4% accuracy compared to 18.8% baseline performance, effectively narrowing the performance gap between reasoning and foundational models. These findings suggest that modular architectures with formalized knowledge representations can make sophisticated legal reasoning more accessible through computationally efficient models while enhancing consistency and explainability in AI legal reasoning, establishing a foundation for future research into more transparent, trustworthy, and effective AI systems for legal domain.