# Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning

arXiv: https://arxiv.org/abs/2510.08710 · HTML: https://mlsanity.com/paper/2510.08710/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 19 of its 56 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

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

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [Hierarchical Reasoning Model](https://mlsanity.com/paper/2506.21734/) (2025)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [A Survey on Large Language Models for Mathematical Reasoning](https://mlsanity.com/paper/2506.08446/) (2025)
- [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025)
- [Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning](https://mlsanity.com/paper/2312.05762/) (2023)
- [Obligation and Prohibition Extraction Using Hierarchical RNNs](https://mlsanity.com/paper/1805.03871/) (2018)
- [An alignment safety case sketch based on debate](https://mlsanity.com/paper/2505.03989/) (2025)
- [Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation](https://mlsanity.com/paper/2506.02992/) (2025)
- [AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction](https://mlsanity.com/paper/2503.00128/) (2025)
- [Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments](https://mlsanity.com/paper/2506.00694/) (2025)

## Built on by (most cited first, 7 of 7)

- [PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice](https://mlsanity.com/paper/2601.16669/) (2026)
- [Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning](https://mlsanity.com/paper/2602.18916/) (2026)
- [OpenExempt: A Diagnostic Benchmark for Legal Reasoning and a Framework for Creating Custom Benchmarks on Demand](https://mlsanity.com/paper/2601.13183/) (2026)
- [LAMUS: A Large-Scale Corpus for Legal Argument Mining from U.S. Caselaw using LLMs](https://mlsanity.com/paper/2603.08286/) (2026)
- [Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication](https://mlsanity.com/paper/2605.02472/) (2026)
- [Toward Human Rights Benchmarking for LLMs: A Pilot Methodology](https://mlsanity.com/paper/2608.10268/) (2026)
- [Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning](https://mlsanity.com/paper/2608.12372/) (2026)

## Abstract (arXiv)

Case-based reasoning is a cornerstone of U.S. legal practice, requiring professionals to argue about a current case by drawing analogies to and distinguishing from past precedents. While Large Language Models (LLMs) have shown remarkable capabilities, their proficiency in this complex, nuanced form of reasoning needs further investigation. We propose a formal framework that decomposes the process of identifying significant distinctions between cases into three-stage reasoning tasks. Our framework models cases using factual predicates called factors, organizes them into a legal knowledge hierarchy, and defines verifiable rules for identifying distinctions, analyzing their argumentative support, and evaluating their significance. Through comprehensive evaluation of modern reasoning LLMs, we reveal a paradox: while models achieve high accuracy on surface-level reasoning (Task 1), performance degrades on hierarchical reasoning (Task 2: 64.82%-92.09%) and collapses on integrated analysis (Task 3: 11.46%-33.99%). Most strikingly, we find that models consistently expend more computational resources on incorrect responses than correct ones, suggesting that "thinking longer" does not always mean "thinking smarter." Our work provides a methodology for fine-grained analysis of LLM reasoning capabilities in complex domains and reveals fundamental limitations that must be addressed for robust and trustworthy legal AI.