# Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning

arXiv: https://arxiv.org/abs/2602.18916 · HTML: https://mlsanity.com/paper/2602.18916/

## Key facts

- Cited by 4 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 21 of its 33 references that are in the map.
- First posted on arXiv 21 Feb 2026.

## 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, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice](https://mlsanity.com/paper/2402.01864/) (2024)
- [Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence](https://mlsanity.com/paper/2306.07075/) (2023)
- [AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation](https://mlsanity.com/paper/2403.02959/) (2024)
- [AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents](https://mlsanity.com/paper/2408.08089/) (2024)
- [Argumentative Large Language Models for Explainable and Contestable Claim Verification](https://mlsanity.com/paper/2405.02079/) (2024)
- [On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations](https://mlsanity.com/paper/2509.00710/) (2025)
- [Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning](https://mlsanity.com/paper/2502.07912/) (2025)
- [Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing](https://mlsanity.com/paper/2304.04906/) (2023)
- [Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks (Technical Report)](https://mlsanity.com/paper/2307.13582/) (2023)
- [Challenges for Generative AI in Legal Reasoning](https://mlsanity.com/paper/2508.18880/) (2025)
- [Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning](https://mlsanity.com/paper/2510.08710/) (2025)
- [Motion2Meaning: A Clinician-Centered Framework for Contestable LLM in Parkinson's Disease Gait Interpretation](https://mlsanity.com/paper/2512.08934/) (2025)
- [LLM Agents in Law: Taxonomy, Applications, and Challenges](https://mlsanity.com/paper/2601.06216/) (2026)
- [NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making](https://mlsanity.com/paper/2508.05344/) (2025)
- [SAMVAD: A Multi-Agent System for Simulating Judicial Deliberation Dynamics in India](https://mlsanity.com/paper/2509.03793/) (2025)

## Built on by (most cited first, 4 of 4)

- [Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification](https://mlsanity.com/paper/2605.14495/) (2026)
- [Position: Multi-Agent Algorithmic Care Systems Demand Contestability for Trustworthy AI](https://mlsanity.com/paper/2603.20595/) (2026)
- [Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification](https://mlsanity.com/paper/2606.16987/) (2026)
- [CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs](https://mlsanity.com/paper/2608.05107/) (2026)

## Abstract (arXiv)

Legal reasoning requires not only high accuracy but also the ability to justify decisions through verifiable and contestable arguments. However, existing Large Language Model (LLM) approaches, such as Chain-of-Thought (CoT) and Retrieval-Augmented Generation (RAG), often produce unstructured explanations that lack a formal mechanism for verification or user intervention. To address this limitation, we propose Adaptive Collaboration of Argumentative LLMs (ACAL), a neuro-symbolic framework that integrates adaptive multi-agent collaboration with an Arena-based Quantitative Bipolar Argumentation Framework (A-QBAF). ACAL dynamically deploys expert agent teams to construct arguments, employs a clash resolution mechanism to adjudicate conflicting claims, and utilizes uncertainty-aware escalation for borderline cases. Crucially, our framework supports a Human-in-the-Loop (HITL) contestability workflow, enabling users to directly audit and modify the underlying reasoning graph to influence the final judgment. Empirical evaluations on the LegalBench benchmark demonstrate that ACAL outperforms strong baselines across Gemini-2.5-Flash-Lite and Gemini-2.5-Flash architectures, effectively balancing efficient predictive performance with structured transparency and contestability. Our implementation is available at: https://github.com/loc110504/ACAL.