Strategic interaction in adversarial domains such as law, diplomacy, and negotiation is mediated by language, yet most game-theoretic models abstract away the mechanisms of persuasion that operate through discourse. We present the Strategic Courtroom Framework, a multi-agent simulation environment in which prosecution and defense teams composed of trait-conditioned Large Language Model (LLM) agents engage in iterative, round-based legal argumentation. Agents are instantiated using nine interpretable traits organized into four archetypes, enabling systematic control over rhetorical style and strategic orientation. We evaluate the framework across 10 synthetic legal cases and 84 three-trait team configurations, totaling over 7{,}000 simulated trials using DeepSeek-R1 and Gemini2.5Pro. Our results show that heterogeneous teams with complementary traits consistently outperform homogeneous configurations, that moderate interaction depth yields more stable verdicts, and that certain traits (notably quantitative and charismatic) contribute disproportionately to persuasive success. We further introduce a reinforcement-learning-based Trait Orchestrator that dynamically generates defense traits conditioned on the case and opposing team, discovering strategies that outperform static, human-designed trait combinations. Together, these findings demonstrate how language can be treated as a first-class strategic action space and provide a foundation for building autonomous agents capable of adaptive persuasion in multi-agent environments.
Figures & tables
Archetype
Trait
Philosophy
Behavior
Rhetorician
Charismatic
Pathos
Appeals to emotions and rapport to sway judgment beyond mere facts
Rhetorician
Folksy
Social Virtue
Appears as a peer to foster trust with the jury
Rhetorician
Moralistic
Ethics
Frames the case through the lens of “The Good”
Technician
Pedantic
Excess of Exactness
Extreme focus on the letter of the law
Technician
Quantitative
Logos
Relies on logical demonstration and hard data
Gladiator
Tenacious
Courage
Persists in difficult arguments despite pressure
Table 1. Strategic Profiles and Behavioral Characteristics Based on Aristotelian Philosophy
Figure 1. Overview of the Strategic Courtroom Framework. Prosecution and defense teams generate opening statements, engage in multi-round argumentation with shared memory, summarize positions, and a judge produces a final verdict.
Figure 2. Normalized trait-importance scores derived from model-based rankings of three-trait combinations across DeepSeek-R1, Gemini-2.5-Pro, and GPT-5. Higher values indicate traits more frequently ranked as most important within winning configurations.
Figure 3. Cumulative reward of the RL-based Trait Orchestrator during training, showing convergence toward stable positive returns as trait generation improves.
Figure 4. Cumulative judge confidence over training episodes for the RL-based Trait Orchestrator, illustrating increasing certainty in favorable defense outcomes.
Figure 5. Cumulative defense win rate over training episodes for the RL-based Trait Orchestrator, demonstrating learning progress compared to early random performance.
Method
Avg Defense Elo
Win Rate (%)
Best Static (2 Traits)
1885.3
37.5
Best Static (3 Traits)
1869.1
36.2
RL Orchestrator
1912.4
41.1
Table 8. Performance comparison between best static trait configurations and the RL-based Trait Orchestrator.
Appendix figures & tables22 assets
Supplementary material from the paper’s appendix.
Appendix
Trait
Archetype
Full Description
Charismatic
Rhetorician
Appeals to the audience’s emotions and rapport to sway judgment beyond mere facts.
Folksy
Rhetorician
The “Mean” of friendliness; appearing as a peer to the jury to foster trust.
Moralistic
Rhetorician
Frames the case through the lens of “The Good,” focusing on ultimate justice.
Pedantic
Technician
Extreme focus on the “letter” of the law, often at the expense of the “spirit” or equity.
Quantitative
Technician
Relies on logical demonstration and hard data to prove a point (Syllogistic reasoning).
Tenacious
Gladiator
The virtue of persisting in a difficult course of action despite legal or social pressure.
Appendix
Table 9. Complete Trait Definitions
Figure 6. Trait confidence analysis for Single Agent, 1 Trait, 1 Round using DeepSeek-R1. Left: Average judge confidence when a trait wins versus loses. Right: Mean confidence across traits for winning and losing cases.
Figure 7. Elo rankings of traits under Single Agent, 1 Trait, 1 Round using DeepSeek-R1, shown for overall performance, prosecution role, and defense role.
Figure 11
Figure 10. Trait confidence analysis for Single Agent, 1 Trait, 2 Rounds using DeepSeek-R1. Left: Average judge confidence when a trait wins versus loses. Right: Mean confidence across traits for winning and losing cases.
Figure 11. Elo rankings of traits under Single Agent, 1 Trait, 2 Rounds using DeepSeek-R1, shown for overall performance, prosecution role, and defense role.
Figure 14
Figure 14. Trait confidence analysis for Single Agent, 1 Trait, 3 Rounds using DeepSeek-R1. Left: Average judge confidence when a trait wins versus loses. Right: Mean confidence across traits for winning and losing cases.
Figure 15. Elo rankings of traits under Single Agent, 1 Trait, 3 Rounds using DeepSeek-R1, shown for overall performance, prosecution role, and defense role.
Figure 17
Figure 18. Trait confidence analysis for Single Agent, 2 Traits, 3 Rounds using Gemini-2.5-Pro. Left: Average judge confidence when a trait wins versus loses. Right: Mean confidence across traits for winning and losing cases.
Figure 19. Elo rankings of traits under Single Agent, 2 Traits, 3 Rounds using Gemini-2.5-Pro, shown for overall performance, prosecution role, and defense role.
Figure 20
Figure 22. Trait confidence analysis for Team, 1 Trait, 2 Rounds using DeepSeek-R1. Left: Average judge confidence when a trait wins versus loses. Right: Mean confidence across traits for winning and losing cases.
Figure 23. Elo rankings of traits under Team, 1 Trait, 2 Rounds using DeepSeek-R1, shown for overall performance, prosecution role, and defense role.
Figure 23
Figure 26. Trait confidence analysis for Team, 1 Trait, 3 Rounds using DeepSeek-R1. Left: Average judge confidence when a trait wins versus loses. Right: Mean confidence across traits for winning and losing cases.
Figure 27. Elo rankings of traits under Team, 1 Trait, 3 Rounds using DeepSeek-R1, shown for overall performance, prosecution role, and defense role.
Figure 26
Figure 30. Trait confidence analysis for Team, 2 Traits, 3 Rounds using Gemini-2.5-Pro. Left: Average judge confidence when a trait wins versus loses. Right: Mean confidence across traits for winning and losing cases.
Figure 31. Elo rankings of traits under Team, 2 Traits, 3 Rounds using Gemini-2.5-Pro, shown for overall performance, prosecution role, and defense role.
Artificial Intelligence is increasingly applied to the field of law, and has the potential to increase access to justice. One particular movement that is gaining traction is that of agentic AI, wherein AI agents, based on Large Language Models (LLMs) can take autonomous actions. In particular, multi-agent approaches in the legal domain remain largely unexplored. In this paper, we investigate multi-agent deliberation methods for legal reasoning tasks using LLMs. We explore multi-agent deliberation (MAD) and introduce two novel multi-agent frameworks inspired by courtroom procedures and legal argumentation. Our experiments on both legal and non-legal benchmarks reveal that multi-agent frameworks achieve comparable overall performance to baseline large language models, but produce significantly distinct answers. Notably, these approaches can successfully solve cases that the baseline fails to address, and vice versa. We conduct a qualitative evaluation and highlight scenarios where multi-agent frameworks outperform monolithic approaches. For example, multi-agent approaches appear better suited for answering questions that require critical thinking from multiple perspectives. Our work positions multi-agent systems as a promising direction for AI in the legal domain, while demonstrating the potential of law-inspired multi-agent approaches for deliberation.
Cor Steging, Ludi van Leeuwen, Tadeusz Zbiegień
Bernoulli Institute of Mathematics, Computer Science and Artificial Intelligence, University of Groningen The Netherlands · Department of Legal Theory, Jagiellonian University Poland
As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and construct a controlled environment in which strategic behavior can be directly observed and measured. We introduce a large-scale multi-agent simulation in a simplified model of New York City, where LLM-driven agents interact under opposing incentives. Blue agents aim to reach their destinations efficiently, while Red agents attempt to divert them toward billboard-heavy routes using persuasive language to maximize advertising revenue. Hidden identities make navigation socially mediated, forcing agents to decide when to trust or deceive. We study policy learning through an iterative simulation pipeline that updates agent policies across repeated interaction rounds using Kahneman-Tversky Optimization (KTO). Blue agents are optimized to reduce billboard exposure while preserving navigation efficiency, whereas Red agents adapt to exploit remaining weaknesses. Across iterations, the best Blue policy improves task success from 46.0% to 57.3%, although susceptibility remains high at 70.7%. Later policies exhibit stronger selective cooperation while preserving trajectory efficiency. However, a persistent safety-helpfulness trade-off remains: policies that better resist adversarial steering do not simultaneously maximize task completion. Overall, our results show that LLM agents can exhibit limited strategic behavior, including selective trust and deception, while remaining highly vulnerable to adversarial persuasion.
Aarush Sinha, Arion Das, Soumyadeep Nag +7
University of Copenhagen · IIIT Ranchi · ISI Kolkata +6
While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly structured, knowledge-heavy legal domains remains under-explored. In this work, we introduce the Legal Multi-Agent Debate (L-MAD) framework to systematically evaluate different debate structures and aggregation methods within Legal Textual Entailment. By assigning distinct expert personas to multiple agents, L-MAD improves upon strong single-agent baselines by up to 8%. Furthermore, analyzing how debate scales reveals a clear trade-off: increasing the agent population reduces inconsistency and improves accuracy, whereas extending discussion rounds induces a detrimental over-deliberation drift where agents reinforce each other's mistakes. Ultimately, our findings outline the practical boundaries and safety margins of deploying collaborative multi-agent systems in high-stakes legal reasoning environments.