arXiv:2604.07028v2 Announce Type: replace-cross 
Abstract: 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 Gemini~2.5~Pro. 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.

تم تقديم إطار المحكمة الاستراتيجية كبيئة محاكاة متعددة الوكلاء حيث تشارك فرق من وكلاء نماذج اللغة الكبيرة المشروطة بالسمات في جدل قانوني تكراري. يسمح هذا الإطار بالتحكم المنهجي في الأنماط البلاغية والتوجهات الاستراتيجية، وقد تم تقييمه عبر 10 حالات قانونية اصطناعية و84 تكوينًا لفريق، مما أدى إلى أكثر من 7000 تجربة محاكاة.

Se ha presentado el Marco de Tribunal Estratégico como un entorno de simulación multiagente donde equipos de agentes de Modelos de Lenguaje de Gran Tamaño condicionados por rasgos participan en argumentación legal iterativa. Este marco permite un control sistemático sobre los estilos retóricos y las orientaciones estratégicas, evaluado a través de 10 casos legales sintéticos y 84 configuraciones de equipo, totalizando más de 7,000 ensayos simulados.

Le Strategic Courtroom Framework a été introduit comme un environnement de simulation multi-agents où des équipes d'agents de modèles de langage conditionnés par des traits s'engagent dans une argumentation légale itérative. Ce cadre permet un contrôle systématique des styles rhétoriques et des orientations stratégiques, évalué à travers 10 cas juridiques synthétiques et 84 configurations d'équipe, totalisant plus de 7 000 essais simulés.

The Strategic Courtroom Framework has been introduced as a multi-agent simulation environment where teams of trait-conditioned Large Language Model agents engage in iterative legal argumentation. This framework allows for the systematic control of rhetorical styles and strategic orientations, evaluated across 10 synthetic legal cases and 84 team configurations, resulting in over 7,000 simulated trials.