Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation
This work addresses the challenge of building autonomous agents capable of adaptive persuasion in multi-agent environments, representing an incremental advance in applying LLMs to strategic interaction domains.
The researchers tackled the problem of modeling strategic persuasion in adversarial domains like law by creating a multi-agent simulation framework where LLM agents with interpretable traits engage in iterative legal argumentation, finding that heterogeneous teams with complementary traits consistently outperform homogeneous configurations and that a reinforcement-learning-based trait orchestrator can discover strategies that beat human-designed combinations.
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.