# Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation

Source: [Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation](<https://www.sota2.com/research/paper/69d732c47d0172140ec76dd5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-28T05:00:05.404Z

Authors: Philipp D. Siedler

Published: 2026-04-08T12:46:03.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Adversarial legal persuasion on Strategic Courtroom Framework 10 legal cases trial flow](<https://www.sota2.com/research/sota/adversarial-legal-persuasion-on-strategic-courtroom-framework-10-legal-cases-trial-flow.md>): Adversarial legal persuasion; Strategic Courtroom Framework 10 legal cases trial flow; Average Defense Elo: 1912.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.07028>)

[PDF](<https://arxiv.org/pdf/2604.07028.pdf>)