KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks

A new arXiv paper (2611.06972v1) proposes KDASO, a Knowledge-Data Dual-Driven Automated Skill Optimization method that continuously evolves a skill library for liability adjudication tasks using LLMs. KDASO combines neighborhood-conditioned induction from recent adjudication data, execution-aligned refinement based on LLM trajectory analysis, and context-budgeted routing for scalable skill selection. Experiments on ride-hailing adjudication, legal liability determination, and logical reasoning judgment show KDASO outperforms general-purpose and domain-specific baselines and achieves an 8.96% improvement when transferring skills to concept-similar scenarios.

arXiv:2611.06972v1 Announce Type: new Abstract: Liability adjudication tasks e.g., legal charge determination require analyzing event descriptions against domain-specific skills to determine whether a party should bear liability. While Large Language Models LLMs have shown promise in this area by leveraging executable skills for interpretable reasoning, existing approaches face three critical limitations: skill libraries become stale as real-world scenarios dynamically evolve, skill descriptions often suffer from a semantic execution gap where LLMs deviate from intended expert logic, and growing skill collections exceed context budgets causing critical skill omission. To address these challenges, we propose Knowledge-Data Dual-Driven Automated Skill Optimization KDASO , which continuously evolves a skill library through neighborhood-conditioned induction from recent adjudication data, execution-aligned refinement based on LLM trajectory analysis, and context-budgeted routing for scalable skill selection. Experiments across ride-hailing adjudication, legal liability determination, and logical reasoning judgment demonstrate that KDASO significantly outperforms current general-purpose and domain-specific baselines. KDASO further achieves 8.96% improvement when transferring skills to concept-similar scenarios and maintains consistent performance gains through continuous optimization, underscoring the high transferability and stability of generated skills.