{"slug": "kdaso-knowledge-data-dual-driven-automated-skill-optimization-for-liability", "title": "KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks", "summary": "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.", "body_md": "arXiv:2611.06972v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/kdaso-knowledge-data-dual-driven-automated-skill-optimization-for-liability", "canonical_source": "https://arxiv.org/abs/2611.06972", "published_at": "2026-11-06 05:00:00+00:00", "updated_at": "2026-11-06 05:22:22.760028+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-agents"], "entities": ["KDASO", "arXiv", "Large Language Models"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/kdaso-knowledge-data-dual-driven-automated-skill-optimization-for-liability", "markdown": "https://wpnews.pro/news/kdaso-knowledge-data-dual-driven-automated-skill-optimization-for-liability.md", "text": "https://wpnews.pro/news/kdaso-knowledge-data-dual-driven-automated-skill-optimization-for-liability.txt", "jsonld": "https://wpnews.pro/news/kdaso-knowledge-data-dual-driven-automated-skill-optimization-for-liability.jsonld"}}