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

DevFeed: [KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks](<https://devfeed.tech/articles/kdaso-knowledge-data-dual-driven-automated-skill-optimization-for-liability-adjudication-tasks-120143.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06972>)

Author: Zi-Jian Cheng, Weiming Wu, Jie Meng, Zhen Peng, Shan Huang, Qun Li, Guobing Wu, Lan-Zhe Guo

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [data](<https://devfeed.tech/tags/data.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [legal](<https://devfeed.tech/tags/legal.md>), [liability](<https://devfeed.tech/tags/liability.md>), [logic](<https://devfeed.tech/tags/logic.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [ride-hailing](<https://devfeed.tech/tags/ride-hailing.md>), [routing](<https://devfeed.tech/tags/routing.md>), [skills](<https://devfeed.tech/tags/skills.md>)

## AI overview

KDASO targets three problems in skill-based liability adjudication: libraries can become stale, skill descriptions can lead LLMs away from expert logic, and large collections can exceed context limits. It updates skills from recent, similar adjudication data, refines them using analysis of LLM execution trajectories, and routes tasks to skills within a context budget. The abstract reports better performance than general-purpose and domain-specific baselines across ride-hailing adjudication, legal liability determination, and logical reasoning judgment, plus an 8.96% improvement when transferring skills to concept-similar scenarios. It also reports sustained gains during continuous optimization; the supplied excerpt gives no further methodological or metric details.

## Source excerpt

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.