# Researchers propose KDASO for automated liability adjudication

Digest AI · Research · published 2026-11-06T05:00:00Z

Canonical: https://digestai.news/story/researchers-propose-kdaso-for-automated-liability-adjudication

## Summary

A new paper on arXiv introduces KDASO, a framework designed to improve how Large Language Models handle liability adjudication tasks, such as legal charge determination. The authors argue that current LLM approaches suffer from three main issues: skill libraries become outdated as real-world scenarios change, descriptions often fail to match the LLM's actual execution logic, and large skill collections exceed context limits, causing important skills to be missed.

KDASO addresses these problems by continuously evolving the skill library using recent adjudication data. It refines skills based on the LLM's execution trajectories and uses context-budgeted routing to select the most relevant skills without exceeding token limits. The method combines knowledge-driven and data-driven optimization to keep the system current and efficient.

Experiments in ride-hailing adjudication, legal liability, and logical reasoning show that KDASO outperforms existing general-purpose and domain-specific baselines. The authors report an 8.96% improvement when transferring skills to similar scenarios, suggesting the generated skills are stable and transferable. The paper highlights the potential for automated, interpretable reasoning in complex legal and liability contexts.

## Key points

- KDASO evolves skill libraries using recent data to prevent staleness in liability adjudication.
- The method uses context-budgeted routing to avoid omitting critical skills due to token limits.
- KDASO shows an 8.96% improvement when transferring skills to concept-similar scenarios.

## Why it matters

This research offers a scalable way to keep LLM-based legal and liability tools accurate as rules and scenarios change, reducing errors from outdated knowledge or context overflow.

## Sources

1. [KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks](https://arxiv.org/abs/2611.06972) (arXiv cs.AI, 2026-11-06, primary source)

## Cite

Digest AI, "Researchers propose KDASO for automated liability adjudication", 6 November 2026, https://digestai.news/story/researchers-propose-kdaso-for-automated-liability-adjudication

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-propose-kdaso-for-automated-liability-adjudication.json