AutoAdapt: An Automated Domain Adaptation Framework for LLMs

2026-03-09

AI Summary

This work addresses the performance limitations of large language models (LLMs) in specialized domains, where data scarcity and evolving knowledge hinder effectiveness. Existing adaptation methods often rely on manual trial-and-error, involve complex hyperparameter tuning, and incur high computational and human costs. To overcome these challenges, we propose AutoAdapt, an end-to-end automated framework that introduces a novel multi-agent debate mechanism to align user intent with data signals, while integrating external knowledge bases to minimize expert intervention. The framework features two core components: AutoRefine, an LLM-driven hyperparameter optimizer, and a multi-agent collaborative planning module. Evaluated across ten domain-specific tasks, AutoAdapt achieves an average accuracy improvement of 25% over state-of-the-art AutoML baselines, while substantially reducing both computational overhead and human effort.

Technology Category

• Machine Learning: Auto ML and Hyperparameter Tuning
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily on manual trial-and-error processes, incur significant hyperparameter complexity, and are highly sensitive to data and user preferences, all under the high cost of LLM training. Moreover, the interactions and transferability of hyperparameter choices across models/domains remain poorly understood, making adaptation gains uncertain even with substantial effort. To solve these challenges, we present AutoAdapt, a novel end-to-end automated framework for efficient and reliable LLM domain adaptation. AutoAdapt leverages curated knowledge bases from literature and open-source resources to reduce expert intervention. To narrow the search space, we design a novel multi-agent debating system in which proposal and critic agents iteratively interact to align user intent and incorporate data signals and best practices into the planning process. To optimize hyperparameters under tight budgets, we propose AutoRefine, a novel LLM-based surrogate that replaces costly black-box search. Across 10 tasks, AutoAdapt achieves a 25% average relative accuracy improvement over state-of-the-art Automated Machine Learning baselines with minimal overhead.

Problem

• domain adaptation
• large language models
• hyperparameter optimization
• automated machine learning
• specialized domains

Innovation

• Automated Domain Adaptation
• Large Language Models
• Multi-agent Debate
• Hyperparameter Optimization
• AutoRefine