Agent Fine-tuning through Distillation for Domain-specific LLMs in Microdomains

• URL: http://arxiv.org/abs/2510.00482v1
• Date: Wed, 01 Oct 2025 04:04:53 GMT
• Title: Agent Fine-tuning through Distillation for Domain-specific LLMs in Microdomains
• Authors: Yawen Xue, Masaya Tsunokake, Yuta Koreeda, Ekant Muljibhai Amin, Takashi Sumiyoshi, Yasuhiro Sogawa,
• Abstract summary: Agentic large language models (LLMs) have become prominent for autonomously interacting with external environments.<n>This paper explores agent fine-tuning for domain adaptation within Hitachi's JP1 microdomain for specialized IT operations.
• Score: 6.323778761045108
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Agentic large language models (LLMs) have become prominent for autonomously interacting with external environments and performing multi-step reasoning tasks. Most approaches leverage these capabilities via in-context learning with few-shot prompts, but this often results in lengthy inputs and higher computational costs. Agent fine-tuning offers an alternative by enabling LLMs to internalize procedural reasoning and domain-specific knowledge through training on relevant data and demonstration trajectories. While prior studies have focused on general domains, their effectiveness in specialized technical microdomains remains unclear. This paper explores agent fine-tuning for domain adaptation within Hitachi's JP1 middleware, a microdomain for specialized IT operations. We fine-tuned LLMs using JP1-specific datasets derived from domain manuals and distilled reasoning trajectories generated by LLMs themselves, enhancing decision making accuracy and search efficiency. During inference, we used an agentic prompt with retrieval-augmented generation and introduced a context-answer extractor to improve information relevance. On JP1 certification exam questions, our method achieved a 14% performance improvement over the base model, demonstrating the potential of agent fine-tuning for domain-specific reasoning in complex microdomains.

Related papers

• Building Domain-Specific Small Language Models via Guided Data Generation [5.404790079646315]
  Large Language Models (LLMs) have shown remarkable success in supporting a wide range of knowledge-intensive tasks.<n>In specialized domains, there is growing interest in leveraging LLMs to assist subject matter experts with domain-specific challenges.<n>Many open-source models demand significant computational resources for effective domain adaptation and deployment.<n>We present a cost-efficient and scalable training pipeline that combines guided synthetic data generation from a small seed corpus with bottom-up domain data.
  arXiv  Detail & Related papers  (2025-11-23T07:19:31Z)
• Domain Adaptation of LLMs for Process Data [7.611051482274626]
  Large Language Models (LLMs) have emerged as a prominent area of interest across various research domains, including Process Mining (PM)<n>This study investigates the direct adaptation of pretrained LLMs to process data without natural language reformulation.<n>More specifically, we focus on parameter-efficient fine-tuning techniques to mitigate the computational overhead typically associated with such models.
  arXiv  Detail & Related papers  (2025-09-03T09:21:35Z)
• Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs [56.76586846269894]
  Multimodal Large Language Models (MLLMs) have achieved success across various domains.<n>Despite its importance, the study of knowledge sharing among domain-specific MLLMs remains largely underexplored.<n>We propose a unified parameter integration framework that enables modular composition of expert capabilities.
  arXiv  Detail & Related papers  (2025-06-30T15:07:41Z)
• Beyond Benchmarks: A Novel Framework for Domain-Specific LLM Evaluation and Knowledge Mapping [0.7555681642774916]
  The paper addresses two critical challenges in language model (LM) evaluation: creating reliable domain-specific benchmarks and understanding knowledge representation during domain adaptation.<n>We introduce a deterministic pipeline that converts raw domain corpora into completion-type benchmarks without relying on LMs or human curation.<n>Our approach generates domain-specific keywords and related word lists using TF and Term TF-IDF methods and constructs prompt-target pairs.<n>We evaluate models by measuring their ability to complete these prompts with the correct domain-specific targets, providing a direct assessment of domain knowledge with low computational cost.
  arXiv  Detail & Related papers  (2025-06-09T11:30:12Z)
• Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation [36.41708236431343]
  Large language models (LLMs) have been increasingly adopted for machine translation (MT)<n>Our work studies domain-adapted MT with LLMs through a careful prompting setup.<n>We find that demonstrations consistently outperform terminology, and retrieval consistently outperforms generation.
  arXiv  Detail & Related papers  (2025-03-06T22:23:07Z)
• On Domain-Adaptive Post-Training for Multimodal Large Language Models [78.65220510401045]
  This paper systematically investigates domain adaptation of MLLMs via post-training.<n>We focus on data synthesis, training pipeline, and task evaluation.<n>We conduct experiments in high-impact domains such as biomedicine, food, and remote sensing.
  arXiv  Detail & Related papers  (2024-11-29T18:42:28Z)
• Exploring Language Model Generalization in Low-Resource Extractive QA [57.14068405860034]
  We investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift.<n>We devise a series of experiments to explain the performance gap empirically.
  arXiv  Detail & Related papers  (2024-09-27T05:06:43Z)
• PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs [49.32067576992511]
  Large language models often fall short of the performance achieved by domain-specific state-of-the-art models. One potential approach to enhance domain-specific capabilities of LLMs involves fine-tuning them using corresponding datasets. We propose Preference Adaptation for Enhancing Domain-specific Abilities of LLMs (PANDA) Our experimental results reveal that PANDA significantly enhances the domain-specific ability of LLMs on text classification and interactive decision tasks.
  arXiv  Detail & Related papers  (2024-02-20T09:02:55Z)
• A Self-enhancement Approach for Domain-specific Chatbot Training via Knowledge Mining and Digest [62.63606958140248]
  Large Language Models (LLMs) often encounter challenges when dealing with intricate and knowledge-demanding queries in specific domains. This paper introduces a novel approach to enhance LLMs by effectively extracting the relevant knowledge from domain-specific textual sources. We train a knowledge miner, namely LLMiner, which autonomously extracts Question-Answer pairs from relevant documents.
  arXiv  Detail & Related papers  (2023-11-17T16:09:10Z)
• Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations [50.81844184210381]
  We propose a general paradigm that augments large language models with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE. This paradigm relies on a domain knowledge extractor, working in three steps: 1) preparing effective knowledge for the task; 2) selecting the knowledge for each specific sample; and 3) expressing the knowledge in an LLM-understandable way.
  arXiv  Detail & Related papers  (2023-11-16T07:09:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.