# EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning

arXiv: https://arxiv.org/abs/2601.03725 · HTML: https://mlsanity.com/paper/2601.03725/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 50 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Builds on (most cited first, 30 of 37)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains](https://mlsanity.com/paper/2503.23829/) (2025)
- [SaulLM-7B: A pioneering Large Language Model for Law](https://mlsanity.com/paper/2403.03883/) (2024)
- [JEC-QA: A Legal-Domain Question Answering Dataset](https://mlsanity.com/paper/1911.12011/) (2019)
- [Self-Evolving Curriculum for LLM Reasoning](https://mlsanity.com/paper/2505.14970/) (2025)
- [Rule Based Rewards for Language Model Safety](https://mlsanity.com/paper/2411.01111/) (2024)
- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)
- [LUQ: Long-text Uncertainty Quantification for LLMs](https://mlsanity.com/paper/2403.20279/) (2024)
- [Language Model Self-improvement by Reinforcement Learning Contemplation](https://mlsanity.com/paper/2305.14483/) (2023)
- [A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law](https://mlsanity.com/paper/2405.01769/) (2024)
- [Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.10708/) (2025)
- [EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling](https://mlsanity.com/paper/2403.14541/) (2024)
- [Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?](https://mlsanity.com/paper/2405.06105/) (2024)
- [Entropy Law: The Story Behind Data Compression and LLM Performance](https://mlsanity.com/paper/2407.06645/) (2024)
- [Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs](https://mlsanity.com/paper/2410.08020/) (2024)
- [LawLLM: Law Large Language Model for the US Legal System](https://mlsanity.com/paper/2407.21065/) (2024)
- [Fine-tuning and Utilization Methods of Domain-specific LLMs](https://mlsanity.com/paper/2401.02981/) (2024)
- [Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning](https://mlsanity.com/paper/2405.07490/) (2024)
- [A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions](https://mlsanity.com/paper/2412.19823/) (2024)
- [Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward](https://mlsanity.com/paper/2509.01321/) (2025)
- [Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models](https://mlsanity.com/paper/2406.14115/) (2024)
- [MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster](https://mlsanity.com/paper/2507.19017/) (2025)
- [Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning](https://mlsanity.com/paper/2508.21589/) (2025)

## Built on by (most cited first, 2 of 2)

- [DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation](https://mlsanity.com/paper/2605.09188/) (2026)
- [Reinforcement Learning with Promising Tokens for Large Language Models](https://mlsanity.com/paper/2602.03195/) (2026)

## Abstract (arXiv)

Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is curriculum learning, which pre-orders training samples based on metrics like difficulty to improve learning efficiency compared to a random sampling strategy. However, most existing methods for LLM fine-tuning rely on a static curriculum, designed prior to training, which lacks adaptability to the model's evolving needs during fine-tuning. To address this, we propose EDCO, a novel framework based on two key concepts: inference entropy and dynamic curriculum orchestration. Inspired by recent findings that maintaining high answer entropy benefits long-term reasoning gains, EDCO prioritizes samples with high inference entropy in a continuously adapted curriculum. EDCO integrates three core components: an efficient entropy estimator that uses prefix tokens to approximate full-sequence entropy, an entropy-based curriculum generator that selects data points with the highest inference entropy, and an LLM trainer that optimizes the model on the selected curriculum. Comprehensive experiments in communication, medicine and law domains, EDCO outperforms traditional curriculum strategies for fine-tuning Qwen3-4B and Llama3.2-3B models under supervised and reinforcement learning settings. Furthermore, the proposed efficient entropy estimation reduces computational time by 83.5% while maintaining high accuracy.