paper-with-me

홈 › Papers

MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching

2025-06-03 · Liang Yue, Yihong Tang, Kehai Chen, Jie Liu, Min Zhang

Instruction fine-tuning is crucial in NLP tasks, enhancing pretrained models' instruction-following capabilities and task-specific performance. However, obtaining high-quality fine-tuning data for large models is challenging due to data collection difficulties and high production costs. To address this, we propose MASTER, a novel data augmentation method that enriches original data through interactions among multiple agents with varying cognitive levels. We simulate three pedagogically grounded teaching scenarios, leveraging multi-agent conversations to generate high-quality teacher-student interaction data. Utilizing MASTER, we construct BOOST-QA, a fine-tuning dataset augmented from existing datasets like Orca-Math-200k, ProcQA, and OpenHermes2.5. Experiments show that models fine-tuned with BOOST-QA perform excellently across multiple benchmarks, demonstrating strong multitask generalization. Notably, MASTER significantly improves models' reasoning abilities in complex tasks, providing valuable insights for future research.

📄 PDF Abstract BibTeX arXiv:2506.02689

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationInstruction FollowingLanguage ModelingLanguage ModellingLarge Language ModelMath

Similar Papers 제목 키워드 기반

MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Framework

2025-05-24 · Yifan Zhu, Chao Zhang, Xin Shi, Xueqiao Zhang 외

Large Language Models (LLMs)-based Multi-Agent Systems (MAS) exhibit remarkable problem-solving and task planning capabilities across diverse domains due to their specialized agentic roles and collaborative interactions.…

Task Planning

Empowering LLMs in Decision Games through Algorithmic Data Synthesis

2025-03-18 · Haolin Wang, Xueyan Li, Yazhe Niu, Shuai Hu 외

Large Language Models (LLMs) have exhibited impressive capabilities across numerous domains, yet they often struggle with complex reasoning and decision-making tasks. Decision-making games, which inherently require multi…

Decision Making

You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function Calling

2024-09-11 · Jaewoo Song, Andrew Zhu, Chris Callison-Burch

Developing a consistent and reliable AI game master for text-based games is a challenging task due to the limitations of large language models (LLMs) and the complexity of the game master's role. This paper presents a no…

text-based games

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

2026-04-19 · Xinyu Zhu, Yuzhu Cai, Zexi Liu, Cheng Wang 외 arxiv

The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly stati…

Static Vs. Agentic Game Master AI for Facilitating Solo Role-Playing Experiences

2025-02-26 · Nicolai Hejlesen Jørgensen, Sarmilan Tharmabalan, Ilhan Aslan, Nicolai Brodersen Hansen 외

This paper presents a game master AI for single-player role-playing games. The AI is designed to deliver interactive text-based narratives and experiences typically associated with multiplayer tabletop games like Dungeon…

Prompt Engineering