8 papers
Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning
Xiaokun Wang, Siyu Song, Wentao Liu +1
Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students throug…
Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment
Wentao Liu, Siyu Song, Xi Chen +4
Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a cohere…
Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios
Tao Liu, Ye Lu, Ruohua Zhang +4
Evaluating large language models (LLMs) for education requires measuring how models teach, not only what they know. Existing benchmarks emphasize domain-general correctness or depe…
Automating Skill Acquisition through Large-Scale Mining of Open-Source Agentic Repositories: A Framework for Multi-Agent Procedural Knowledge Extraction
Shuzhen Bi, Mengsong Wu, Hao Hao +5
The transition from monolithic large language models (LLMs) to modular, skill-equipped agents represents a fundamental architectural shift in artificial intelligence deployment. Wh…
Scaling Laws for Educational AI Agents
Mengsong Wu, Hao Hao, Shuzhen Bi +5
While scaling laws for Large Language Models (LLMs) have been extensively studied along dimensions of model parameters, training data, and compute, the scaling behavior of LLM-base…
AutoSynth: Automated Workflow Optimization for High-Quality Synthetic Dataset Generation via Monte Carlo Tree Search
Shuzhen Bi, Chang Song, Siyu Song +5
Supervised fine-tuning (SFT) of large language models (LLMs) for specialized tasks requires high-quality datasets, but manual curation is prohibitively expensive. Synthetic data ge…