相关论文: Instruct, Not Assist: LLM-based Multi-Turn Plannin…

Intelligent tutoring systems have demonstrated effectiveness in teaching formal propositional logic proofs, but their reliance on template-based explanations limits their ability to provide personalized student feedback. While large…

Code LLMs have shown promising results with converting tasks in natural language to programs that can be executed by service robots. We are interested in finetuning small, specialized LLMs for this purpose, but collecting datasets of…

Personalized chatbot-based teaching assistants can be crucial in addressing increasing classroom sizes, especially where direct teacher presence is limited. Large language models (LLMs) offer a promising avenue, with increasing research…

Intelligent tutoring systems (ITSs) that imitate human tutors and aim to provide immediate and customized instructions or feedback to learners have shown their effectiveness in education. With the emergence of generative artificial…

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However,…

One-to-one tutoring is widely considered the gold standard for personalized education, yet it remains prohibitively expensive to scale. To evaluate whether generative AI might help expand access to this resource, we conducted an exploratory…

In this work, we provide a systematic analysis of how large language models (LLMs) contribute to solving planning problems. In particular, we examine how LLMs perform when they are used as problem solver, solution verifier, and heuristic…

This paper explores the synergy between human cognition and Large Language Models (LLMs), highlighting how generative AI can drive personalized learning at scale. We discuss parallels between LLMs and human cognition, emphasizing both the…

Large Language Models (LLMs) have shown strong performance in automated source-to-target code translation through pretraining on extensive code corpora. However, mainstream LLM-based code translation methods suffer from two critical…

Large Language Models (LLMs) show promise in code generation tasks. However, their code-writing abilities are often limited in scope: while they can successfully implement simple functions, they struggle with more complex tasks. A…

This paper explores role engineering as an effective paradigm for customizing Large Language Models (LLMs) into specialized AI tutors for physics education. We demonstrate this methodology by designing a Socratic physics problem-solving…

Large Language Models (LLMs) have demonstrated remarkable performance across multiple tasks through in-context learning. For complex reasoning tasks that require step-by-step thinking, Chain-of-Thought (CoT) prompting has given impressive…

Large Language Models (LLMs) were shown to struggle with long-term planning, which may be caused by the limited way in which they explore the space of possible solutions. We propose an architecture where a Reinforcement Learning (RL) Agent…

Automated agent workflows can enhance the problem-solving ability of large language models (LLMs), but common search strategies rely on stochastic exploration and often traverse implausible branches. This occurs because current pipelines…

In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method. We investigate the practical utility of two…

Chain-of-thought (CoT), tree-of-thought (ToT), and related techniques work surprisingly well in practice for some complex reasoning tasks with Large Language Models (LLMs), but why? This work seeks the underlying reasons by conducting…

Code data in large language model (LLM) pretraining is recognized crucial not only for code-related tasks but also for enhancing general intelligence of LLMs. Current open-source LLMs often heavily rely on human effort to produce their code…

Can a model learn to escape its own learning plateau? Reinforcement learning methods for finetuning large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental…

While Large Language Models (LLMs) have demonstrated remarkable fluency in educational dialogues, most generative tutors primarily operate through intuitive, single-pass generation. This reliance on fast thinking precludes a dedicated…

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…