Related papers: Evidence-Decision-Feedback: Theory-Driven Adaptive…

Hierarchical review workflows, where a second-tier reviewer (Checker) corrects first-tier (Maker) decisions, generate valuable correction signals that encode why initial judgments failed. However, learning from these signals is hindered by…

We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty…

Grounding the reasoning ability of large language models (LLMs) for embodied tasks is challenging due to the complexity of the physical world. Especially, LLM planning for multi-agent collaboration requires communication of agents or credit…

Recent agent-based recommendation frameworks aim to simulate user behaviors by incorporating memory mechanisms and prompting strategies, but they struggle with hallucinating non-existent items and full-catalog ranking. Besides, a largely…

UML and ER diagrams are foundational in computer science education but come with challenges for learners due to the need for abstract thinking, contextual understanding, and mastery of both syntax and semantics. These complexities are…

Emotional Support Conversation (ESC) systems aim to alleviate users' emotional difficulties and provide long-term, systematic support for emotional well-being. However, most large language model (LLM)-based ESC systems rely on predefined…

We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their…

LLM-based automatic heuristic design has shown promise for generating executable heuristics for combinatorial optimization, but existing methods mainly rely on delayed endpoint performance. We propose a \emph{teacher-aware evolutionary…

We study how prompt-level inductive biases influence the cognitive behavior of large language models (LLMs) in instructional dialogue. We introduce a symbolic scaffolding method paired with a short-term memory schema designed to promote…

Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures. This has given rise to a variety of…

Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by feedback-conditioned planning across generations. However, how planning decisions attribute and combine…

High-quality, multi-turn instructional dialogues between novices and experts are essential for developing AI systems that support teaching, learning, and decision-making. These dialogues often involve scaffolding -- the process by which an…

Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through…

As language model (LM) agents become increasingly capable and adopted in real-world applications, there is a growing need for scalable evaluation frameworks beyond costly, manually designed benchmarks. We propose information-theoretic…

Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teacher training. While Large Language Models (LLMs) offer…

As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly focus on binary outcome accuracy. Instead, an effective AI tutor must exhibit faithful reasoning,…

The integration of LLM-generated feedback into educational settings has shown promise in enhancing student learning outcomes. This paper presents a novel LLM-driven system that provides targeted feedback for conceptual designs in a Database…

Foundation models (FMs) have emerged as a promising approach for time series forecasting. While effective, FMs typically remain fixed during deployment due to the high computational costs of learning them online. Consequently, deployed FMs…

Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…

We introduce a modular prompting framework that supports safer and more adaptive use of large language models (LLMs) across dynamic, user-centered tasks. Grounded in human learning theory, particularly the Zone of Proximal Development…