相关论文: Kintsugi: Learning Policies by Repairing Executabl…

LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools, calling APIs, and executing actions to interact with…

This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm…

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow…

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…

We study computationally and statistically efficient reinforcement learning under the linear $Q^{\pi}$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this…

Knowledge graph (KG) embedding methods learn geometric representations of entities and relations to predict plausible missing knowledge. These representations are typically assumed to capture rule-like inference patterns. However, our…

Knowledge base completion is formulated as a binary classification problem in this work, where an XGBoost binary classifier is trained for each relation using relevant links in knowledge graphs (KGs). The new method, named KGBoost, adopts a…

How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on…

Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient…

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…

Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to…

The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any…

Given a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of success, prototypicality, and efficiency, all without moving a…

Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during…

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack…

In Reinforcement Learning interpretability generally means to provide insight into the agent's mechanisms such that its decisions are understandable by an expert upon inspection. This definition, with the resulting methods from the…

The quest for interpretable reinforcement learning is a grand challenge for the deployment of autonomous decision-making systems in safety-critical applications. Modern deep reinforcement learning approaches, while powerful, tend to produce…

Knowledge-based programs specify multi-agent protocols with epistemic guards that abstract from how agents learn and record facts or information about other agents and the environment. Their interpretation involves a non-monotone mutual…

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…

Modern GUI agents typically rely on a model-centric and step-wise interaction paradigm, where LLMs must re-interpret the UI and re-decide actions at every screen, which is fragile in long-horizon tasks. In this paper, we propose Executable…