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

As large language models (LLMs) continue to grow in size, their abilities to tackle complex tasks have significantly improved. However, issues such as hallucination and the lack of up-to-date knowledge largely remain unresolved. Knowledge…

Multi-task reinforcement learning endeavors to efficiently leverage shared information across various tasks, facilitating the simultaneous learning of multiple tasks. Existing approaches primarily focus on parameter sharing with carefully…

This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically…

In multi-agent tasks, the central challenge lies in the dynamic adaptation of strategies. However, directly conditioning on opponents' strategies is intractable in the prevalent deep reinforcement learning paradigm due to a fundamental…

Knowledge graph embedding (KGE) is a technique that enhances knowledge graphs by addressing incompleteness and improving knowledge retrieval. A limitation of the existing KGE models is their underutilization of ontologies, specifically the…

The quality assurance of the knowledge graph is a prerequisite for various knowledge-driven applications. We propose KGClean, a novel cleaning framework powered by knowledge graph embedding, to detect and repair the heterogeneous dirty…

This paper presents Auto-RubikAI, a modular autonomous planning framework that integrates a symbolic Knowledge Base (KB), a vision-language model (VLM), and a large language model (LLM) to solve structured manipulation tasks exemplified by…

This study investigates an explainable reasoning method for financial decision-making based on knowledge-enhanced large language model agents. To address the limitations of traditional financial decision methods that rely on parameterized…

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed…

In reinforcement learning, agents that consider the context, or current state, when selecting source policies for transfer have been shown to outperform context-free approaches. However, none of the existing approaches transfer knowledge…

Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce coordinate-free strategies yet suffer from learning under…

We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained…

Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement.…

We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks. We consider tasks specified as linear temporal logic (LTL) formulae,…

Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to ground the output of…

Fine-tuning adapts pretrained models for specific tasks but poses the risk of catastrophic forgetting (CF), where critical knowledge from pretraining is overwritten. To address the issue of CF in a general-purpose framework, we propose…

Today's advanced Reinforcement Learning algorithms produce black-box policies, that are often difficult to interpret and trust for a person. We introduce a policy distilling algorithm, building on the CN2 rule mining algorithm, that…

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing…

Software vulnerabilities are a challenge in cybersecurity. Manual security patches are often difficult and slow to be deployed, while new vulnerabilities are created. Binary code vulnerability detection is less studied and more complex…

System-level emulators have been used extensively for system design, debugging and evaluation. They work by providing a system-level virtual machine to support a guest operating system (OS) running on a platform with the same or different…