Related papers: Worst-Case Discovery and Runtime Protection for RL…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Reinforcement Learning (RL) has gained significant momentum in the development of network protocols. However, RL-based protocols are still in their infancy, and substantial research is required to build deployable solutions. Developing a…

Constrained reinforcement learning (CRL) has gained significant interest recently, since safety constraints satisfaction is critical for real-world problems. However, existing CRL methods constraining discounted cumulative costs generally…

DeepSearch paradigms have become a core enabler for deep reasoning models, allowing them to invoke external search tools to access up-to-date, domain-specific knowledge beyond parametric boundaries, thereby enhancing the depth and factual…

Android malware detectors often degrade after deployment because of concept drift, while full retraining at each maintenance step is costly. We propose a chronological adaptive maintenance framework that models deployment-time maintenance…

In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augmented generation (RAG) also relies on context, but retrieved…

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

Modern control designs in robotics, aerospace, and cyber-physical systems rely heavily on real-world data obtained through system outputs. However, these outputs can be compromised by system faults and malicious attacks, distorting critical…

RL post-training for LLMs has been widely scaled to enhance reasoning and tool-using capabilities. However, RL post-training interleaves training and inference workloads, exposing the system to faults from both sides. Existing fault…

Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across LLMs under RAG necessitates intelligent routing mechanisms,…

Inverter-based distributed energy resources provide the possibility for fast time-scale voltage control by quickly adjusting their reactive power. The power-electronic interfaces allow these resources to realize almost arbitrary control…

Although large language models (LLMs) are increasingly used in security-critical workflows, practitioners lack quantitative guidance on which safeguards are worth deploying. This paper introduces a decision-oriented framework and…

Web service applications are distributed processes that are composed of dynamically bounded services. In our previous work [15], we have described a framework for performing runtime monitoring of web service against behavioural correctness…

Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…

In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods. RL algorithms have become…

We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile…

Computer-use agents are increasingly capable of operating on real operating systems, but this capability has also increased the risks posed by prompt injection, indirect instructions, and visual attacks. Existing defenses typically rely on…

Large language models (LLMs) are reshaping numerous facets of our daily lives, leading widespread adoption as web-based services. Despite their versatility, LLMs face notable challenges, such as generating hallucinated content and lacking…

Safe reinforcement learning (Safe RL) aims to ensure policy performance while satisfying safety constraints. However, most existing Safe RL methods assume benign environments, making them vulnerable to adversarial perturbations commonly…

Reinforcement learning with general utilities (RLGU) offers a unifying framework to capture several problems beyond standard expected returns, including imitation learning, pure exploration, and safe RL. Despite recent fundamental advances…