Related papers: ARISE -- Adaptive Refinement and Iterative Scenari…

Motivated by the substantial achievements observed in Large Language Models (LLMs) in the field of natural language processing, recent research has commenced investigations into the application of LLMs for complex, long-horizon sequential…

LLMs have advanced tool-using agents for real-world applications, yet they often lead to unexpected behaviors or results. Beyond obvious failures, the subtle issue of "intent deviation" severely hinders reliable evaluation and performance…

Evaluating and improving planning for autonomous vehicles requires scalable generation of long-tail traffic scenarios. To be useful, these scenarios must be realistic and challenging, but not impossible to drive through safely. In this…

Safety-critical scenarios are essential for the development of autonomous vehicles (AVs) but are rare in real-world driving data. While simulation offers a way to generate such scenarios, manually designed test cases lack scalability, and…

The inspection-planning problem calls for computing motions for a robot that allow it to inspect a set of points of interest (POIs) while considering plan quality (e.g., plan length). This problem has applications across many domains where…

Runtime uncertainty such as unpredictable resource unavailability, changing environmental conditions and user needs, as well as system intrusions or faults represents one of the main current challenges of self-adaptive systems. Moreover,…

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

Autonomous driving systems require comprehensive evaluation in safety-critical scenarios to ensure safety and robustness. However, such scenarios are rare and difficult to collect from real-world driving data, necessitating simulation-based…

The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…

The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies…

Effective exploration remains a key challenge in RL, especially with non-stationary rewards or high-dimensional policies. We introduce ARISE, a lightweight framework that enhances reinforcement learning by augmenting standard…

The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajectories obtained from running a solver…

Driving in compliance with traffic laws and regulations is a basic requirement for human drivers, yet autonomous vehicles (AVs) can violate these requirements in diverse real-world scenarios. To encode law compliance into AV systems,…

Ensuring the safety and reliability of Automated Driving Systems (ADS) remains a critical challenge, as traditional verification methods such as large-scale on-road testing are prohibitively costly and time-consuming.To address…

In the instruction fine-tuning of large language models (LLMs), it is widely recognized that a few high-quality instructions are superior to a large number of low-quality instructions. At present, many instruction selection methods have…

Automated red-teaming methods for large language models typically optimize attack prompts within a fixed, human-designed strategy, leaving the attack strategy itself unchanged. We instead optimize the strategy. We propose AutoRISE, a method…

Since their inception, programming languages have trended towards greater readability and lower barriers for programmers. Following this trend, natural language can be a promising type of programming language that provides great flexibility…

In the past year, large language models (LLMs) have had remarkable success in domains outside the traditional natural language processing, and their capacity is further expanded into the so-called LLM agents when connected with external…

A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the latter focusing on their logical and structural validity.…

Non-Axiomatic Reasoning Systems (NARS) provide a framework for building adaptive agents that operate under insufficient knowledge and resources. However, the standard input language, Narsese, poses a usability barrier: its dense symbolic…