There is an increasing body of work using Large Language Models (LLMs) as agents for orchestrating workflows and making decisions in domains that require planning and multi-step reasoning. As a result, it is imperative to evaluate LLMs on core skills required for planning. In this work, we present ACPBench, a benchmark for evaluating the reasoning tasks in the field of planning. The benchmark consists of 7 reasoning tasks over 13 planning domains. The collection is constructed from planning domains described in a formal language. This allows us to synthesize problems with provably correct solutions across many tasks and domains. Further, it allows us the luxury of scale without additional human effort, i.e., many additional problems can be created automatically. Our extensive evaluation of 22 LLMs and OpenAI o1 reasoning models highlights the significant gap in the reasoning capability of the LLMs. Our findings with OpenAI o1, a multi-turn reasoning model, reveal significant gains in performance on multiple-choice questions, yet surprisingly, no notable progress is made on boolean questions. The ACPBench collection is available at https://ibm.github.io/ACPBench.

One person has been killed and others wounded in a Ukrainian drone attack on a ferry at port in southern Russia, the regional governor has said. Krasnodar governor Veniamin Kondratyev said the ferry had caught fire at Port Kavkaz but there was no risk of it spreading. The port lies a few kilometres from the Kerch bridge, which enables road and rail travel between Russia and the Crimean peninsula, which Russia illegally annexed in 2014. "Unfortunately there are injured and dead among the crew and port staff," Mr Kondratyev said. He added that emergency services were on the scene.

Planning is a fundamental task in artificial intelligence that involves finding a sequence of actions that achieve a specified goal in a given environment. Large language models (LLMs) are increasingly employed in applications that require such planning capabilities, including web and embodied agents. In line with recent studies, we demonstrate through experimentation that LLMs lack necessary skills required for planning. We focus on their ability to function as world models, and show that they struggle to simulate the complex dynamics of classic planning domains. Based on these observations, we advocate for the potential of a hybrid approach that combines language models with classical planning methodology. We introduce SimP lan, a novel hybrid architecture, utilizing external world modeling tools and the greedy best-first search algorithm. We assess its effectiveness in a rigorous set of experiments across a variety of challenging planning domains. Our results demonstrate that SimP lan significantly outperforms existing LLM-based planners, highlighting the critical role of search strategies and world models in planning applications.

The maritime industry's continuous commitment to sustainability has led to a dedicated exploration of methods to reduce vessel fuel consumption. This paper undertakes this challenge through a machine learning approach, leveraging a real-world dataset spanning two years of a ferry in west coast Canada. Our focus centers on the creation of a time series forecasting model given the dynamic and static states, actions, and disturbances. This model is designed to predict dynamic states based on the actions provided, subsequently serving as an evaluative tool to assess the proficiency of the ferry's operation under the captain's guidance. Additionally, it lays the foundation for future optimization algorithms, providing valuable feedback on decision-making processes. To facilitate future studies, our code is available at \url{https://github.com/pagand/model_optimze_vessel/tree/AAAI}

This paper provides a collision avoidance perspective to maritime autonomy, in the shift towards Maritime Autonomous Surface Ships (MASS). In particular, the paper presents the developments related to the Greenhopper, Denmark's first autonomous harbour bus. The collision and grounding avoidance scheme, called the Short Horizon Planner (SHP), is described and discussed in detail. Furthermore, the required autonomy stack for facilitating safe and rule-compliant collision avoidance is presented. The inherent difficulties related to adhering to the COLREGs are outlined, highlighting some of the operational constraints and challenges within the space of autonomous ferries and harbour buses. Finally, collision and grounding avoidance is demonstrated using a simulation of the whole Greenhopper autonomy stack.

Pro-Kremlin officials were pulling out of the key southern Ukraine city of Kherson on Wednesday, as Kyiv's forces advanced on territory in Russian hands since the war's earliest days. Kherson was the first major city to fall to Moscow's troops after the February invasion and retaking it would be a major prize in Ukraine's ongoing counter-offensive. Kyiv's recapturing of swathes of its territory in the east and parts of the south has however been followed by punishing missile and drone strikes that have demolished large parts of Ukraine's power grid ahead of winter. "The entire administration is already moving today," to the left bank of the Dnieper river, the region's Moscow-installed head Vladimir Saldo, said on Russian state television. The city is located on the western bank of the Dnieper, the same side where Ukrainian troops have been moving forward in a counter-offensive that began in August.

Autonomous vessel software and systems provider Sea Machines Robotics today closed a $15 million funding round to accelerate deployment of its technologies in the unmanned naval boat and ship market. Sea Machines boldly claims this is one of the largest rounds for a tech company tackling marine and maritime use cases. Self-steering vessels aren't a new idea -- but they are gaining steam. Earlier this year, IBM and Promare -- a U.K.-based marine research and exploration charity -- trialed a prototype of an AI-powered maritime navigation system ahead of a September 6th venture to send a ship across the Atlantic Ocean. In Norway, a crewless cargo ship called the Yara Birkeland is expected to go into commercial operation later in 2020.

Autonomous vessel software and systems provider Sea Machines Robotics today closed a $15 million funding round to accelerate deployment of its technologies in the unmanned naval boat and ship market. Sea Machines boldly claims this is one of the largest rounds for a tech company tackling marine and maritime use cases. Self-steering vessels aren't a new idea -- but they are gaining steam. Earlier this year, IBM and Promare -- a U.K.-based marine research and exploration charity -- trialed a prototype of an AI-powered maritime navigation system ahead of a September 6th venture to send a ship across the Atlantic Ocean. In Norway, a crewless cargo ship called the Yara Birkeland is expected to go into commercial operation later in 2020.

Mutual exclusion (mutex) can be traced back to concurrency control, which refers to the condition that prevents simultaneous accesses to a shared resource. In knowledge representation, they specify the constraints that some properties cannot hold at the same time. For example, an object cannot be at different locations at the same time. These constraints frequently occur in applications from model-checking problems in computer-aided verification [2], computer vision [12, 17], graph algorithms [11], and AI planning [14]. The goal of this paper is to develop a graph-theoretic technique for compactly encoding large sets of mutex constraints and apply it to planning in ASP . We do his by focusing on domain-independent AI planning as started out by SA TPlan [10]. That is, we will first obtain an ASP planner by a straightforward translation from SA TPlan and then study how to encode mutex constraints compactly for the planner. In SA T/ASP planning, mutex constraints are specified by formulas/rules that, for any state (which involves a time step, also called a layer in this paper), the actions with conflicting preconditions or effects, and the fluents that are inferred to be conflicting, are mutually exclusive. A naive encoding of these constraints can certainly generate enough rules to overwhelm the underlying solver for large planning instances.

Paval Botica, chief officer on CMA CGM's Benjamin Franklin container ship, checks a monitor off Guangzhou, China, in 2016. The startup Shone is outfitting CMA CGM ships with situational awareness systems, a first step toward autonomous operation. The next time you hop on a ferry, take a look at the captain's bridge. There may not be a human at the helm much longer. Ships around the world are beginning a transformation into autonomous machines, leveraging the same advances in artificial intelligence that are shaking up the automotive world.