Related papers: HDDL -- A Language to Describe Hierarchical Planni…
PDDL was originally conceived and constructed as a lingua franca for the International Planning Competition. PDDL2.1 embodies a set of extensions intended to support the expression of something closer to real planning problems. This…
Differentiable logics (DL) have recently been proposed as a method of training neural networks to satisfy logical specifications. A DL consists of a syntax in which specifications are stated and an interpretation function that translates…
Hoist scheduling has become a bottleneck in electroplating industry applications with the development of autonomous devices. Although there are a few approaches proposed to target at the challenging problem, they generally cannot scale to…
While systems designed for solving planning tasks vastly outperform Large Language Models (LLMs) in this domain, they usually discard the rich semantic information embedded within task descriptions. In contrast, LLMs possess parametrised…
Several solutions for specifying normative artefacts (norms, contracts, policies) in a computational processable way have been presented in the literature. Legal core ontologies have been proposed to systematize concepts and relationships…
Large language models are increasingly used within larger systems ("LLM agents"). These make a sequence of LLM calls, each call providing the LLM with a combination of instructions, observations, and interaction history. The design of the…
I comment on the PDDL 2.1 language and its use in the planning competition, focusing on the choices made for accommodating time and concurrency. I also discuss some methodological issues that have to do with the move toward more expressive…
On the one hand, ACME is a language designed in the late 90s as an interchange format for software architectures. The need for recon guration at runtime has led to extend the language with speci c support in Plastik. On the other hand, PDDL…
Epistemic Planning (EP) refers to an automated planning setting where the agent reasons in the space of knowledge states and tries to find a plan to reach a desirable state from the current state. Its general form, the Multi-agent Epistemic…
This document discusses the definition of the Parameter Description Language (PDL). In this language parameters are described in a rigorous data model. With no loss of generality, we will represent this data model using XML. It intends to…
Classical planners are powerful systems, but modeling tasks in input formats such as PDDL is tedious and error-prone. In contrast, planning with Large Language Models (LLMs) allows for almost any input text, but offers no guarantees on plan…
A tactical military unit is a complex system composed of many agents such as infantry, robots, or drones. Given a mission, an automated planner can find an optimal plan. Therefore, the mission itself must be modeled. The problem is that…
Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach…
The planning ability of Large Language Models (LLMs) has garnered increasing attention in recent years due to their remarkable capacity for multi-step reasoning and their ability to generalize across a wide range of domains. While some…
PDDL+ is an extension of PDDL that enables modelling planning domains with mixed discrete-continuous dynamics. In this paper we present a new approach to PDDL+ planning based on Constraint Answer Set Programming (CASP), i.e. ASP rules plus…
Recently, deep learning models have increasingly been used in cognitive modelling of language. This study asks whether deep learning can help us to better understand the learning problem that needs to be solved by speakers, above and beyond…
In this commentary I argue that although PDDL is a very useful standard for the planning competition, its design does not properly consider the issue of domain modeling. Hence, I would not advocate its use in specifying planning domains…
Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers…
Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended…
Federations of RDF data sources provide great potential when queried for answers and insights that cannot be obtained from one data source alone. A challenge for planning the execution of queries over such a federation is that the…