Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs as a source of heuristic guidance for other agents (AI planners) in their planning tasks. We conduct a systematic study by generating a suite of instances on domains similar to the ones employed in the International Planning Competition and evaluate LLMs in two distinct modes: autonomous and heuristic. Our findings reveal that LLMs' ability to generate executable plans autonomously is rather limited, with the best model (GPT-4) having an average success rate of ~12% across the domains.

Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs as a source of heuristic guidance for other agents (AI planners) in their planning tasks. We conduct a systematic study by generating a suite of instances on domains similar to the ones employed in the International Planning Competition and evaluate LLMs in two distinct modes: autonomous and heuristic. Our findings reveal that LLMs' ability to generate executable plans autonomously is rather limited, with the best model (GPT-4) having an average success rate of 12% across the domains. In the heuristic mode, we demonstrate that LLM-generated plans can improve the search process for underlying sound planners and additionally show that external verifiers can help provide feedback on the generated plans and back-prompt the LLM for better plan generation.

Several recent works in scientific machine learning have revived interest in the application of neural networks to partial differential equations (PDEs). A popular approach is to aggregate the residual form of the governing PDE and its boundary conditions as soft penalties into a composite objective/loss function for training neural networks, which is commonly referred to as physics-informed neural networks (PINNs). In the present study, we visualize the loss landscapes and distributions of learned parameters and explain the ways this particular formulation of the objective function may hinder or even prevent convergence when dealing with challenging target solutions. We construct a purely data-driven loss function composed of both the boundary loss and the domain loss. Using this data-driven loss function and, separately, a physics-informed loss function, we then train two neural network models with the same architecture. We show that incomparable scales between boundary and domain loss terms are the culprit behind the poor performance. Additionally, we assess the performance of both approaches on two elliptic problems with increasingly complex target solutions. Based on our analysis of their loss landscapes and learned parameter distributions, we observe that a physics-informed neural network with a composite objective function formulation produces highly non-convex loss surfaces that are difficult to optimize and are more prone to the problem of vanishing gradients.

The MRes RCA programme provides early and mid-career art and design researchers with the intellectual, technical and professional tools with which to complete high-quality research projects. The programme is a uniquely interdisciplinary degree, and the first to be taught across all four Schools of the RCA. Over a full-time year it offers training in practice and theory-led research methods for critical studies in art and design. As demonstrated by the graduating students' work, MRes RCA supports students from diverse backgrounds. Students come from previous study both in art and design and in related disciplines such as history, political sciences and psychology, and with experience working in the creative industries, as practising architects, designers and artists.

Many recent papers address reading comprehension, where examples consist of (question, passage, answer) tuples. Presumably, a model must combine information from both questions and passages to predict corresponding answers. However, despite intense interest in the topic, with hundreds of published papers vying for leaderboard dominance, basic questions about the difficulty of many popular benchmarks remain unanswered. In this paper, we establish sensible baselines for the bAbI, SQuAD, CBT, CNN, and Who-did-What datasets, finding that question- and passage-only models often perform surprisingly well. On $14$ out of $20$ bAbI tasks, passage-only models achieve greater than $50\%$ accuracy, sometimes matching the full model. Interestingly, while CBT provides $20$-sentence stories only the last is needed for comparably accurate prediction. By comparison, SQuAD and CNN appear better-constructed.