We present our work on a new modal logic of optimality, OPT, whose semantics are modeled in terms of optimal paths through reward-weighted transition systems. We prove some basic properties of OPT, including its status as a normal modal logic, as well as its relation to some of the standard modal axioms. We end with a discussion of applications to AI and future research directions and extensions.

The creation of planning models, and in particular domain models, is among the last bastions of tasks that require exten- sive manual labor in AI planning; it is desirable to simplify this process for the sake of making planning more accessi- ble. To this end, we investigate whether large language mod- els (LLMs) can be used to generate planning domain models from textual descriptions. We propose a novel task for this as well as a means of automated evaluation for generated do- mains by comparing the sets of plans for domain instances. Finally, we perform an empirical analysis of 7 large language models, including coding and chat models across 9 different planning domains. Our results show that LLMs, particularly larger ones, exhibit some level of proficiency in generating correct planning domains from natural language descriptions

Developing domain models is one of the few remaining places that require manual human labor in AI planning. Thus, in order to make planning more accessible, it is desirable to automate the process of domain model generation. To this end, we investigate if large language models (LLMs) can be used to generate planning domain models from simple textual descriptions. Specifically, we introduce a framework for automated evaluation of LLM-generated domains by comparing the sets of plans for domain instances. Finally, we perform an empirical analysis of 7 large language models, including coding and chat models across 9 different planning domains, and under three classes of natural language domain descriptions. Our results indicate that LLMs, particularly those with high parameter counts, exhibit a moderate level of proficiency in generating correct planning domains from natural language descriptions. Our code is available at https://github.com/IBM/NL2PDDL.

DNA-stabilized silver nanoclusters (AgN-DNAs) are a class of nanomaterials comprised of 10-30 silver atoms held together by short synthetic DNA template strands. AgN-DNAs are promising biosensors and fluorophores due to their small sizes, natural compatibility with DNA, and bright fluorescence---the property of absorbing light and re-emitting light of a different color. The sequence of the DNA template acts as a "genome" for AgN-DNAs, tuning the size of the encapsulated silver nanocluster, and thus its fluorescence color. However, current understanding of the AgN-DNA genome is still limited. Only a minority of DNA sequences produce highly fluorescent AgN-DNAs, and the bulky DNA strands and complex DNA-silver interactions make it challenging to use first principles chemical calculations to understand and design AgN-DNAs. Thus, a major challenge for researchers studying these nanomaterials is to develop methods to employ observational data about studied AgN-DNAs to design new nanoclusters for targeted applications.