Optimizing black-box functions is a fundamental problem in science and engineering. To solve this problem, many approaches learn a surrogate function that estimates the underlying objective from limited historical evaluations. Large Language Models (LLMs), with their strong pattern-matching capabilities via pretraining on vast amounts of data, stand out as a potential candidate for surrogate modeling. However, directly prompting a pretrained language model to produce predictions is not feasible in many scientific domains due to the scarcity of domain-specific data in the pretraining corpora and the challenges of articulating complex problems in natural language. In this work, we introduce LICO, a general-purpose model that extends arbitrary base LLMs for black-box optimization, with a particular application to the molecular domain. To achieve this, we equip the language model with a separate embedding layer and prediction layer, and train the model to perform in-context predictions on a diverse set of functions defined over the domain. Once trained, LICO can generalize to unseen molecule properties simply via in-context prompting. LICO achieves state-of-the-art performance on PMO, a challenging molecular optimization benchmark comprising over 20 objective functions.

A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack of generality across multiple tasks and the need for a large amount of training data. The leading cause is that it cannot effectively integrate prior information into the perception-action cycle when devising the policy. Large language models (LLMs) emerged as a fundamental way to incorporate cross-domain knowledge into AI agents but lack crucial learning and adaptation toward specific decision problems. This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies. Our methodology is motivated by the modularity found in the human brain. The framework utilises the construction of intrinsic and extrinsic functions to add previous understandings of reasoning structures. It also provides the adaptive ability to learn models inside every module or function, consistent with the modular structure of cognitive processes. We describe the framework in-depth and compare it with other AI pipelines and existing frameworks. The paper explores practical applications, covering experiments that show the effectiveness of our method. Our results indicate that AI agents perform and adapt far better when organised reasoning and prior knowledge are embedded. This opens the door to more resilient and general AI agent systems.

Today AWS Step Functions expands the number of supported AWS services from 17 to over 200 and AWS API Actions from 46 to over 9,000 with its new capability AWS SDK Service Integrations. When developers build distributed architectures, one of the patterns they use is the workflow-based orchestration pattern. This pattern is helpful for workflow automation inside a service to perform distributed transactions. An example of a distributed transaction is all the tasks required to handle an order and keep track of the transaction status at all times. Step Functions is a low-code visual workflow service used for workflow automation, to orchestrate services, and help you to apply this pattern.

It first reviews the core issues in experiencebased design, for example, (1) the content of a design experience (or case), (2) the internal organization of design cases, (3) the language for indexing the cases, (4) the mechanism for retrieving a case relevant to a given design task, (5) the mechanism for adapting a retrieved design to satisfy the constraints of the design task, (6) the mechanism for evaluating a design against the specification of the design task, (7) the mechanism for redesigning a failed design, (8) the mechanism for acquiring new design knowledge, (9) the mechanism for chunking information about a design into a new case, and (10) the mechanism for storing a new case in memory for potential reuse in the future. It then proposes that decisions about these issues might lie in the designer's comprehension of the designs of artifacts he/she has encountered in the past, that is, in his/her mental models of how the designs achieve the functions and satisfy the constraints of the artifacts. To elaborate and evaluate this proposal, the dissertation analyzes the design of physical devices such as simple electric circuits, heat exchangers, and angular momentum controllers. It develops a theory of designers' comprehension of device designs in terms of functional models of how devices work. The functional model of a device provides a causal explanation of how the structure of the device produces its functions.