Large language models (LLMs) are increasingly being asked to make economically rational decisions and indeed are already being applied to economic tasks like stock picking and financial analysis. Existing LLM benchmarks tend to focus on specific applications, making them insufficient for characterizing economic reasoning more broadly. In previous work, we offered a blueprint for comprehensively benchmarking $\textit{strategic}$ decision-making Raman et al. 2024. However, this work did not engage with the even larger microeconomic literature on $\textit{non-strategic}$ settings. We address this gap here, taxonomizing microeconomic reasoning into $58$ distinct elements, each grounded in up to $10$ distinct domains, $5$ perspectives, and $3$ types. The generation of benchmark data across this combinatorial space is powered by a novel LLM-assisted data generation protocol that we dub auto-STEER, which generates a set of questions by adapting handwritten templates to target new domains and perspectives. By generating fresh questions for each element, auto-STEER induces diversity which could help to reduce the risk of data contamination. We use this benchmark to evaluate $27$ LLMs spanning a range of scales and adaptation strategies, comparing performance across multiple formats—multiple-choice and free-text question answering—and scoring schemes. Our results surface systematic limitations in current LLMs' ability to generalize economic reasoning across types, formats, and textual perturbations, and establish a foundation for evaluating and improving economic competence in foundation models.

Conspicuous consumption occurs when a consumer derives value from a good based on its social meaning as a signal of wealth, taste, and/or community affiliation. Common conspicuous goods include designer footwear, country club memberships, and artwork; conspicuous goods also exist in the digital sphere, with non-fungible tokens (NFTs) as a prominent example. The NFT market merits deeper study for two key reasons: first, it is poorly understood relative to its economic scale; and second, it is unusually amenable to analysis because NFT transactions are publicly available on the blockchain, making them useful as a test bed for conspicuous consumption dynamics. This paper introduces a model that incorporates two previously identified elements of conspicuous consumption: the bandwagon effect (goods increase in value as they become more popular) and the snob effect (goods increase in value as they become rarer). Our model resolves the apparent tension between these two effects, exhibiting net complementarity between others' and one's own conspicuous consumption. We also introduce a novel dataset combining NFT transactions with embeddings of the corresponding NFT images computed using an off-the-shelf vision transformer architecture. We use our dataset to validate the model, showing that the bandwagon effect raises an NFT collection's value as more consumers join, while the snob effect drives consumers to seek rarer NFTs within a given collection.

Mobile gaming is a rapidly growing and incredibly profitable sector; having grown seven-fold over the past 10 years, it now grosses over $100 billion annually. This growth was due in large part to a shift in monetization strategies: rather than charging players an upfront cost ("pay-to-play"), games often request optional microtransactions throughout gameplay ("free-to-play"). We focus on a common scenario in which games include wait times---gating either items or game progression---that players can pay to skip. Game designers typically say that they optimize for player happiness rather than revenue; however, prices for skips are typically set at levels that few players are willing to pay, leading to low purchase rates. Under a traditional analysis, it would seem that game designers fail at their stated goal if few players buy what they are selling. We argue that an alternate model can better explain this dynamic: players value tasks more highly as they are perceived to be more difficult. While skips can increase players' utilities by providing instant gratification, pricing skips too cheaply can lower players' utilities by decreasing the perceived amount of work needed to complete a task. We show that high revenue, high player utility, and low purchase rates can all coexist under this model, particularly under a realistic distribution of players having few buyers but a few big-spending "whales." We also investigate how a game designer should optimize prices under our model. An appendix of the paper with proofs, more comprehensive results and visualizations can be found at https://arxiv.org/abs/2312.10205.

There is increasing interest in using LLMs as decision-making "agents". Doing so includes many degrees of freedom: which model should be used; how should it be prompted; should it be asked to introspect, conduct chain-of-thought reasoning, etc? Settling these questions---and more broadly, determining whether an LLM agent is reliable enough to be trusted---requires a methodology for assessing such an agent's economic rationality. In this paper, we provide one. We begin by surveying the economic literature on rational decision making, taxonomizing a large set of fine-grained "elements" that an agent should exhibit, along with dependencies between them. We then propose a benchmark distribution that quantitatively scores an LLMs performance on these elements and, combined with a user-provided rubric, produces a "rationality report card". Finally, we describe the results of a large-scale empirical experiment with 14 different LLMs, characterizing the both current state of the art and the impact of different model sizes on models' ability to exhibit rational behavior.

In 2015 Schiefer and Winfree introduced the chemical reaction network-controlled tile assembly model (CRN-TAM), a variant of the abstract tile assembly model (aTAM), where tile reactions are mediated via non-local chemical signals. In this paper, we introduce ALCH, an imperative programming language for specifying CRN-TAM programs. ALCH contains common features like Boolean variables, conditionals, and loops. It also supports CRN-TAM-specific features such as adding and removing tiles. A unique feature of the language is the branch statement, a nondeterministic control structure that allows us to query the current state of tile assemblies. We also developed a compiler that translates ALCH to the CRN-TAM, and a simulator that simulates and visualizes the self-assembly of a CRN-TAM program. Using this language, we show that the discrete Sierpinski triangle can be strictly self-assembled in the CRN-TAM. This solves an open problem that the CRN-TAM is capable of self-assembling infinite shapes at scale one that the aTAM cannot. ALCH allows us to present this construction at a high level, abstracting species and reactions into C-like code that is simpler to understand. Our construction utilizes two new CRN-TAM techniques that allow us to tackle this open problem. First, it employs the branching feature of ALCH to probe the previously placed tiles of the assembly and detect the presence and absence of tiles. Second, it uses scaffolding tiles to precisely control tile placement by occluding any undesired binding sites.

We present a novel model for classifying the quality of Wikipedia articles based on structural properties of a network representation of the article's revision history. We create revision history networks (an adaptation of Keegan et. al's article trajectory networks [7]), where nodes correspond to individual editors of an article, and edges join the authors of consecutive revisions. Using descriptive statistics generated from these networks, along with general properties like the number of edits and article size, we predict which of six quality classes (Start, Stub, C-Class, B-Class, Good, Featured) articles belong to, attaining a classification accuracy of 49.35% on a stratified sample of articles. These results suggest that structures of collaboration underlying the creation of articles, and not just the content of the article, should be considered for accurate quality classification.