Uri Wilensky

Can Gurkan, Forrest Stonedahl, Uri Wilensky

When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones? We study this question by analyzing LLM-driven mutation chains in the absence of selection pressure within a domain-specific language, varying prompt design, model family, and stochastic replication. We find that LLM-based mutation consistently converges toward restricted attractor regions in program space. Convergence is especially severe at the structural level: in 87% of chains, over 93% of mutations revisit a previously seen structural form, with most variation confined to terminal substitutions within recurring templates. Cycle analysis reveals short cycles and self-loops dominating the transition structure. The rate of convergence varies with prompt wording and model choice, but the phenomenon is robust across conditions. A classical GP subtree mutation operator does not exhibit comparable convergence, suggesting that the effect is intrinsic to the LLM mutation pipeline. These findings reveal a tension at the heart of LLM-driven program evolution: the same capabilities that enable semantics-aware program transformation also carry a systematic bias toward structural homogeneity that must be accounted for if such systems are to sustain open-ended exploration. Source code is available at https://github.com/can-gurkan/lmca.

John Chen, Uri Wilensky

Building on Papert (1980)'s idea of children talking to computers, we propose ChatLogo, a hybrid natural-programming language interface for agent-based modeling and programming. We build upon previous efforts to scaffold ABM & P learning and recent development in leveraging large language models (LLMs) to support the learning of computational programming. ChatLogo aims to support conversations with computers in a mix of natural and programming languages, provide a more user-friendly interface for novice learners, and keep the technical system from over-reliance on any single LLM. We introduced the main elements of our design: an intelligent command center, and a conversational interface to support creative expression. We discussed the presentation format and future work. Responding to the challenges of supporting open-ended constructionist learning of ABM & P and leveraging LLMs for educational purposes, we contribute to the field by proposing the first constructionist LLM-driven interface to support computational and complex systems thinking.

John Chen, Alexandros Lotsos, Sihan Cheng et al.

Qualitative analysis is critical to understanding human datasets in many social science disciplines. A central method in this process is inductive coding, where researchers identify and interpret codes directly from the datasets themselves. Yet, this exploratory approach poses challenges for meeting methodological expectations (such as ``depth'' and ``variation''), especially as researchers increasingly adopt Generative AI (GAI) for support. Ground-truth-based metrics are insufficient because they contradict the exploratory nature of inductive coding, while manual evaluation can be labor-intensive. This paper presents a theory-informed computational method for measuring inductive coding results from humans and GAI. Our method first merges individual codebooks using an LLM-enriched algorithm. It measures each coder's contribution against the merged result using four novel metrics: Coverage, Overlap, Novelty, and Divergence. Through two experiments on a human-coded online conversation dataset, we 1) reveal the merging algorithm's impact on metrics; 2) validate the metrics' stability and robustness across multiple runs and different LLMs; and 3) showcase the metrics' ability to diagnose coding issues, such as excessive or irrelevant (hallucinated) codes. Our work provides a reliable pathway for ensuring methodological rigor in human-AI qualitative analysis.

John Chen, Alexandros Lotsos, Lexie Zhao et al.

Inductive qualitative methods have been a mainstay of education research for decades, yet it takes much time and effort to conduct rigorously. Recent advances in artificial intelligence, particularly with generative AI (GAI), have led to initial success in generating inductive coding results. Like human coders, GAI tools rely on instructions to work, and how to instruct it may matter. To understand how ML/GAI approaches could contribute to qualitative coding processes, this study applied two known and two theory-informed novel approaches to an online community dataset and evaluated the resulting coding results. Our findings show significant discrepancies between ML/GAI approaches and demonstrate the advantage of our approaches, which introduce human coding processes into GAI prompts.

John Chen, Alexandros Lotsos, Grace Wang et al.

Open coding, a key inductive step in qualitative research, discovers and constructs concepts from human datasets. However, capturing extensive and nuanced aspects or "coding moments" can be challenging, especially with large discourse datasets. While some studies explore machine learning (ML)/Generative AI (GAI)'s potential for open coding, few evaluation studies exist. We compare open coding results by five recently published ML/GAI approaches and four human coders, using a dataset of online chat messages around a mobile learning software. Our systematic analysis reveals ML/GAI approaches' strengths and weaknesses, uncovering the complementary potential between humans and AI. Line-by-line AI approaches effectively identify content-based codes, while humans excel in interpreting conversational dynamics. We discussed how embedded analytical processes could shape the results of ML/GAI approaches. Instead of replacing humans in open coding, researchers should integrate AI with and according to their analytical processes, e.g., as parallel co-coders.

James T. Wilkinson, Jacob Kelter, John Chen et al.

We present a novel agent-based approach to simulating an over-the-counter (OTC) financial market in which trades are intermediated solely by market makers and agent visibility is constrained to a network topology. Dynamics, such as changes in price, result from agent-level interactions that ubiquitously occur via market maker agents acting as liquidity providers. Two additional agents are considered: trend investors use a deep convolutional neural network paired with a deep Q-learning framework to inform trading decisions by analysing price history; and value investors use a static price-target to determine their trade directions and sizes. We demonstrate that our novel inclusion of a network topology with market makers facilitates explorations into various market structures. First, we present the model and an overview of its mechanics. Second, we validate our findings via comparison to the real-world: we demonstrate a fat-tailed distribution of price changes, auto-correlated volatility, a skew negatively correlated to market maker positioning, predictable price-history patterns and more. Finally, we demonstrate that our network-based model can lend insights into the effect of market-structure on price-action. For example, we show that markets with sparsely connected intermediaries can have a critical point of fragmentation, beyond which the market forms distinct clusters and arbitrage becomes rapidly possible between the prices of different market makers. A discussion is provided on future work that would be beneficial.

Bryan Head, Uri Wilensky

We present a method of endowing agents in an agent-based model (ABM) with sophisticated cognitive capabilities and a naturally tunable level of intelligence. Often, ABMs use random behavior or greedy algorithms for maximizing objectives (such as a predator always chasing after the closest prey). However, random behavior is too simplistic in many circumstances and greedy algorithms, as well as classic AI planning techniques, can be brittle in the context of the unpredictable and emergent situations in which agents may find themselves. Our method, called agent-centric Monte Carlo cognition (ACMCC), centers around using a separate agent-based model to represent the agents' cognition. This model is then used by the agents in the primary model to predict the outcomes of their actions, and thus guide their behavior. To that end, we have implemented our method in the NetLogo agent-based modeling platform, using the recently released LevelSpace extension, which we developed to allow NetLogo models to interact with other NetLogo models. As an illustrative example, we extend the Wolf Sheep Predation model (included with NetLogo) by using ACMCC to guide animal behavior, and analyze the impact on agent performance and model dynamics. We find that ACMCC provides a reliable and understandable method of controlling agent intelligence, and has a large impact on agent performance and model dynamics even at low settings.