Can AI agents make law? Evaluating AI legal relevance and creativity

Benjamin Ricaud; Artem Galushko

cs.AIOct 17, 2026

Can AI agents make law? Evaluating AI legal relevance and creativity

Authors: Benjamin Ricaud, Artem Galushko

Organizations: Department of Physics and Technology, UiT The Arctic University of Norway, Tromsø, Norway

Abstract

Large language models, the artificial intelligence (AI) systems behind modern chatbots, are trained on vast amounts of legal text, but can they build on it to write law for situations that text never anticipated? In this study, we analyse AI agents' ability to draft a hypothetical "Constitution" for a "community of AI agents". We design "constitutional assemblies" in which a single language model plays several characters that debate to produce a draft constitution. We find that the assemblies converge on a robust floor of legal provisions, and generate a wide variety of different proposals around it, including several AI-specific provisions with no equivalent in human law. Looking more closely at the "creativity" of these AI agents, we find different levels: most proposals combine existing concepts and themes from human constitutions with AI-specific vocabulary. We introduce a measure of this recombination, which helps identify and highlight the most novel legal material. This study reveals a ceiling on AI creativity: the agents extend familiar legal ideas to new situations, but they do not work through what those situations would change. Although current AI models can help develop new laws, they still depend on human legal reasoning.

LLM Agents

Large language model agents use language models to plan, use tools, and act across multi-step tasks and environments.

See all 705 papers

Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?
Sep 6, 2026Nirav Patel, Emily Wenger, Christopher BuccafuscoLLM Evaluation Demographic Bias in Language Models
Duke University, Departments of Computer Science & Electrical and Computer Engineering · Duke University Law School
Investigating Multi-Agent Deliberation in Law
Jun 29, 2026Cor Steging, Ludi van Leeuwen, Tadeusz ZbiegieńMulti-Agent Systems Multi-Agent Reasoning
Bernoulli Institute of Mathematics, Computer Science and Artificial Intelligence, University of Groningen The Netherlands · Department of Legal Theory, Jagiellonian University Poland
Commit or Abstain? System One Decision Models, LLMs, and Missing Legal Authority
Oct 21, 2026M. Mikail DemirLegal Citation Verification LLM Abstention
Department of Information Science, University at Albany, SUNY, USA

Sep 6, 2026J/K move · Enter open · S save

Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?

Nirav Patel, Emily Wenger, Christopher Buccafusco

Duke University, Departments of Computer Science & Electrical and Computer Engineering · Duke University Law School

LLM Evaluation Demographic Bias in Language Models Human-AI Decision Making

Open paper AskPDF arXiv

As people increasingly rely on artificial intelligence (AI) for guidance in their own lives, scholars, lawyers, and even judges have begun to consider the role of AI in legal decision-making. As "silicon sampling" -- the use of generative AI models in social science research -- is now impacting academia, "silicon jurors" could make an appearance in courtrooms. This study joins an emerging line of research on generative AI models' ability to simulate human legal judgments. In particular, we study how large language model (LLM)-powered chatbots respond to series of questions about legal reasonableness. When the law needs to judge the appropriateness of a behavior, it most often asks whether the behavior was "reasonable." Yet despite the ubiquity of reasonableness judgments, they are the site of constant vexation for lawyers, judges, and lay people. Reasonableness seems inherently vague and unpredictable, since it relies on variable context and implicit conceptual schemas. Moreover, many scholars caution that reasonableness judgments may vary along demographic lines. We compare the answers of human participants to those of twenty-six LLMs across twenty-five different legally relevant reasonableness judgments. Overall, our findings suggest that chatbot responses generally track those of human participants. Nonetheless, we find some suggestive -- and potentially concerning -- results. Compared to humans, LLMs generate more homogeneous responses and occasionally treat a variable standard as an invariant rule. And, compared to humans, LLMs tend to generate answers that are more favorable to the government and to corporations. Finally, our results indicate that LLMs' responses tend to align more closely with those of respondents who are white, male, older, and more educated. More systematic research is needed to confirm or reject these initial findings.

Abstract

LLM Agents

Explore similar work

Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?

Investigating Multi-Agent Deliberation in Law

Commit or Abstain? System One Decision Models, LLMs, and Missing Legal Authority