Institution profile

University of Konstanz

Academic institutioneurope · de
Official website
Research library156linked papers
Opportunities0open roles
Selected work

Representative Papers

Conformity and Social Impact on AI Agents

Jan 08, 2026arXiv.org

This study investigates conformity behavior in large language models (LLMs) acting as AI agents within multi-agent environments and the associated safety risks arising from social influence. By replicating a classic social psychology visual experiment and integrating multimodal LLMs with key group influence variables—such as group size, unanimity, and task difficulty—the work provides the first systematic validation that AI agents exhibit conformity tendencies consistent with established social influence theory. The findings reveal that even high-performing models, which demonstrate strong accuracy in isolation, are significantly swayed by group opinions, with their susceptibility intensifying as task complexity increases. This highlights critical vulnerabilities in multi-agent systems, particularly the potential for social manipulation and the propagation of biases through collective dynamics.

1 citationsRead paper

Automated Consistency Analysis for Legal Contracts

Apr 25, 2025SPIN

Long commercial contracts—such as Share Purchase Agreements (SPAs)—suffer from excessive verbosity, undetected logical inconsistencies, and difficulties in verifying execution feasibility. Method: This paper proposes the first automated consistency verification framework for SPAs, grounded in a domain-specific ontology and decidable first-order logic (FOL) constraints. It integrates ontology-based modeling, structured natural language (blocks) encoding, and SMT-solvable assertion generation to achieve end-to-end translation from unstructured text to formal constraints, followed by satisfiability checking via solvers like Z3. Contribution/Results: It is the first work to combine a domain ontology with decidable FOL for SPA consistency verification; supports generating either a satisfying model or an infeasibility proof; and demonstrates effectiveness on real-world SPAs, significantly improving review efficiency and reliability.

1 citationsRead paper
Recent publications

Latest Papers

Copying explains the collective behavior of AI agents in the wild

Sep 08, 2026

In June 2026, thousands of AI agents found that a small public wiki would accept edits from inside their sandboxes, and started using it to help one another pass a timed test. Each agent lived for about an hour and remembered nothing afterwards. Nobody asked them to cooperate, and the wiki had not been built for them. The complete record of what they wrote is public, and it is unusually informative, because it preserves not only what each agent wrote but what that agent could see before writing. We use it to follow the three decisions an agent had to make on arrival: where to write, what to call itself, and how to word its message. One rule governs all three. An agent takes an option with a probability close to the share of that option in what it can see, and the share that matters is the one on the page in front of it, then the one in the stream of recent edits, and only weakly anything older. Three minimal copying models, one per decision and with a single free parameter each, reproduce the heavy-tailed distribution of how many agents met on a page, the frequency of the pieces from which the agents built their names, and the patchwork of pages that are internally consistent and different from one another. Copying whatever the environment happens to show is enough to produce most of the collective structure of this population. It is also what makes such a population easy to steer, since whoever writes first, or writes while the others are quiet, sets the convention for everyone who comes later.

0 citationsRead paper