Generalizing the Turing Test to Interactive Agents

arXiv:2605.10851v2 Announce Type: replace Abstract: We initiate the study of the Generalized Turing Test (GTT), a formal generalization of Turing's imitation game from humans to arbitrary interactive agents. For agents $A$ and $B$, $A$ passes the GTT against $B$ if an instance of $B$, acting as a distinguisher, cannot reliably distinguish an $A$ instructed to imitate $B$ from another instance of $B$; if so, we write $A \geq B$. We study the theoretical and empirical consequences of this idea. On the theory side, we prove sufficient conditions under which this "Turing Comparator" is transitive. We introduce natural variants with querying (the imitator can first interact with a specimen of the target), a Universal Turing Test with arbitrary distinguishers and targets, and complexity-theoretic variants that control interaction length. As a proof of concept, we evaluate the GTT and its variants across nine large language models. Remarkably, Turing Scores recover a clear model stratification consistent with standard external benchmarks despite being derived entirely from pairwise imitation games. Transcript analysis reveals that models use both stylistic signatures and substantive STEM and logic-based probes. Together, these results suggest indistinguishability could provide a meaningful signal for comparing agents, yielding an inherently adaptive form of evaluation that does not rely on fixed benchmarks.

Abstract:We initiate the study of the Generalized Turing Test (GTT), a formal generalization of Turing's imitation game from humans to arbitrary interactive agents. For agents $A$ and $B$, $A$ passes the GTT against $B$ if an instance of $B$, acting as a distinguisher, cannot reliably distinguish an $A$ instructed to imitate $B$ from another instance of $B$; if so, we write $A \geq B$. We study the theoretical and empirical consequences of this idea. On the theory side, we prove sufficient conditions under which this "Turing Comparator" is transitive. We introduce natural variants with querying (the imitator can first interact with a specimen of the target), a Universal Turing Test with arbitrary distinguishers and targets, and complexity-theoretic variants that control interaction length. As a proof of concept, we evaluate the GTT and its variants across nine large language models. Remarkably, Turing Scores recover a clear model stratification consistent with standard external benchmarks despite being derived entirely from pairwise imitation games. Transcript analysis reveals that models use both stylistic signatures and substantive STEM and logic-based probes. Together, these results suggest indistinguishability could provide a meaningful signal for comparing agents, yielding an inherently adaptive form of evaluation that does not rely on fixed benchmarks.

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)

arXiv:2605.10851 [cs.AI]

(or arXiv:2605.10851v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.10851 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

Generalizing the Turing Test to Interactive Agents

Subiecte conexe