We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log score, and compositions are defined through weighted logarithmic pooling that strictly improves every member's welfare. We prove that strict unanimity is impossible under linear pooling or in binary outcome spaces, but possible with three or more outcomes. Our framework admits recursive structure via cloning invariance, continuity, and openness, while tilt-based analysis rules out trivial duplication. Finally, we formalize an agentic alignment phenomenon in LLMs using our theory: eliciting a benevolent persona ("Luigi'") induces an antagonistic counterpart ("Waluigi"), while a manifest-then-suppress Waluigi strategy yields strictly larger first-order misalignment reduction than pure Luigi reinforcement alone. These results clarify how developing a principled mathematical framework for how subagents can coalesce into coherent higher-level entities provides novel implications for alignment in agentic AI systems.

In machine learning ensembles predictions from multiple models are aggregated. Despite widespread use and strong performance of ensembles in applied problems little is known about the mathematical properties of aggregating models and associated consequences for safe, explainable use of such models. In this paper we prove a theorem that shows that any ensemble will exhibit at least one of the following forms of prediction instability. It will either ignore agreement among all underlying models, change its mind when none of the underlying models have done so, or be manipulable through inclusion or exclusion of options it would never actually predict. As a consequence, ensemble aggregation procedures will always need to balance the benefits of information use against the risk of these prediction instabilities. This analysis also sheds light on what specific forms of prediction instability to expect from particular ensemble algorithms; for example popular tree ensembles like random forest, or xgboost will violate basic, intuitive monotonicity and fairness properties.

In this paper we propose a new model to represent human debates and methods to obtain collective conclusions from them. This model overcomes two drawbacks of existing approaches. First, our model does not assume that participants agree on the structure of the debate. It does this by allowing participants to express their opinion about all aspects of the debate. Second, our model does not assume that participants' opinions are rational, an assumption that significantly limits current approaches. Instead, we define a weaker notion of rationality that characterises coherent opinions, and we consider different scenarios based on the coherence of individual opinions and the level of consensus. We provide a formal analysis of different opinion aggregation functions that compute a collective decision based on the individual opinions and the debate structure. In particular, we demonstrate that aggregated opinions can be coherent even if there is a lack of consensus and individual opinions are not coherent. We conclude with an empirical evaluation demonstrating that collective opinions can be computed efficiently for real-sized debates.

Readers will delight in the gradual reveal of both the technology within the story and the dramatic history between many of those involved with the creation and evolution of that technology. Tom, a screenwriter, works with Harry, the genius inventor of the world's most popular AI (artificial intelligence) app, to create a simulation that will nudge people toward acting morally. This virtual world consists of multiple layers, each focusing on a different psychological alignment depending on the needs of the person using the program. A lower level, much like Hell, exposes people to horrors and cruelty, while some upper levels focus on order and happiness. The project becomes more complex when they upload the entire consciousness of people, creating virtual immortality.

We focus on a simple, one-dimensional collective decision problem (often referred to as the facility location problem) and explore issues of strategyproofness and proportional fairness. We present several characterization results for mechanisms that satisfy strategyproofness and varying levels of proportional fairness. We also characterize one of the mechanisms as the unique equilibrium outcome for any mechanism that satisfies natural fairness and monotonicity properties. Finally, we identify strategyproof and proportionally fair mechanisms that provide the best welfare-optimal approximation among all mechanisms that satisfy the corresponding fairness axiom.

Inspired by e-participation systems, in this paper we propose a new model to represent human debates and methods to obtain collective conclusions from them. This model overcomes drawbacks of existing approaches by allowing users to introduce new pieces of information into the discussion, to relate them to existing pieces, and also to express their opinion on the pieces proposed by other users. In addition, our model does not assume that users' opinions are rational in order to extract information from it, an assumption that significantly limits current approaches. Instead, we define a weaker notion of rationality that characterises coherent opinions, and we consider different scenarios based on the coherence of individual opinions and the level of consensus that users have on the debate structure. Considering these two factors, we analyse the outcomes of different opinion aggregation functions that compute a collective decision based on the individual opinions and the debate structure. In particular, we demonstrate that aggregated opinions can be coherent even if there is a lack of consensus and individual opinions are not coherent. We conclude our analysis with a computational evaluation demonstrating that collective opinions can be computed efficiently for real-sized debates.

Approval ballot based committee formation is concerned with aggregating individual approvals of voters. Voters submit their approvals of candidates and these approvals are aggregated to arrive at the optimal committee of specified size. There are several aggregation techniques proposed in the literature and these techniques differ among themselves on the criterion function they optimize. Voters preferences for a candidate is based on his/her opinion on candidate suitability. We note that candidates have attributes that make him/her suitable or otherwise. Hence, it is relevant to approve attributes and select candidates who have the approved attributes. This paper addresses the committee selection problem when voters submit their approvals on attributes. Though attribute based preference is addressed in several contexts, committee selection problem with attribute approval has not been attempted earlier. We note that extending the theory of candidate approval to attribute approval in committee selection problem is not trivial. In this paper, we study different aspects of this problem and show that none of the existing aggregation rules satisfies Unanimity and Justified Representation when attribute based approvals are considered. We propose a new aggregation rule that satisfies both the above properties. We also present other analysis of committee selection problem with attribute approval.

We consider peer review in a conference setting where there is typically an overlap between the set of reviewers and the set of authors. This overlap can incentivize strategic reviews to influence the final ranking of one's own papers. In this work, we address this problem through the lens of social choice, and present a theoretical framework for strategyproof and efficient peer review. We first present and analyze an algorithm for reviewer-assignment and aggregation that guarantees strategyproofness and a natural efficiency property called unanimity, when the authorship graph satisfies a simple property. Our algorithm is based on the so-called partitioning method, and can be thought as a generalization of this method to conference peer review settings. We then empirically show that the requisite property on the authorship graph is indeed satisfied in the ICLR-17 submission data, and further demonstrate a simple trick to make the partitioning method more practically appealing for conference peer review. Finally, we complement our positive results with negative theoretical results where we prove that under various ways of strengthening the requirements, it is impossible for any algorithm to be strategyproof and efficient.

The literature on judgment aggregation is moving from studying impossibility results regarding aggregation rules towards studying specific judgment aggregation rules. Here we give a structured list of most rules that have been proposed and studied recently in the literature, together with various properties of such rules. We first focus on the majority-preservation property, which generalizes Condorcet-consistency, and identify which of the rules satisfy it. We study the inclusion relationships that hold between the rules. Finally, we consider two forms of unanimity, monotonicity, homogeneity, and reinforcement, and we identify which of the rules satisfy these properties.

Distance rationalizability is an intuitive paradigm for developing and studying voting rules: given a notion of consensus and a distance function on preference profiles, a rationalizable voting rule selects an alternative that is closest to being a consensus winner. Despite its appeal, distance rationalizability faces the challenge of connecting the chosen distance measure and consensus notion to an operational measure of social desirability. We tackle this issue via the decision-theoretic framework of dynamic social choice, in which a social choice Markov decision process (MDP) models the dynamics of voter preferences in response to winner selection. We show that, for a prominent class of distance functions, one can construct a social choice MDP, with natural preference dynamics and rewards, such that a voting rule is (votewise) rationalizable with respect to the unanimity consensus for a given distance function iff it is a (deterministic) optimal policy in the MDP. This provides an alternative rationale for distance rationalizability, demonstrating the equivalence of rationalizable voting rules in a static sense and winner selection to maximize societal utility in a dynamic process.