Papers for
team managers
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Optimizing social influence to improve collective judgment accuracy
Susceptibility optimization for wisdom of crowds: A social power reformulation and realization framework
Abstract: Whether social influence makes a crowd wiser or more biased hinges on who yields to others and who holds firm. Such heterogeneous susceptibilities to social influence, together with the influence network, determine the weight each agent's initial estimate carries in the collective estimate, known as social power. This paper studies susceptibility optimization for maximizing the wisdom of crowds under the Friedkin-Johnsen model. Minimizing the squared collective bias over susceptibilities leads to a nonconvex problem. To overcome this nonconvexity, we develop a social power reformulation and realization framework, which decomposes the problem into two stages: first characterizing the social power that minimizes the collective bias, then determining the susceptibilities that induce such social power. Social power reformulation yields a quadratic program over the probability simplex. Under uniform-sign biases, the optimal social power concentrates on the least biased agents and immediately determines the optimal susceptibilities; under mixed-sign biases, its geometry enables a linear-time construction algorithm. For social power realization, we introduce the notions of susceptibility realizability and establish necessary and sufficient conditions for them, under which we derive all optimal susceptibilities in closed form using the Laplacian pseudoinverse and eigenvector centrality. These results yield a unified algorithm that solves the original problem globally, with worst-case complexity cubic in the number of agents when realizability holds. Finally, we develop a fully distributed implementation with linear communication complexity, illustrating how collective intelligence can emerge from local interactions.
Solitary movement style predicts group foraging success but not leadership choices
Solitary movement style predicts collective foraging while whom to follow emerges only in company
Abstract: How far can behaviour inside a group, and the group's performance, be predicted from members measured while alone? We tested this on three public datasets of human collective foraging (621, 128 and 1,133 participants). A low-dimensional individual representation estimated from private-phase movement was mapped onto behaviour inside the group through a mapping learned on other participants. Private information processing was stable between the two halves of a session (split-half reliability, the correlation between the halves, 0.60--0.83) and predicted behaviour inside the group with correlations of 0.30--0.66. Selective social learning, following those who have succeeded or stopped, showed stable individual differences inside the group (reliability 0.45--0.59) yet was not predicted at all from the same person's private behaviour. Group performance was predicted with a correlation of 0.55 in all three datasets by simulations never fitted to group outcomes or by the mean of individually measured performance, a prediction carried by mobility and individual performance rather than by social weights. We found no credible evidence for an effect of how members were combined (equivalence bound 0.06). Whom to follow thus emerges only in company, which delimits what solitary measurements can predict and compose.
AI agent networks measured for group agreement and decision accuracy
Measuring Consensus in AI Agent Networks
Abstract: As AI agents become increasingly connected through networks and take on tasks that require negotiation and joint decision-making, a systematic approach is needed to assess how their views converge and what information supports their decisions. We present an evaluation framework that treats consensus formation as the evolution of publicly stated positions toward a shared region, using accumulated communication history as context. The framework tracks position trajectories, group dispersion, and information expressed in public messages. Two case studies examine staffing decisions based on distributed facts and decisions requiring agents to reconcile duplicate information and a cancelled contract. Results from 1,872 completed runs associate sharing explanations with more accurate group decisions, while the second task reveals persistent disagreement despite accurate aggregate answers. Membership-change experiments provide a complementary evaluation. By separating convergence among agents from progress toward a task's full-information answer, the framework relates decision accuracy and bounded disagreement to the information available during the exchange.
Personality mix shapes social network polarization and collective smarts
Diverse Minds, Divided Networks? Personality Composition, Polarization, and Collective Intelligence in LLM-Based Social Simulations
Abstract: Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two are rarely measured in the same system. It is therefore difficult to say whether a society's personality composition shapes both, or whether reducing polarization costs collective competence. We present TraitMix, an experimental design in which the Big Five composition of a simulated social network, both trait levels and trait heterogeneity, is a controlled experimental variable, and in which polarization and collective performance are measured in the same runs. Across 991 simulations of hundred-agent societies, spanning six contested topics and six language models, trait heterogeneity has the largest measured effects, acting in opposite directions on two faces of polarization: varied societies hold more dispersed opinions while being less segregated into camps, so homogeneous societies are not moderate but consensual echo chambers. Trait effects are not additive, as Agreeableness determines the sign of Openness, an interaction that replicates across models although the primary model's estimate is influence-driven. Contrary to the trade-off the study was designed to measure, no polarization measure predicts poorer collective performance, and cross-cutting interaction is the only one of four whose association with collective accuracy survives partialling on the aggregation identity. We report ablations removing two potential measurement circularities, an induction gate applied to every model, and the measures that failed them.