Hiroki Sayama

Cecil Pang, Hiroki Sayama

Modern business environments demand continuous reconfiguration of cross-functional processes, yet most enterprise systems remain organized around siloed departments, rigid workflows, and hard-coded automation. Meanwhile, large language models (LLMs) demonstrate strong capabilities in interpreting natural language and synthesizing unstructured information, but they lack deterministic, auditable execution of complex business logic. We introduce Autonomous Business System (AUTOBUS), a system that integrates LLM-based AI agents, predicate-logic programming, and business-semantics-centric enterprise data into a unified neuro-symbolic architecture for executing end-to-end business initiatives. AUTOBUS models a business initiative as a network of interrelated tasks with explicit pre- and post-conditions, required data, evaluation rules, and API-level actions. Enterprise data is organized as a knowledge graph, whose entities, relationships, and constraints are translated into logic facts and foundational rules that ground reasoning and ensure semantic consistency. Core AI agents synthesize task instructions, enterprise semantics, and available tools into task-specific logic programs, which are executed by a logic engine that enforces constraints, coordinates auxiliary tools, and produces deterministic outcomes. Humans specify task instructions, define and maintain business semantics and policies, curate tools, and supervise high-impact or ambiguous decisions, ensuring accountability and adaptability. We detail the AUTOBUS architecture, the structure of AI-generated logic programs, and the human-AI collaboration model and present a case study that demonstrates accelerated time to market in a data-rich organization. A reference implementation of the case study is available at https://github.com/cecilpang/autobus-paper.

Hiroki Sayama, Junichi Yamanoi

Organizational structure of corporations has potential to provide implications for dynamics and performance of corporate operations. However, this subject has remained unexplored because of the lack of readily available organization network datasets. To overcome the this gap, we developed a new heuristic image-processing method to extract and reconstruct organization network data from published organization charts. Our method analyzes a PDF file of a corporate organization chart and detects text labels, boxes, connecting lines, and other objects through multiple steps of heuristically implemented image processing. The detected components are reorganized together into a Python's NetworkX Graph object for visualization, validation and further network analysis. We applied the developed method to the organization charts of all the listed firms in Japan shown in the ``Organization Chart/System Diagram Handbook'' published by Diamond, Inc., from 2008 to 2011. Out of the 10,008 organization chart PDF files, our method was able to reconstruct 4,606 organization networks (data acquisition success rate: 46%). For each reconstructed organization network, we measured several network diagnostics, which will be used for further statistical analysis to investigate their potential correlations with corporate behavior and performance.

Yingjun Dong, Neil G. MacLaren, Yiding Cao et al.

Utterance clustering is one of the actively researched topics in audio signal processing and machine learning. This study aims to improve the performance of utterance clustering by processing multichannel (stereo) audio signals. Processed audio signals were generated by combining left- and right-channel audio signals in a few different ways and then extracted embedded features (also called d-vectors) from those processed audio signals. This study applied the Gaussian mixture model for supervised utterance clustering. In the training phase, a parameter sharing Gaussian mixture model was conducted to train the model for each speaker. In the testing phase, the speaker with the maximum likelihood was selected as the detected speaker. Results of experiments with real audio recordings of multi-person discussion sessions showed that the proposed method that used multichannel audio signals achieved significantly better performance than a conventional method with mono audio signals in more complicated conditions.

Yiding Cao, Yingjun Dong, Minjun Kim et al.

Collective design and innovation are crucial in organizations. To investigate how the collective design and innovation processes would be affected by the diversity of knowledge and background of collective individual members, we conducted three collaborative design task experiments which involved nearly 300 participants who worked together anonymously in a social network structure using a custom-made computer-mediated collaboration platform. We compared the idea generation activity among three different background distribution conditions (clustered, random, and dispersed) with the help of the "doc2vec" text representation machine learning algorithm. We also developed a new method called "Idea Geography" to visualize the idea utility terrain on a 2D problem domain. The results showed that groups with random background allocation tended to produce the best design idea with highest utility values. It was also suggested that the diversity of participants' backgrounds distribution on the network might interact with each other to affect the diversity of ideas generated. The proposed idea geography successfully visualized that the collective design processes did find the high utility area through exploration and exploitation in collaborative work.

Minjun Kim, Hiroki Sayama

Text classification is one of the most critical areas in machine learning and artificial intelligence research. It has been actively adopted in many business applications such as conversational intelligence systems, news articles categorizations, sentiment analysis, emotion detection systems, and many other recommendation systems in our daily life. One of the problems in supervised text classification models is that the models' performance depends heavily on the quality of data labeling that is typically done by humans. In this study, we propose a new network community detection-based approach to automatically label and classify text data into multiclass value spaces. Specifically, we build networks with sentences as the network nodes and pairwise cosine similarities between the Term Frequency-Inversed Document Frequency (TFIDF) vector representations of the sentences as the network link weights. We use the Louvain method to detect the communities in the sentence networks. We train and test the Support Vector Machine and the Random Forest models on both the human-labeled data and network community detection labeled data. Results showed that models with the data labeled by the network community detection outperformed the models with the human-labeled data by 2.68-3.75% of classification accuracy. Our method may help developments of more accurate conversational intelligence and other text classification systems.

Carlos Gershenson, Vito Trianni, Justin Werfel et al.

Self-organization can be broadly defined as the ability of a system to display ordered spatio-temporal patterns solely as the result of the interactions among the system components. Processes of this kind characterize both living and artificial systems, making self-organization a concept that is at the basis of several disciplines, from physics to biology and engineering. Placed at the frontiers between disciplines, Artificial Life (ALife) has heavily borrowed concepts and tools from the study of self-organization, providing mechanistic interpretations of life-like phenomena as well as useful constructivist approaches to artificial system design. Despite its broad usage within ALife, the concept of self-organization has been often excessively stretched or misinterpreted, calling for a clarification that could help with tracing the borders between what can and cannot be considered self-organization. In this review, we discuss the fundamental aspects of self-organization and list the main usages within three primary ALife domains, namely "soft" (mathematical/computational modeling), "hard" (physical robots), and "wet" (chemical/biological systems) ALife. We also provide a classification to locate this research. Finally, we discuss the usefulness of self-organization and related concepts within ALife studies, point to perspectives and challenges for future research, and list open questions. We hope that this work will motivate discussions related to self-organization in ALife and related fields.

Hiroki Sayama

Open-ended evolution requires unbounded possibilities that evolving entities can explore. The cardinality of a set of those possibilities thus has a significant implication for the open-endedness of evolution. We propose that facilitating formation of higher-order entities is a generalizable, effective way to cause a "cardinality leap" in the set of possibilities that promotes open-endedness. We demonstrate this idea with a simple, proof-of-concept toy model called "Hash Chemistry" that uses a hash function as a fitness evaluator of evolving entities of any size/order. Simulation results showed that the cumulative number of unique replicating entities that appeared in evolution increased almost linearly along time without an apparent bound, demonstrating the effectiveness of the proposed cardinality leap. It was also observed that the number of individual entities involved in a single replication event gradually increased over time, indicating evolutionary appearance of higher-order entities. Moreover, these behaviors were not observed in control experiments in which fitness evaluators were replaced by random number generators. This strongly suggests that the dynamics observed in Hash Chemistry were indeed evolutionary behaviors driven by selection and adaptation taking place at multiple scales.

Hiroki Sayama

We studied the long-term dynamics of evolutionary Swarm Chemistry by extending the simulation length ten-fold compared to earlier work and by developing and using a new automated object harvesting method. Both macroscopic dynamics and microscopic object features were characterized and tracked using several measures. Results showed that the evolutionary dynamics tended to settle down into a stable state after the initial transient period, and that the extent of environmental perturbations also affected the evolutionary trends substantially. In the meantime, the automated harvesting method successfully produced a huge collection of spontaneously evolved objects, revealing the system's autonomous creativity at an unprecedented scale.

Carlos Gershenson, Vito Trianni, Justin Werfel et al.

Self-organization has been an important concept within a number of disciplines, which Artificial Life (ALife) also has heavily utilized since its inception. The term and its implications, however, are often confusing or misinterpreted. In this work, we provide a mini-review of self-organization and its relationship with ALife, aiming at initiating discussions on this important topic with the interested audience. We first articulate some fundamental aspects of self-organization, outline its usage, and review its applications to ALife within its soft, hard, and wet domains. We also provide perspectives for further research.

Hiroki Sayama, Farnaz Zamani Esfahlani, Ali Jazayeri et al.

We propose a novel computational method to extract information about interactions among individuals with different behavioral states in a biological collective from ordinary video recordings. Assuming that individuals are acting as finite state machines, our method first detects discrete behavioral states of those individuals and then constructs a model of their state transitions, taking into account the positions and states of other individuals in the vicinity. We have tested the proposed method through applications to two real-world biological collectives: termites in an experimental setting and human pedestrians in a university campus. For each application, a robust tracking system was developed in-house, utilizing interactive human intervention (for termite tracking) or online agent-based simulation (for pedestrian tracking). In both cases, significant interactions were detected between nearby individuals with different states, demonstrating the effectiveness of the proposed method.

Ali Jazayeri, Hiroki Sayama

We propose a new polynomial-time deterministic algorithm that produces an approximated solution for the traveling salesperson problem. The proposed algorithm ranks cities based on their priorities calculated using a power function of means and standard deviations of their distances from other cities and then connects the cities to their neighbors in the order of their priorities. When connecting a city, a neighbor is selected based on their neighbors' priorities calculated as another power function that additionally includes their distance from the focal city to be connected. This repeats until all the cities are connected into a single loop. The time complexity of the proposed algorithm is $O(n^2)$, where $n$ is the number of cities. Numerical evaluation shows that, despite its simplicity, the proposed algorithm produces shorter tours with less time complexity than other conventional tour construction heuristics. The proposed algorithm can be used by itself or as an initial tour generator for other more complex heuristic optimization algorithms.

Andreas D. Pape, Kenneth J. Kurtz, Hiroki Sayama

The nature of concept learning is a core question in cognitive science. Theories must account for the relative difficulty of acquiring different concepts by supervised learners. For a canonical set of six category types, two distinct orderings of classification difficulty have been found. One ordering, which we call paradigm-specific, occurs when adult human learners classify objects with easily distinguishable characteristics such as size, shape, and shading. The general order occurs in all other known cases: when adult humans classify objects with characteristics that are not readily distinguished (e.g., brightness, saturation, hue); for children and monkeys; and when categorization difficulty is extrapolated from errors in identification learning. The paradigm-specific order was found to be predictable mathematically by measuring the logical complexity of tasks, i.e., how concisely the solution can be represented by logical rules. However, logical complexity explains only the paradigm-specific order but not the general order. Here we propose a new difficulty measurement, information complexity, that calculates the amount of uncertainty remaining when a subset of the dimensions are specified. This measurement is based on Shannon entropy. We show that, when the metric extracts minimal uncertainties, this new measurement predicts the paradigm-specific order for the canonical six category types, and when the metric extracts average uncertainties, this new measurement predicts the general order. Moreover, for learning category types beyond the canonical six, we find that the minimal-uncertainty formulation correctly predicts the paradigm-specific order as well or better than existing metrics (Boolean complexity and GIST) in most cases.

Hiroki Sayama, Shelley D. Dionne

We report a summary of our interdisciplinary research project "Evolutionary Perspective on Collective Decision Making" that was conducted through close collaboration between computational, organizational and social scientists at Binghamton University. We redefined collective human decision making and creativity as evolution of ecologies of ideas, where populations of ideas evolve via continual applications of evolutionary operators such as reproduction, recombination, mutation, selection, and migration of ideas, each conducted by participating humans. Based on this evolutionary perspective, we generated hypotheses about collective human decision making using agent-based computer simulations. The hypotheses were then tested through several experiments with real human subjects. Throughout this project, we utilized evolutionary computation (EC) in non-traditional ways---(1) as a theoretical framework for reinterpreting the dynamics of idea generation and selection, (2) as a computational simulation model of collective human decision making processes, and (3) as a research tool for collecting high-resolution experimental data of actual collaborative design and decision making from human subjects. We believe our work demonstrates untapped potential of EC for interdisciplinary research involving human and social dynamics.

Hiroki Sayama

We studied the roles of morphogenetic principles---heterogeneity of components, dynamic differentiation/re-differentiation of components, and local information sharing among components---in the self-organization of morphogenetic collective systems. By incrementally introducing these principles to collectives, we defined four distinct classes of morphogenetic collective systems. Monte Carlo simulations were conducted using an extended version of the Swarm Chemistry model that was equipped with dynamic differentiation/re-differentiation and local information sharing capabilities. Self-organization of swarms was characterized by several kinetic and topological measurements, the latter of which were facilitated by a newly developed network-based method. Results of simulations revealed that, while heterogeneity of components had a strong impact on the structure and behavior of the swarms, dynamic differentiation/re-differentiation of components and local information sharing helped the swarms maintain spatially adjacent, coherent organization.

Shelley D. Dionne, Hiroki Sayama, Francis J. Yammarino

Collective, especially group-based, managerial decision making is crucial in organizations. Using an evolutionary theoretic approach to collective decision making, agent-based simulations were conducted to investigate how human collective decision making would be affected by the agents' diversity in problem understanding and/or behavior in discussion, as well as by their social network structure. Simulation results indicated that groups with consistent problem understanding tended to produce higher utility values of ideas and displayed better decision convergence, but only if there was no group-level bias in collective problem understanding. Simulation results also indicated the importance of balance between selection-oriented (i.e., exploitative) and variation-oriented (i.e., explorative) behaviors in discussion to achieve quality final decisions. Expanding the group size and introducing non-trivial social network structure generally improved the quality of ideas at the cost of decision convergence. Simulations with different social network topologies revealed collective decision making on small-world networks with high local clustering tended to achieve highest decision quality more often than on random or scale-free networks. Implications of this evolutionary theory and simulation approach for future managerial research on collective, group, and multi-level decision making are discussed.

Hiroki Sayama

Self-organization of heterogeneous particle swarms is rich in its dynamics but hard to design in a traditional top-down manner, especially when many types of kinetically distinct particles are involved. In this chapter, we discuss how we have been addressing this problem by (1) utilizing and enhancing interactive evolutionary design methods and (2) realizing spontaneous evolution of self organizing swarms within an artificial ecosystem.