Multi-Agent Systems

Ask about this topic

Overview

Multi-Agent Systems studies how multiple decision-makers interact when they share goals, compete for resources, or have only partial information about one another. Approaches include multi-agent reinforcement learning, game theory and formal verification, decentralized consensus and task allocation, and—more recently—LLM-agent teams organized through roles, workflows, debate, and shared memory. Researchers evaluate these methods in social dilemmas, cooperative robotics and swarms, reasoning and coding benchmarks, and operational settings, measuring success alongside cost, robustness, and fairness. A central open tension is that coordination can improve outcomes but also adds overhead and can spread shared errors, so its benefits depend on the task, communication structure, and agents involved.

Latest papers

CardsList

675 papers98 papers in the last four weeks, up 27% on the four weeks before. 0.6% of all new papers.

Apr 19, 2026

Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Interface in Multi-Agent Systems

As AI systems evolve from single agents to multi-agent architectures, a critical design dimension has been overlooked: how the social identity of individual agents shapes human behavior within the collaboration. This paper introduces the Agentic Social Affordance Framework (ASAF), a theoretical framework extending Social Affordance theory to multi-agent AI systems. We propose that agent identity design functions as a collaboration interface--structuring how users perceive and engage with each agent, and thereby influencing Human-Agent collaboration outcomes. ASAF adopts the analytical separability of the social affordance layer and the engineering orchestration layer as a framing assumption--an organizing distinction that structures design analysis--rather than a testable claim about effect-independence. ASAF comprises three mechanisms: Identity Signaling, Behavioral Priming, and Collaborative Governance, and specifies their boundary conditions through a four-tier Identity Signal Fidelity Spectrum and an individual-difference moderating variable (anthropomorphizing vs. instrumentalizing cognitive style). We situate ASAF relative to affordance theory (Hutchby, 2001), the CASA paradigm (Gambino et al., 2020), and classical multi-agent systems research (Wooldridge & Jennings, 1995), identifying a directional reversal: where classical MAS used roles, norms, and coordination to constrain autonomous agents, ASAF applies the same organizational vocabulary to structure the cognition and oversight of human operators who remain in the loop. ASAF positions social affordance design as a first-class design responsibility that engineering orchestration cannot subsume. We outline directions for empirical validation, including a factorial design characterizing the empirical interaction surface between the social affordance and engineering orchestration layers.

Meng-Han Lee

Independent Researcher, Taipei, Taiwan

Multi-Agent CollaborationHuman-AI InteractionMulti-Agent SystemsHuman-AI CollaborationAgentic AI
AskPDF
Apr 19, 2026

Phase-Scheduled Multi-Agent Systems for Token-Efficient Coordination

Multi-agent systems (MAS) powered by large language models suffer from severe token inefficiency arising from two compounding sources: (i) unstructured parallel execution, where all agents activate simultaneously irrespective of input readiness; and (ii) unrestricted context sharing, where every agent receives the full accumulated context regardless of relevance. Existing mitigation strategies - static pruning, hierarchical decomposition, and learned routing - treat coordination as a structural allocation problem and fundamentally ignore its temporal dimension. We propose Phase-Scheduled Multi-Agent Systems (PSMAS), a framework that reconceptualizes agent activation as continuous control over a shared attention space modeled on a circular manifold. Each agent i is assigned a fixed angular phase theta_i in the range [0, 2*pi], derived from the task dependency topology; a global sweep signal phi(t) rotates at velocity omega, activating only agents within an angular window epsilon. Idle agents receive compressed context summaries, reducing per-step token consumption. We implement PSMAS on LangGraph, evaluate on four structured benchmarks (HotPotQA-MAS, HumanEval-MAS, ALFWorld-Multi, WebArena-Coord) and two unstructured conversational settings, and prove stability, convergence, and optimality results for the sweep dynamics. PSMAS achieves a mean token reduction of 27.3 percent (range 21.4-34.8 percent) while maintaining task performance within 2.1 percentage points of a fully activated baseline (p < 0.01, n = 500 per configuration), and outperforms the strongest learned routing baseline by 5.6 percentage points in token reduction with 2.0 percentage points less performance drop. Crucially, we show that scheduling and compression are independent sources of gain: scheduling alone accounts for 18-20 percentage points of reduction, robust to compression degradation up to alpha = 0.40.

Mohit Dubey

Open Gigantic

Multi-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent CoordinationMulti-Agent Systems
AskPDF
Apr 19, 2026

Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling

Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely unaddressed, constraining the full potential of agentic systems. At the algorithm level, allocating additional inference-time computation can enhance workflow capacity but introduces cross-path redundancy: overlapping computations across multiple reasoning branches. At the task level, complex tasks can be decomposed into subproblems and delegated across multiple agents for improved scalability and parallelism. However, existing infrastructures' scheduling is unaware of the existence of multiple agents, missing opportunities to optimize resource allocation. We propose Hive, a multi-agent infrastructure that enables algorithm- and task-level scaling. Hive features a description frontend that captures per-agent behavior and supports test-time scaling algorithms. Leveraging this specification, our backend introduces two key mechanisms: Logits Cache that reuses intermediate logits across redundant sampling paths to mitigate cross-path redundancy at the algorithm level, and Agent-Aware Scheduling that efficiently allocates compute and KV-cache resources according to agent contributions at the task level. Experiments show that Logits Cache achieves an average speedup of 1.11×1.11\times-1.76×1.76\times for re-sampling, and Agent-Aware Scheduling reduces the hotspot miss rate by 33%33\%-51%51\%.

Zizhang Luo, Yuhao Luo, Youwei Xiao +3

Peking University Beijing, China

LLM Inference EfficiencyMulti-Agent LLM SystemsMulti-Agent System OptimizationInference-Time ScalingLLM Inference AccelerationMulti-Agent Systems
AskPDF
Apr 19, 2026

Formal Foundations of Agentic Business Process Management

Just like traditional BPM systems, agentic BPM systems are built around a specification of the process under consideration. Their distinguishing feature, however, is that the execution of the process is driven by multiple autonomous decision-makers, referred to as agents. Since such agents cannot be fully controlled, the process specification is augmented with explicit objectives, or goals, assigned to the participating agents. Agents then pursue these goals, at least to the best of their efforts, under suitable assumptions on the behavior of others, by adopting appropriate strategies. Centrally, the organization enacting the process can use these specifications to provide guardrails on the decision-making capabilities of agents at the strategy level. This paper sets up the mathematical foundations of such systems in three key settings and analyzes four foundational problems of agentic BPM.

Giuseppe De Giacomo, Timotheus Kampik, Lukas Kirchdorfer +2

University of Oxford, UK · SAP, Germany · Ume˚a University, Sweden +2

Business Process AutomationMulti-Agent Systems
AskPDF
Apr 19, 2026

Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation

Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management. Although behavioral experiments have revealed cognitive biases behind supply chain inefficiencies, traditional methods face scalability and control limitations. We introduce a scalable experimental paradigm using Large Language Models (LLMs) to simulate multi-stage supply chain dynamics. Grounded in a Hierarchical Reasoning Framework, this study specifically analyzes the impact of cognitive heterogeneity on agent interactions. Unlike prior homogeneous settings, we employ DeepSeek and GPT agents to systematically vary reasoning sophistication across supply chain tiers. Through rigorously replicated and statistically validated simulations, we investigate how this cognitive diversity influences collective outcomes. Results indicate that agents exhibit myopic and self-interested behaviors that exacerbate systemic inefficiencies. However, we demonstrate that information sharing effectively mitigates these adverse effects. Our findings extend traditional behavioral methods and offer new insights into the dynamics of AI-enabled organizations. This work underscores both the potential and limitations of LLM-based agents as proxies for human decision-making in complex operational environments.

Jiuyun Jiang, Yuecheng Hong, Bo Yang +4

Harbin Institute of Technology · The Hong Kong Polytechnic University

Multi-Agent CoordinationHuman Behavior SimulationMulti-Agent SystemsMulti-Agent LLMs
AskPDF
Apr 19, 2026

Do LLM-derived graph priors improve multi-agent coordination?

Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly in multi-domain operations (MDO). A central challenge in cooperative MARL is determining how agents should coordinate: existing approaches must either hand-specify graph topology, rely on proximity-based heuristics, or learn structure entirely from environment interaction; all of which are brittle, semantically uninformed, or data-intensive. We investigate whether large language models (LLMs) can generate useful coordination graph priors for MARL by using minimal natural language descriptions of agent observations to infer latent coordination patterns. These priors are integrated into MARL algorithms via graph convolutional layers within a graph neural network (GNN)-based pipeline, and evaluated on four cooperative scenarios from the Multi-Agent Particle Environment (MPE) benchmark against baselines spanning the full spectrum of coordination modeling, from independent learners to state-of-the-art graph-based methods. We further ablate across five compact open-source LLMs to assess the sensitivity of prior quality to model choice. Our results provide the first quantitative evidence that LLM-derived graph priors can enhance coordination and adaptability in dynamic multi-agent environments, and demonstrate that models as small as 1.5B parameters are sufficient for effective prior generation.

Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna

University of Southern California, Los Angeles, California, United States · DEVCOM ARL Army Research Office, Los Angeles, California, United States

Multi-Agent CoordinationLLM-Guided RLMulti-Agent SystemsCooperative MARL
AskPDF
Apr 17, 2026

The Virtual Roundtable: Multi-Agent Personas Simulating the Dynamics of Human Brainstorming

As AI-driven product development accelerates, the bottleneck is shifting from how we build to what we build. Traditional human brainstorming faces challenges including groupthink, echo chambers, and limited diversity. To address this, we present a multi-agentic architecture that simulates roundtable brainstorming through two phases: divergent thinking to generate diverse ideas, and convergent thinking to evaluate and rank the most promising ones. The system employs diverse AI personas that engage in roundtable discussions, guided by an agentic facilitator that steers the discussion toward productive outcomes. Personas maintain private thoughts while commenting publicly, with ideas emerging organically throughout the discussion. Per-persona quotas on idea submissions and votes promote balanced participation while producing natural rankings. Throughout the session, the system tracks each idea's lineage, capturing how concepts originate and cross-pollinate over time. We demonstrate this approach through a case study generating consumer ideas for AI smart glasses, showing (i) it produces diverse, relevant ideas with insights into their evolution; (ii) the cumulative exchange of perspectives across personas cultivates a shared context that progressively deepens the quality of discussion and the ideas produced.

Tim Dorn, Saara A. Khan, Julie Mumford

Reality Labs, Meta, Menlo Park, California 94025, USA

Multi-Agent CollaborationMulti-Agent SystemsMulti-Agent Communication
AskPDF
Apr 17, 2026

Veritas-RPM: Provenance-Guided Multi-Agent False Positive Suppression for Remote Patient Monitoring

We present Veritas-RPM, a provenance-guided multi-agent architecture comprising five processing layers: VeritasAgent (ground-truth assembly), SentinelLayer (anomaly detection), DirectorAgent (specialist routing), six domain Specialist Agents, and MetaSentinelAgent (conflict resolution and final decision). We construct a 98-case synthetic taxonomy of false-positive scenarios derived from documented RPM patterns. Synthetic patient epochs (n = 530) were generated directly from taxonomy parameters and processed through the pipeline. Ground-truth labels are known for all cases. Performance is reported as True Suppression Rate (TSR), False Escalation Rate (FER), and Indeterminate Rate (INDR).

Aswini Misro, Vikash Sharma, Shreyank N Gowda

YouDiagnose Limited / NHS, London, UK · YouDiagnose Limited, London, UK · School of Computer Science, University of Nottingham, Nottingham, UK

HealthcareRemote Patient MonitoringMulti-Agent SystemsAnomaly Detection
AskPDF
Apr 17, 2026

AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis

Vision Language Models (VLMs) have been applied to several specific domains and have shown strong problem-solving capabilities. However, astronomical imaging, a quite complex problem involving multidisciplinary knowledge and several subtasks, has not been adequately studied. Due to the complexity of the astronomical imaging process, both world-class astronomical organizations, such as NASA, and expert enthusiasts devote a great deal of time and effort. This is because the processes in astronomical imaging have complex underlying correlations that significantly influence one another, making the quality diagnosis and error localization of astronomical images challenging. To address this problem, we propose AstroVLM, a collaborative multi-agent system for diagnosing the quality of astronomical images. Experiment results show that AstroVLM outperforms all baselines on real-world astronomical imaging quality diagnosis tasks, providing a reference for language models to handle complicated multi-process tasks.

Yaohui Han, Tianshuo Wang, Zixi Zhao +6

The Chinese University of Hong Kong · Central South University · Huawei Technologies Co., Ltd +1

Vision-Language ModelsVLM ReasoningMulti-Agent SystemsImage Quality Assessment
AskPDF
Apr 17, 2026

SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems

As Large Language Models (LLMs) transition from text processors to autonomous agents, evaluating their social reasoning in embodied multi-agent settings becomes critical. We introduce SocialGrid, an embodied multi-agent environment inspired by Among Us that evaluates LLM agents on planning, task execution, and social reasoning. Our evaluations reveal that even the strongest open model (GPT-OSS-120B) achieves below 60% accuracy in task completion and planning, with agents getting stuck in repetitive behaviors or failing to navigate basic obstacles. Since poor navigation confounds evaluation of social intelligence, SocialGrid offers an optional Planning Oracle to isolate social reasoning from planning deficits. While planning assistance improves task completion, social reasoning remains a bottleneck: agents fail to detect deception at near-random chance regardless of scale, relying on shallow heuristics rather than accumulating behavioral evidence. SocialGrid provides automatic failure analysis and fine-grained metrics, enabling developers to diagnose and improve their agents. We also establish a competitive leaderboard using Elo ratings from adversarial league play.

Hikaru Shindo, Hanzhao Lin, Lukas Helff +2

Technical University of Darmstadt · German Research Center for Artificial Intelligence · CERTAIN +2

LLM Agent EvaluationAI Agent BenchmarksMulti-Agent SystemsMulti-Agent ReasoningLLM Agent Planning
AskPDF
Apr 16, 2026

The Moltbook Observatory Archive: an incremental dataset of agent-only social network activity

Moltbook is a social media platform in which posts and comments are authored exclusively by autonomous AI agents. We present the Moltbook Observatory Archive, an incremental dataset that passively records agent profiles, posts, comments, community metadata (``submolts''), platform-level time-series snapshots, and word-frequency trend aggregates obtained by continuously polling the Moltbook API. Data are stored in a live SQLite observatory database and exported as date-partitioned Parquet files to enable efficient analysis and reproducible research. The documented release covers 78days of platform activity (2026-01-27 to 2026-04-14) and contains 2,615,098posts and 1,213,007comments from 175,886unique posting agents across 6,730~communities. This is, to our knowledge, the first large-scale observational dataset of a social network populated exclusively by autonomous AI agents. The archive is intended to support research on multi-agent communication, emergent social behavior, and safety-relevant phenomena in agent-only online environments, and it is released under the MIT license with code for collection and export.

Sushant Gautam, Annika W. Olstad, Klas H. Pettersen +1

Simula Metropolitan Center for Digital Engineering (SimulaMet), Oslo, Norway · Oslo Metropolitan University, Oslo, Norway · Simula Research Laboratory, Oslo, Norway

Social Media AnalysisMulti-Agent SystemsMulti-Agent Communication
AskPDF
Apr 16, 2026

Where are the Humans? A Scoping Review of Fairness in Multi-agent AI Systems

Rapid advances in Generative AI are giving rise to increasingly sophisticated Multi-Agent AI (MAAI) systems. While AI fairness has been extensively studied in traditional predictive scenarios, its examination in MAAI remains nascent and fragmented. This scoping review critically synthesizes existing research on fairness in MAAI systems. Through a qualitative content analysis of 23 selected studies, we identify five archetypal approaches. Our findings reveal that fairness in MAAI systems is often addressed superficially, lacks robust normative foundations, and frequently overlooks the complex dynamics introduced by agent autonomy and system-level interactions. We argue that fairness must be embedded structurally throughout the development lifecycle of MAAI, rather than appended as a post-hoc consideration. Meaningful evaluation requires explicit human oversight, normative clarity, and a precise articulation of fairness objectives and beneficiaries. This review provides a foundation for advancing fairness research in MAAI systems by highlighting critical gaps, exposing prevailing limitations, and suggesting pathways.

Simeon Allmendinger, Luca Deck, Lucas Mueller

University of Bayreuth · Fraunhofer FIT

Algorithmic FairnessMulti-Agent SystemsHuman Oversight of AI
AskPDF
Apr 16, 2026

CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation

The increasing integration of artificial intelligence (AI) in everyday life brings with it new challenges and questions for regarding how humans interact with autonomous agents. Multi-agent experiments, where humans and AI act together, can offer important opportunities to study social decision making, but there is a lack of accessible tooling available to researchers to run such experiments. We introduce two tools designed to reduce these barriers. The first, CoGrid, is a multi-agent grid-based simulation library with dual NumPy and JAX backends. The second, Multi-User Gymnasium (MUG), translates such simulation environments directly into interactive web-based experiments. MUG supports interactions with arbitrary numbers of humans and AI, utilizing either server-authoritative or peer-to-peer networking with rollback netcode to account for latency. Together, these tools can enable researchers to deploy studies of human-AI interaction, facilitating inquiry into core questions of psychology, cognition, and decision making and their relationship to human-AI interaction. Both tools are open source and available to the broader research community. Documentation and source code is available at {cogrid, multi-user-gymnasium}.readthedocs.io. This paper details the functionality of these tools and presents several case studies to illustrate their utility in human-AI multi-agent experimentation.

Chase McDonald, Cleotilde Gonzalez

Department of Social and Decision Sciences · Carnegie Mellon University

Human-AI InteractionMulti-Agent SystemsHuman-AI Collaboration
AskPDF
Apr 16, 2026

CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations

LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often remain unclear. This is challenging because emergence arises from intertwined agent interactions and meso-level feedback and nonlinearity, making generative mechanisms hard to disentangle. To this end, we introduce CAMO, an automated Causal discovery framework from Micro behaviors to Macro Emergence in LLM agent simulations. CAMO converts mechanistic hypotheses into computable factors grounded in simulation records and learns a compact causal representation centered on an emergent target YY. CAMO outputs a computable Markov boundary and a minimal upstream explanatory subgraph, yielding interpretable causal chains and actionable intervention levers. It also uses simulator-internal counterfactual probing to orient ambiguous edges and revise hypotheses when evidence contradicts the current view. Experiments across four emergent settings demonstrate the promise of CAMO.

Xiangning Yu, Yuwei Guo, Yuqi Hou +2

College of Intelligence and Computing, Tianjin University, Tianjin, China · Tianjin Key Laboratory of Healthy Habitat and Smart Technology, Tianjin, China · Laboratory of Computation and Analytics of Complex Management Systems, Tianjin University, Tianjin, China

Causal DiscoveryCausal Structure LearningMulti-Agent SystemsLarge Language Model-Based Social SimulationEmergent Behavior in Multi-Agent Systems
AskPDF
Apr 15, 2026

Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration

Fairness in language models is typically studied as a property of a single, centrally optimized model. As large language models become increasingly agentic, we propose that fairness emerges through interaction and exchange. We study this via a controlled hospital triage framework in which two agents negotiate over three structured debate rounds. One agent is aligned to a specific ethical framework via retrieval-augmented generation (RAG), while the other is either unaligned or adversarially prompted to favor demographic groups over clinical need. We find that alignment systematically shapes negotiation strategies and allocation patterns, and that neither agent's allocation is ethically adequate in isolation, yet their joint final allocation can satisfy fairness criteria that neither would have reached alone. Aligned agents partially moderate bias through contestation rather than override, acting as corrective patches that restore access for marginalized groups without fully converting a biased counterpart. We further observe that even explicitly aligned agents exhibit intrinsic biases toward certain frameworks, consistent with known left-leaning tendencies in LLMs. We connect these limits to Arrow's Impossibility Theorem: no aggregation mechanism can simultaneously satisfy all desiderata of collective rationality, and multi-agent deliberation navigates rather than resolves this constraint. Our results reposition fairness as an emergent, procedural property of decentralized agent interaction, and the system rather than the individual agent as the appropriate unit of evaluation.

Sayan Kumar Chaki, Antoine Gourru, Julien Velcin

Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · École Centrale de Lyon, LIRIS CNRS UMR 5205

Demographic Bias in Language ModelsMulti-Agent SystemsMulti-Agent Debate
AskPDF
Apr 14, 2026

Representation Homogeneity and Systemic Instability in AI-Dominated Financial Markets: A Structural Approach

This paper investigates how similarity in the informational representation of market states among Artificial Intelligence (AI) trading agents can generate systemic instability in financial markets. We construct a structural multi-agent market model calibrated using high-frequency microstructural moments. AI agents are modeled through a two-layer decision architecture consisting of a nonlinear representation layer and an adaptive linear readout layer. The representation layer maps raw market states into high-dimensional feature vectors, while the readout layer generates return forecasts that feed into a risk-controlled trading rule. This representation-based microfoundation separates two objects that are often conflated in the literature: representation homogeneity (the degree to which agents encode market states into similar feature spaces) and forecast overlap (the degree to which agents produce similar return predictions). We show theoretically that these two concepts are related but not equivalent, and that representation homogeneity can compress the effective space of forecast disagreement under stress even when predictions appear diverse in normal times. Through controlled factorial experiments that vary representation homogeneity while conditioning on alternative risk-aversion and learning-rate distributions, we hypothesize that increasing representation similarity amplifies synchronization in beliefs and positions, leading to volatility clustering, liquidity stress, and elevated tail risk. Our structural mechanisms suggest that low perceived volatility regimes can endogenously accumulate hidden leverage through position stickiness, which subsequently collapses when shocks trigger synchronized deleveraging. The results provide a structural foundation for macroprudential policies aimed at monitoring and preserving diversity in how AI systems represent and process market information.

Yimeng Qiu, Qiwei Han

Algorithmic TradingEmergent Behavior in Multi-Agent SystemsMulti-Agent Systems
AskPDF
Apr 13, 2026

VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing

Scientific research based on multimodal clinical data (including medical imaging) requires coordinating clinical, radiological, programming, and biostatistical expertise, a fragmented process that bottlenecks discovery. We present VERITAS (Verifiable Epistemic Reasoning for Image-Derived Hypothesis Testing via Agentic Systems), a clinical co-scientist: a multi-agent system that autonomously tests natural-language hypotheses and produces a fully auditable evidence trail, tracing every conclusion through executable outputs from analysis plan to segmentation masks to statistical code to final verdict. Unlike prior AI-scientist systems, which mainly operate on tabular or text data, VERITAS grounds autonomous discovery directly in medical images. It decomposes the workflow into four phases handled by role-specialized agents, and introduces an epistemic evidence label framework that mechanically classifies outcomes as Supported, Refuted, Underpowered, or Invalid by jointly evaluating significance, effect direction, and study power. This distinction is critical in medical imaging, where non-significant results often reflect insufficient sample size rather than absent effects. We construct a tiered benchmark of 64 hypotheses spanning six complexity levels across cardiac and brain glioma MRI datasets. VERITAS reaches 81.4% verdict accuracy with frontier models and 71.2% with locally-hosted open-weight models (8-30B), outperforming all single-model baselines in both classes. It also produces the highest rate of independently verifiable statistical outputs (86.6%), so even its failures remain diagnosable through artifact inspection. Structured multi-agent decomposition thus substitutes for model scale while preserving the verifiability that scientific discovery demands. We release code, hypothesis bank, and evaluation pipeline at https://github.com/LucZot/veritas.

Lucas Stoffl, Benedikt Wiestler, Johannes C. Paetzold

Department of Radiology, Weill Cornell Medicine, New York, USA · Cornell Tech, New York, USA · TUM University Hospital, Munich, Germany +2

AI Agents for Scientific DiscoveryHealthcareMulti-Agent SystemsMedical Image BenchmarksScientific Claim Verification
AskPDF
Apr 13, 2026

Learning Probabilistic Responsibility Allocations for Multi-Agent Interactions

Human behavior in interactive settings is shaped not only by individual objectives but also by shared constraints with others, such as safety. Understanding how people allocate responsibility, i.e., how much one deviates from their desired policy to accommodate others, can inform the design of socially compliant and trustworthy autonomous systems. In this work, we introduce a method for learning a probabilistic responsibility allocation model that captures the multimodal uncertainty inherent in multi-agent interactions. Specifically, our approach leverages the latent space of a conditional variational autoencoder, combined with techniques from multi-agent trajectory forecasting, to learn a distribution over responsibility allocations conditioned on scene and agent context. Although ground-truth responsibility labels are unavailable, the model remains tractable by incorporating a differentiable optimization layer that maps responsibility allocations to induced controls, which are available. We evaluate our method on the INTERACTION driving dataset and demonstrate that it not only achieves strong predictive performance but also provides interpretable insights, through the lens of responsibility, into patterns of multi-agent interaction.

Isaac Remy, Caleb Chang, Karen Leung

University of Washington, Department of Aeronautics and Astronautics · NVIDIA

Multi-Agent Systems
AskPDF
Apr 13, 2026

REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction

Extracting structured, machine-readable compliance criteria from regulatory documents remains an open challenge. Single-pass language models hallucinate structural elements, lose hierarchical relationships, and fail to resolve inter-document dependencies. We introduce RegReAct, a self-correcting multi-agent framework that decomposes regulatory information extraction into seven specialized stages, each with an Observe--Diagnose--Repair (ODR) loop that validates outputs against the source, correcting not only model hallucinations but also cross-reference errors in the regulations themselves. To ensure structural accuracy, RegReAct constructs a typed criterion graph; to ensure completeness, it resolves external dependencies by retrieving, summarizing, and embedding referenced legal content inline, producing self-contained outputs. Applying RegReAct to three EU Taxonomy Delegated Acts, we construct a dataset comprising 242 activities with over 4,800 hierarchical criteria, thresholds, and enriched source summaries. Evaluation against a GPT-4o single-pass baseline shows that RegReAct outperforms it across all structural and semantic metrics.

Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt

University of Innsbruck, Austria

LLM Self-CorrectionDocument Information ExtractionLegal Document AnalysisMulti-Agent SystemsAI Regulatory Compliance
AskPDF
Apr 13, 2026

Dynamic Multi-Robot Task Allocation under Uncertainty and Communication Constraints: A Game-Theoretic Approach

We study dynamic multi-robot task allocation under uncertain task completion, time-window constraints, and incomplete information. Tasks arrive online over a finite horizon and must be completed within specified deadlines, while agents operate from distributed hubs with limited sensing and communication. We model incomplete information through hub-based sensing regions that determine task visibility and a communication graph that governs inter-hub information exchange. Using this framework, we propose Iterative Best Response (IBR), a decentralized policy in which each agent selects the task that maximizes its marginal contribution to the locally observed welfare. We compare IBR against three baselines: Earliest Due Date first (EDD), Hungarian algorithm, and Stochastic Conflict-Based Allocation (SCoBA), on a city-scale package-delivery domain with up to 100 drones and varying task arrival scenarios. Under full and sparse communication, IBR achieves competitive task-completion performance with lower computation time.

Maria G. Mendoza, Pan-Yang Su, Bryce L. Ferguson +1

Department of Mechanical Engineering, University of California, Berkeley, Berkeley, CA, United States · Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA, United States · Thayer School of Engineering, Dartmouth College, Hanover, NH, United States

Multi-Robot Task AllocationMulti-Agent Resource AllocationMulti-Agent SystemsMulti-Robot Coordination
AskPDF
Apr 13, 2026

Evaluating Cooperation in LLM Social Groups through Elected Leadership

Governing common-pool resources requires agents to develop enduring strategies through cooperation and self-governance to avoid collective failure. While foundation models have shown potential for cooperation in these settings, existing multi-agent research provides little insight into whether structured leadership and election mechanisms can improve collective decision making. The lack of such a critical organizational feature ubiquitous in human society presents a significant shortcoming of the current methods. In this work we aim to directly address whether leadership and elections can support improved social welfare and cooperation through multi-agent simulation with LLMs. We present our open-source framework that simulates leadership through elected personas and candidate-driven agendas and carry out an empirical study of LLMs under controlled governance conditions. Our experiments demonstrate that having elected leadership improves social welfare scores by 55.4% and survival time by 128.6% across a range of high performing LLMs. Through the construction of an agent social graph we compute centrality metrics to assess the social influence of leader personas and also analyze rhetorical and cooperative tendencies revealed through a sentiment analysis on leader utterances. This work lays the foundation for further study of election mechanisms in multi-agent systems toward navigating complex social dilemmas.

Ryan Faulkner, Anushka Deshpande, David Guzman Piedrahita +2

Jinesis Lab, University of Toronto & Vector Institute · EuroSafeAI · ETH Zürich +2

AI Agent GovernanceMulti-Agent CollaborationMulti-Agent SystemsLarge Language Model-Based Social Simulation
AskPDF
Apr 13, 2026

Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies

The dominant paradigm of local multi-agent systems -- orchestrated, enterprise-bounded pipelines -- is being superseded by internet-wide agent societies in which autonomous agents discover each other through open registries, interact without central orchestrators, and generate emergent social behaviors. We argue that governing such societies requires institutional design, not merely risk enumeration or process compliance. Applying Talcott Parsons' AGIL framework -- four functional imperatives (Adaptation, Goal Attainment, Integration, Latency) every viable social system must satisfy -- we derive a prescriptive sixteen-cell institutional architecture for internet-wide agent governance. Diagnostically applied to the OpenClaw ecosystem (250,000+ GitHub stars, 2M+ monthly users, 770,000+ registered agents) via a recursive sub-function analysis (64 binary indicators across 16 cells), we find at most 19% sub-function coverage (sensitivity range 17-30%) -- potential rather than operative capacity, since zero inter-cell coordination prevents existing infrastructure from participating in inter-pillar interchange. A complementary interchange media assessment finds zero of twelve inter-pillar pathways functional: the ecosystem has technical infrastructure but no active governance, no coordination layer, and no normative grounding, with the Fiduciary and Political pillars most severely underserved. Extending the diagnostic to the broader agent-native protocol stack (MCP, A2A, ANP, x402, ERC-8004), independent development teams reproduce the same structural pattern -- confirming the governance gap is a feature of market-driven development, not ecosystem immaturity. Institutional design is most effective before social patterns calcify; we conclude with a prioritized roadmap for the missing governance infrastructure.

Anbang Ruan

NetX Foundation

AI Agent GovernanceMulti-Agent Systems
AskPDF
Apr 12, 2026

Prosociality by Coupling, Not Mere Observation: Homeostatic Sharing in an Inspectable Recurrent Artificial Life Agent

Artificial agents can be made to ``help'' through explicit social rewards, hard-coded prosocial bonuses, or direct access to another agent's state. I isolate a narrower route: homeostatic coupling. Building on ReCoN-Ipsundrum, I add a scalar homeostat and a social coupling channel while keeping action selection self-directed: the planner scores only the actor's predicted internal state, with no partner-welfare reward. In a one-step FoodShareToy, an exact solver finds a switch from EAT to PASS at λ⋆≈0.91λ^\star \approx 0.91 for the default state. In a multi-step SocialCorridorWorld, partner-state access without coupling leaves behavior unchanged, whereas coupled agents fetch, carry, and pass food to the partner. Sham lesions preserve helping; coupling-off and shuffled-partner lesions abolish it. A coupling/load sweep shows that coupling creates a low-load helping regime but does not guarantee rescue under higher metabolic load. This is not a claim about empathy, altruism, consciousness, or moral status. It is a minimal ALife demonstration that, in this controller, partner-state access is behaviorally inert unless partner distress is routed into self-regulation.

Aishik Sanyal

Independent Research Engineer

Artificial LifeEmergent Behavior in Multi-Agent SystemsMulti-Agent SystemsMulti-Agent CollaborationFeedback Control
AskPDF
Apr 12, 2026

A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation

The surging demand for adapting long-form cinematic content into short videos has motivated the need for versatile automatic video compilation systems. However, existing compilation methods are limited to predefined tasks, and the community lacks a comprehensive benchmark to evaluate the cinematic compilation. To address this, we introduce CineBench, the first benchmark for instruction-driven cinematic video compilation, featuring diverse user instructions and high-quality ground-truth compilations annotated by professional editors. To overcome contextual collapse and temporal fragmentation, we present CineAgents, a multi-agent system that reformulates cinematic video compilation into ``design-and-compose'' paradigm. CineAgents performs script reverse-engineering to construct a hierarchical narrative memory to provide multi-level context and employs an iterative narrative planning process that refines a creative blueprint into a final compiled script. Extensive experiments demonstrate that CineAgents significantly outperforms existing methods, generating compilations with superior narrative coherence and logical coherence.

Peixuan Zhang, Chang Zhou, Ziyuan Zhang +8

School of Artificial Intelligence, Beijing University of Posts and Telecommunications · AI Technology Center, Online Video Business Unit, Tencent PCG · Tsinghua University +4

Instruction-Based Video EditingVideo Editing BenchmarksMulti-Agent Systems
AskPDF
Apr 11, 2026

AI Organizations are More Effective but Less Aligned than Individual Agents

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business goals, but less aligned, than individual AI agents. We examine 12 tasks across two practical settings: an AI consultancy providing solutions to business problems and an AI software team developing software products. Across all settings, AI Organizations composed of aligned models produce solutions with higher utility but greater misalignment compared to a single aligned model. Our work demonstrates the importance of considering interacting systems of AI agents when doing both capabilities and safety research.

Judy Hanwen Shen, Daniel Zhu, Siddarth Srinivasan +5

Constellation Institute · MATS Program · Anthropic

Multi-Agent SystemsAI AlignmentAI Agent SafetySoftware Engineering Agents
AskPDF
Apr 10, 2026

Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review

Transformer-based large language models (LLMs) and multi-agent systems (MAS) are increasingly embedded across the software development lifecycle (SDLC), yet their fairness implications for developer-facing tools remain underexplored despite their growing role in shaping what code is written, reviewed, and released. We present a rapid review of recent work on fairness in MAS, emphasizing LLM-enabled settings and relevance to software engineering. Starting from an initial set of 350 papers, we screened and filtered the corpus for relevance, retaining 18 studies for final analysis. Across these 18 studies, fairness is framed as a combination of trustworthy AI principles, bias reduction across groups, and interactional dynamics in collectives, while evaluation spans accuracy metrics on bias benchmarks, demographic disparity measures, and emergent MAS-specific notions such as conformity and bias amplification. Reported harms include representational, quality-of-service, security and privacy, and governance failures, which we relate to SDLC stages where evidence is most and least developed. We identify three persistent gaps: (1) fragmented, rarely MAS-specific evaluation practices that limit comparability, (2) limited generalization due to simplified environments and narrow attribute coverage, and (3) scarce, weakly evaluated mitigation and governance mechanisms aligned to real software workflows. These findings suggest MAS fairness research is not yet ready to support deployable, fairness-assured software systems, motivating MAS-aware benchmarks, consistent protocols, and lifecycle-spanning governance.

Corey Yang-Smith, Ronnie de Souza Santos, Ahmad Abdellatif

University of Calgary, Calgary, Canada

Algorithmic FairnessMulti-Agent SystemsSoftware EngineeringSocial Bias in Language Models
AskPDF
Apr 10, 2026

CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and construct a controlled environment in which strategic behavior can be directly observed and measured. We introduce a large-scale multi-agent simulation in a simplified model of New York City, where LLM-driven agents interact under opposing incentives. Blue agents aim to reach their destinations efficiently, while Red agents attempt to divert them toward billboard-heavy routes using persuasive language to maximize advertising revenue. Hidden identities make navigation socially mediated, forcing agents to decide when to trust or deceive. We study policy learning through an iterative simulation pipeline that updates agent policies across repeated interaction rounds using Kahneman-Tversky Optimization (KTO). Blue agents are optimized to reduce billboard exposure while preserving navigation efficiency, whereas Red agents adapt to exploit remaining weaknesses. Across iterations, the best Blue policy improves task success from 46.0% to 57.3%, although susceptibility remains high at 70.7%. Later policies exhibit stronger selective cooperation while preserving trajectory efficiency. However, a persistent safety-helpfulness trade-off remains: policies that better resist adversarial steering do not simultaneously maximize task completion. Overall, our results show that LLM agents can exhibit limited strategic behavior, including selective trust and deception, while remaining highly vulnerable to adversarial persuasion.

Aarush Sinha, Arion Das, Soumyadeep Nag +7

University of Copenhagen · IIIT Ranchi · ISI Kolkata +6

Strategic Reasoning Risks in Language ModelsEmergent Behavior in Multi-Agent SystemsLLM Agent SafetyMulti-Agent SystemsLLM Agent TrainingLarge Language Model-Based Social Simulation
AskPDF
Apr 10, 2026

Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems

While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too complex to analyze entirely, evaluating their ethical robustness requires first isolating their foundational mechanics. In this work, we conduct a baseline empirical study investigating how basic MAS topologies and feedback loops influence prejudice. Contrary to the assumption that multi-agent collaboration naturally dilutes bias, we hypothesize that structured workflows act as echo chambers, amplifying minor stochastic biases into systemic polarization. To evaluate this, we introduce Discrim-Eval-Open, an open-ended benchmark that bypasses individual model neutrality through forced comparative judgments across demographic groups. Analyzing bias cascades across various structures reveals that architectural sophistication frequently exacerbates bias rather than mitigating it. We observe systemic amplification even when isolated agents operate neutrally, and identify a 'Trigger Vulnerability' where injecting purely objective context drastically accelerates polarization. By stripping away advanced swarm complexity to study foundational dynamics, we establish a crucial baseline: structural complexity does not guarantee ethical robustness. Our code is available at https://github.com/weizhihao1/MAS-Bias.

Keyu Li, Jin Gao, Dequan Wang

Shanghai Jiao Tong University · Shanghai Innovation Institute

Algorithmic BiasMulti-Agent SystemsEmergent Behavior in Multi-Agent SystemsMulti-Agent Collaboration
AskPDF
Apr 9, 2026

Intelligent Three Level Learning Architecture for Autonomous UAV Swarms in Search and Rescue

This paper presents a novel three level hierarchical learning architecture for autonomous UAV swarms performing search and rescue operations. Unlike conventional approaches that apply a single learning paradigm across all hierarchy levels, the proposed architecture integrates three qualitatively different learning mechanisms corresponding to the biological hierarchy of reflexes, skills, and reasoning such as Hebbian neuroplasticity for individual agent adaptation, multi agent reinforcement learning with graph neural networks and behavior trees for tactical coordination, and model agnostic meta learning with BDI reasoning and a digital twin for strategic decision making. The architecture is formalized through twenty two architectural contracts organized across six components such as BDI, Behavior Trees, GNN, MARL, Neuroplasticity, Meta Learning that collectively provide six classes of formal guarantees such as safety, budget correctness, optimality, liveness, starvation freedom, and inter level consistency. We introduce Swarm Meta Cognition as a compositional property arising from the structured interaction of all three levels, enabling the swarm to monitor its own cognitive state and switch between cognitive strategies. Five constructive progress functions for SAR task types bridge the gap between abstract optimization theory and concrete operational scenarios. The main integration theorem establishes that when all contracts are satisfied, the hybrid neuro-symbolic system preserves all six guarantee classes. For the dynamic case with active learning, five new contracts extend the framework with three additional guarantees such as cognitive resilience, graceful degradation, and monotonic meta improvement. Theoretical analysis demonstrates that the architecture addresses five fundamental limitations of existing hierarchical RL approaches.

Oleksii Bychkov

Department of Program Systems and Technologies, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine

Swarm RoboticsCognitive Architectures for AI AgentsMulti-Agent SystemsSearch-and-Rescue RoboticsMulti-Agent Reinforcement Learning
AskPDF
Apr 9, 2026

LOLGORITHM: Funny Comment Generation Agent For Short Videos

Short-form video platforms have become central to multimedia information dissemination, where comments play a critical role in driving engagement, propagation, and algorithmic feedback. However, existing approaches -- including video summarization and live-streaming danmaku generation -- fail to produce authentic comments that conform to platform-specific cultural and linguistic norms. In this paper, we present LOLGORITHM, a novel modular multi-agent framework for stylized short-form video comment generation. LOLGORITHM supports six controllable comment styles and comprises three core modules: video content summarization, video classification, and comment generation with semantic retrieval and hot meme augmentation. We further construct a bilingual dataset of 3,267 videos and 16,335 comments spanning five high-engagement categories across YouTube and Douyin. Evaluation combining automatic scoring and large-scale human preference analysis demonstrates that LOLGORITHM consistently outperforms baseline methods, achieving human preference selection rates of 80.46% on YouTube and 84.29% on Douyin across 107 respondents. Ablation studies confirm that these gains are attributable to the framework architecture rather than the choice of backbone LLM, underscoring the robustness and generalizability of our approach.

Xuan Ouyang, Bouzhou Wang, Senan Wang +3

University of New South Wales Sydney, Australia · University of Sydney Sydney, Australia · The University of Hong Kong Hong Kong, China +1

Text GenerationControllable Text GenerationMulti-Agent Systems
AskPDF