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.

Mar 25, 2026

Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing

The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic systems represent a particularly important class of operational technology, as modern robots are highly networked cyber-physical systems deployed in domains such as industrial automation, logistics, and autonomous services. This paper explores the use of large language models for automated penetration testing in robotic environments. We propose an environment-grounded multi-agent architecture tailored to Robotics-based systems. The approach dynamically constructs a shared graph-based memory during execution that captures the observable system state, including network topology, communication channels, vulnerabilities, and attempted exploits. This enables structured automation while maintaining traceability and effective context management throughout the testing process. Evaluated across multiple iterations within a specialized robotics Capture-the-Flag scenario (ROS/ROS2), the system demonstrated high reliability, successfully completing the challenge in 100% of test runs (n=5). This performance significantly exceeds literature benchmarks while maintaining the traceability and human oversight required by frameworks like the EU AI Act.

Michael Somma, Markus Großpointner, Paul Zabalegui +2

JOANNEUM RESEARCH Forschungsgesellschaft mbH, DIGITAL – Institute for Digital Technologies, Steyrergasse 17, 8010 Graz, Austria · TU Graz, Institute for Technical Informatics, Inffeldgasse 16/I, 8010 Graz, Austria · Alias Robotics S.L., Calle Venta de la Estrella, 6 Pab. 130, 01006 Vitoria-Gasteiz, Álava, Spain +1

Automated Penetration TestingLLMs for CybersecurityMulti-Agent Systems
AskPDF
Mar 24, 2026

Biased Error Attribution in Multi-Agent Human-AI Systems Under Delayed Feedback

Human decision-making is strongly influenced by cognitive biases, particularly under conditions of uncertainty and risk. While prior work has examined bias in single-step decisions with immediate outcomes and in human interaction with a single autonomous agent, comparatively little attention has been paid to decision-making under delayed outcomes involving multiple AI agents, where decisions at each step affect subsequent states. In this work, we study how delayed outcomes shape decision-making and responsibility attribution in a multi-agent human-AI task. Using a controlled game-based experiment, we analyze how participants adjust their behavior following positive and negative outcomes. We observe asymmetric responses to gains and losses, with stronger corrective adjustments after negative outcomes. Importantly, participants often fail to correctly identify the actions that caused failure and misattribute responsibility across AI agents, leading to systematic revisions of decisions that are weakly related to the underlying causes of poor performance. We refer to this phenomenon as a form of attribution bias, manifested as biased error attribution under delayed feedback. Our findings highlight how cognitive biases can be amplified in human-AI systems with delayed outcomes and multiple autonomous agents, underscoring the need for decision-support systems that better support causal understanding and learning over time.

Teerthaa Parakh, Karen M. Feigh

Georgia Institute of Technology, Atlanta, GA, USA

Human-AI Decision MakingCausal AttributionAI AccountabilityMulti-Agent Systems
AskPDF
Mar 24, 2026

Beyond Preset Identities: Selective Stance Accommodation and Interaction Reorganisation in Generative Agent Societies

Generative agent societies simulate people with assigned roles, preferences and relationships. As agents exchange arguments and choose partners, they can revise their positions and reorganise discussion. Understanding these changes requires examining what they accept and how they continue to interact. Stance-change scores and communication totals describe the extent of change. However, the same stance movement can preserve or reverse an assigned preference, and frequent communication can support either agreement or continuing disagreement. We therefore examine the content of changed positions and the exchanges that strengthen particular partnerships. Using Computational Multi-Agent Society Experiments (CMASE), we combine stance measures, source evaluations and temporal networks with individual answers and messages. Study 1 compares seven conditions across ten GPT-4o runs per condition, with a separate interview collection covering four models. Study 2 follows one 75-step GPT-4o café simulation. Environmental rational persuasion yields the largest mean stance departure (1.30±0.081.30\pm0.08 on a 7-point scale), whereas economic emotional persuasion yields the highest low-trust stance-shift rate (17.3%±11.2%17.3\%\pm11.2\%, with standard deviations across runs). In the separate interviews, eight environmental agents shift from 7 to 6, acknowledge economic concerns and rate the source 3. Their partial acceptance preserves the assigned environmental preference. In the café, a pair with zero earlier exchanges becomes the most frequent final-phase partnership, with 25 messages. Its members develop coordination proposals while disputing their implementation. These results show that partial acceptance can coexist with low source trust, and sustained coordination with continuing disagreement.

Hanzhong Zhang, Siyang Song, Lu Liu +1

Department of Computer Science, University of Exeter, Exeter, United Kingdom · Department of Data Science, William & Mary, Williamsburg, Virginia, United States

Large Language Model-Based Social SimulationMulti-Agent CommunicationMulti-Agent SystemsOpinion DynamicsComputational Social Science
AskPDF
Mar 24, 2026

ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization

How should multi-agent systems be designed, and can that design knowledge be captured in a form that is inspectable, revisable, and transferable? We introduce ABSTRAL, a framework that treats MAS architecture as an evolving natural-language document, an artifact refined through contrastive trace analysis. Three findings emerge. First, we provide a precise measurement of the multi-agent coordination tax: under fixed turn budgets, ensembles achieve only 26% turn efficiency, with 66% of tasks exhausting the limit, yet still improve over single-agent baselines by discovering parallelizable task decompositions. Second, design knowledge encoded in documents transfers: topology reasoning and role templates learned on one domain provide a head start on new domains, with transferred seeds matching coldstart iteration 3 performance in a single iteration. Third, contrastive trace analysis discovers specialist roles absent from any initial design, a capability no prior system demonstrates. On SOPBench (134 bank tasks, deterministic oracle), ABSTRAL reaches 70% validation / 65.96% test pass rate with a GPT-4o backbone. We release the converged documents as inspectable design rationale.

Weijia Song, Jiashu Yue, Zhe Pang

Multi-Agent SystemsMulti-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent Coordination
AskPDF
Mar 23, 2026

EviSearch: Trustworthy Extraction and Synthesis of Clinical Trial Evidence with Agents that Improve with Use

Structured extraction of evidence from clinical trial publications underpins systematic reviews and clinical guidelines, yet large language models are adopted for it only hesitantly: their outputs are difficult to verify, their use commonly requires transmitting documents to proprietary services, and they do not improve from the corrections their users make. We present EviSearch, a multi-agent system that addresses these three obstacles. Three tool-augmented agents with complementary access to a publication extract every column of an evidence table, and a value is admitted only after an attribution verifier has read it on its cited page, so that every value carries a page-level attribution. Disagreement between independent agents directs human review to the cells most likely to be wrong, and reviewer feedback refines the schema definitions and a curation knowledge base without updating model parameters. The agentic system runs entirely offline on open-weight models. On a clinician-annotated benchmark of randomized-trial publications, EviSearch attributes 100.0% of its values, reaches 91.70% accuracy autonomously, and reaches 95.22% after review of 15.6% of cells, exceeding random review of the strongest single agent at equal effort by 1.75 points.

Naman Ahuja, Abhijit Chakraborty, Muhammad Ali Khan +4

Arizona State University · Mayo Clinic

Systematic Review AutomationAI-Assisted Scientific ResearchHuman-in-the-Loop AIClinical Information ExtractionMulti-Agent Systems
AskPDF
Mar 23, 2026

Modal Logic for Distributed Trust

We propose a method for reasoning about trust in multi-agent systems, specifying a language for describing communication protocols and making trust assumptions and derivations. This is given an interpretation in a modal logic for describing the beliefs and communications of agents in a network. We define how information in the network can be shared via forwarding, and how trust between agents can be generalized to trust across networks. We give specifications for the modal logic which can be readily adapted into a lambda calculus of proofs. We show that by nesting modalities, we can describe chains of communication between agents, and establish suitable notions of trust for such chains. We see how this can be applied to trust models in public key infrastructures, as well as other interaction protocols in distributed systems.

Niels Voorneveld, Peeter Laud

Cybernetica AS

Multi-Agent SystemsMulti-Agent Communication
AskPDF
Mar 23, 2026

Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation

Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration capabilities. As these systems become more complex and autonomous, effective failure management is essential to ensure reliability and availability. However, existing approaches often rely on per-trace reasoning, which leads to low efficiency, and neglect historical failure patterns, limiting diagnostic accuracy. In this paper, we conduct a preliminary empirical study to demonstrate the necessity, potential, and challenges of leveraging historical failure patterns to enhance failure management in MASs. Building on this insight, we propose EAGER, an efficient failure management framework for multi-agent systems based on reasoning trace representation. EAGER employs unsupervised reasoning-scoped contrastive learning to encode both intra-agent reasoning and inter-agent coordination, enabling real-time step-wise failure detection, diagnosis, and reflexive mitigation guided by historical failure knowledge. Preliminary evaluations on three open-source MASs demonstrate the effectiveness of EAGER and highlight promising directions for future research in reliable multi-agent system operations.

Lingzhe Zhang, Tong Jia, Mingyu Wang +9

Peking University Beijing, China · Huawei Technologies Co., Ltd. Beijing, China · Huawei Technologies Co., Ltd. Hong Kong SAR, China +1

Agent Failure AnalysisMulti-Agent LLM SystemsMulti-Agent Systems
AskPDF
Mar 23, 2026

Agentic Automation of BT-RADS Scoring: End-to-End Multi-Agent System for Standardized Brain Tumor Follow-up Assessment

The Brain Tumor Reporting and Data System (BT-RADS) standardizes post-treatment MRI response assessment in patients with diffuse gliomas but requires complex integration of imaging trends, medication effects, and radiation timing. This study evaluates an end-to-end multi-agent large language model (LLM) and convolutional neural network (CNN) system for automated BT-RADS classification. A multi-agent LLM system combined with automated CNN-based tumor segmentation was retrospectively evaluated on 509 consecutive post-treatment glioma MRI examinations from a single high-volume center. An extractor agent identified clinical variables (steroid status, bevacizumab status, radiation date) from unstructured clinical notes, while a scorer agent applied BT-RADS decision logic integrating extracted variables with volumetric measurements. Expert reference standard classifications were established by an independent board-certified neuroradiologist. Of 509 examinations, 492 met inclusion criteria. The system achieved 374/492 (76.0%; 95% CI, 72.1%-79.6%) accuracy versus 283/492 (57.5%; 95% CI, 53.1%-61.8%) for initial clinical assessments (+18.5 percentage points; P<.001). Context-dependent categories showed high sensitivity (BT-1b 100%, BT-1a 92.7%, BT-3a 87.5%), while threshold-dependent categories showed moderate sensitivity (BT-3c 74.8%, BT-2 69.2%, BT-4 69.3%, BT-3b 57.1%). For BT-4, positive predictive value was 92.9%. The multi-agent LLM system achieved higher BT-RADS classification agreement with expert reference standard compared to initial clinical scoring, with high accuracy for context-dependent scores and high positive predictive value for BT-4 detection.

Mohamed Sobhi Jabal, Jikai Zhang, Dominic LaBella +6

Department of Radiology, Duke University Medical Center, Durham, NC · Department of Electrical and Computer Engineering, Duke University, Durham, NC · Duke Center for Artificial Intelligence in Radiology, Duke University Medical Center, Durham, NC +5

Brain Tumor ClassificationMulti-Agent Systems
AskPDF
Mar 23, 2026

Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems

Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general nodes like Chain-of-Thought, which lack specialized expertise, or attempt to generate nodes on the fly. In the latter case, the orchestrator is not only bound by its internal knowledge limits but must also simultaneously generate domain-specific logic and optimize high-level topology, leading to a severe architectural coupling that degrades overall system efficacy. To bridge this gap, we propose Unified-MAS that decouples granular node implementation from topological orchestration via offline node synthesis. Unified-MAS operates in two stages: (1) Search-Based Node Generation retrieves external open-world knowledge to synthesize specialized node blueprints, overcoming the internal knowledge limits of LLMs; and (2) Reward-Based Node Optimization utilizes a perplexity-guided reward to iteratively enhance the internal logic of bottleneck nodes. Extensive experiments across four specialized domains demonstrate that integrating Unified-MAS into four Automatic-MAS baselines yields a better performance-cost trade-off, achieving up to a 14.2% gain while significantly reducing costs. Further analysis reveals its robustness across different designer LLMs and its effectiveness on conventional tasks such as mathematical reasoning.

Hehai Lin, Yu Yan, Zixuan Wang +6

The Hong Kong University of Science and Technology (Guangzhou) · Nanyang Technological University · National University of Singapore +1

Multi-Agent OrchestrationMulti-Agent SystemsMulti-Agent Reasoning
AskPDF
Mar 22, 2026

The AI Scientific Community: Agentic Virtual Lab Swarms

In this short note we propose using agentic swarms of virtual labs as a model of an AI Science Community. In this paradigm, each particle in the swarm represents a complete virtual laboratory instance, enabling collective scientific exploration that mirrors real-world research communities. The framework leverages the inherent properties of swarm intelligence - decentralized coordination, balanced exploration-exploitation trade-offs, and emergent collective behavior - to simulate the behavior of a scientific community and potentially accelerate scientific discovery. We discuss architectural considerations, inter-laboratory communication and influence mechanisms including citation-analogous voting systems, fitness function design for quantifying scientific success, anticipated emergent behaviors, mechanisms for preventing lab dominance and preserving diversity, and computational efficiency strategies to enable large swarms exhibiting complex emergent behavior analogous to real-world scientific communities. A working instance of the AI Science Community is currently under development.

Ulisses Braga-Neto

Department of Electrical and Computer Engineering, Texas A&M University

AI for ScienceAutonomous Scientific DiscoveryMulti-Agent SystemsAgent-Based Modeling
AskPDF
Mar 21, 2026

Governance-Aware Vector Subscriptions for Multi-Agent Knowledge Ecosystems

As AI agent ecosystems grow, agents need mechanisms to monitor relevant knowledge in real time. Semantic publish-subscribe systems address this by matching new content against vector subscriptions. However, in multi-agent settings where agents operate under different data handling policies, unrestricted semantic subscriptions create policy violations: agents receive notifications about content they are not authorized to access. We introduce governance-aware vector subscriptions, a mechanism that composes semantic similarity matching with multi-dimensional policy predicates grounded in regulatory frameworks (EU DSM Directive, EU AI Act). The policy predicate operates over multiple independent dimensions (processing level, direct marketing restrictions, training opt-out, jurisdiction, and scientific usage) each with distinct legal bases. Agents subscribe to semantic regions of a curated knowledge base; notifications are dispatched only for validated content that passes both the similarity threshold and all applicable policy constraints. We formalize the mechanism, implement it within AIngram (an operational multi-agent knowledge base), and evaluate it using the PASA benchmark. We validate the mechanism on a synthetic corpus (1,000 chunks, 93 subscriptions, 5 domains): the governed mode correctly enforces all policy constraints while preserving delivery of authorized content. Ablation across five policy dimensions shows that no single dimension suffices for full compliance.

Steven Johnson

Independent Researcher

AI Agent GovernanceMulti-Agent Systems
AskPDF
Mar 21, 2026

Agentic Physical-AI for Self-Aware RF Systems

Intelligent control of RF transceivers adapting to dynamic operational conditions is essential in the modern and future communication systems. We propose a multi-agent neurosymbolic AI system, where AI agents are assigned for circuit components. Agents have an internal model and a corresponding control algorithm as its constituents. Modeling of the IF amplifier shows promising results, where the same approach can be extended to all the components, thus creating a fully intelligent RF system.

Linuka Ratnayake, Danidu Dabare, Sanuja Rupasinghe +4

University of Moratuwa, Moratuwa, Sri Lanka · University of Oulu, Oulu, Finland · Florida International University, Miami, FL, USA

Adaptive ControlMulti-Agent ControlNeuro-Symbolic AIMulti-Agent Systems
AskPDF
Mar 21, 2026

Towards Intelligent Geospatial Data Discovery: a knowledge graph-driven multi-agent framework powered by large language models

The rapid growth in the volume, variety, and velocity of geospatial data has created data ecosystems that are highly distributed, heterogeneous, and semantically inconsistent. Existing data catalogs, portals, and infrastructures still rely largely on keyword-based search with limited semantic support, which often fails to capture user intent and leads to weak retrieval performance. To address these challenges, this study proposes a knowledge graph-driven multi-agent framework for intelligent geospatial data discovery, powered by large language models. The framework introduces a unified geospatial metadata ontology as a semantic mediation layer to align heterogeneous metadata standards across platforms and constructs a geospatial metadata knowledge graph to explicitly model datasets and their multidimensional relationships. Building on the structured representation, the framework adopts a multi-agent collaborative architecture to perform intent parsing, knowledge graph retrieval, and answer synthesis, forming an interpretable and closed-loop discovery process from user queries to results. Results from representative use cases and performance evaluation show that the framework substantially improves intent matching accuracy, ranking quality, recall, and discovery transparency compared with traditional systems. This study advances geospatial data discovery toward a more semantic, intent-aware, and intelligent paradigm, providing a practical foundation for next-generation intelligent and autonomous spatial data infrastructures and contributing to the broader vision of Autonomous GIS.

Ruixiang Liu, Zhenlong Li, Ali Khosravi Kazazi

Geoinformation and Big Data Research Laboratory, Department of Geography, The Pennsylvania State University, University Park, PA, USA

Graph-Based RetrievalLLM AgentsMulti-Agent Systems
AskPDF
Mar 21, 2026

ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework

Instruction-based image editing has emerged as a key capability for unified multimodal models (UMMs), yet constructing large-scale, diverse, and high-quality editing datasets without costly proprietary APIs remains challenging. Previous image editing datasets either rely on closed-source models for annotation, which prevents cost-effective scaling, or employ fixed synthetic editing pipelines, which suffer from limited quality and generalizability. To address these challenges, we propose ScaleEditor, a fully open-source hierarchical multi-agent framework for end-to-end construction of large-scale, high-quality image editing datasets. Our pipeline consists of three key components: source image expansion with world-knowledge infusion, adaptive multi-agent editing instruction-image synthesis, and a task-aware data quality verification mechanism. Using ScaleEditor, we curate ScaleEdit-12M, the largest open-source image editing dataset to date, spanning 23 task families across diverse real and synthetic domains. Fine-tuning UniWorld-V1 and Bagel on ScaleEdit yields consistent gains, improving performance by up to 10.4% on ImgEdit and 35.1% on GEdit for general editing benchmarks and by up to 150.0% on RISE and 26.5% on KRIS-Bench for knowledge-infused benchmarks. These results demonstrate that open-source, agentic pipelines can approach commercial-grade data quality while retaining cost-effectiveness and scalability. Both the framework and dataset will be open-sourced.

Guanzhou Chen, Erfei Cui, Changyao Tian +6

Shanghai Jiao Tong University · Shanghai AI Laboratory · CUHK MMLab +3

Synthetic Data AugmentationText-Guided Image EditingMulti-Agent Systems
AskPDF
Mar 21, 2026

Position: Multi-Agent Algorithmic Care Systems Demand Contestability for Trustworthy AI

Multi-agent systems (MAS) are increasingly used in healthcare to support complex decision-making through collaboration among specialized agents. Because these systems act as collective decision-makers, they raise challenges for trust, accountability, and human oversight. Existing approaches to trustworthy AI largely rely on explainability, but explainability alone is insufficient in multi-agent settings, as it does not enable care partners to challenge or correct system outputs. To address this limitation, Contestable AI (CAI) characterizes systems that support effective human challenge throughout the decision-making lifecycle by providing transparency, structured opportunities for intervention, and mechanisms for review, correction, or override. This position paper argues that contestability is a necessary design requirement for trustworthy multi-agent algorithmic care systems. We identify key limitations in current MAS and Explainable AI (XAI) research and present a human-in-the-loop framework that integrates structured argumentation and role-based contestation to preserve human agency, clinical responsibility, and trust in high-stakes care contexts.

Truong Thanh Hung Nguyen, Hélène Fournier, Piper Jackson +4

Analytics Everywhere Lab, University of New Brunswick, Canada · National Research Council Canada, Canada · Thompson Rivers University, Canada +2

Multi-Agent SystemsAlgorithmic AccountabilityHealthcare
AskPDF
Mar 20, 2026

Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams

Industry practitioners and academic researchers regularly use multi-agent systems to accelerate their work, but the applications through which users operate these systems do not provide a simple, unified mechanism for scalably managing critical components of the agent harness. This lack of control adversely impacts both the quality of individual human-agent interactions and reduces the capacity for practitioners to coordinate context engineering efforts. The behavioral specifications that define what agents in such systems can do remain fragmented across prose instruction files -- for which compliance cannot be guaranteed -- or framework-internal configurations, making these specifications difficult to share, version, or collaboratively maintain across teams and projects. Applying the ALARA principle from radiation safety (exposures kept as low as reasonably achievable) to context, we introduce a context-agent-tool (CAT) data layer expressed through interrelated plain-text files, allowing users to directly declare tool access for each agent and to modify the tools themselves that are used by the agents when processing. We demonstrate capability of this CAT data layer to enable real agentic usage by using a command-line shell that loads the team and executes agent runs -- npcsh -- and evaluating 22 locally-hosted models from 0.6B to 35B parameters across 115 practical tasks spanning file operations, web search, multi-step scripting, tool chaining, and multi-agent delegation. We characterize which model families succeed in certain task categories and where they break down across ∼\sim2500 total executions.

Christopher J. Agostino, Nayan D'Souza

NPC Worldwide, Bloomington, IN, USA · Celeria, Inc., Bloomington, IN, USA · Department of Linguistics, Indiana University, Bloomington, IN, USA

LLM Agent HarnessesMulti-Agent SystemsTool Access Control for LLM AgentsLLM Agent Evaluation
AskPDF
Mar 19, 2026

Graph-of-Constraints Model Predictive Control for Reactive Multi-agent Task and Motion Planning

Sequences of interdependent geometric constraints are central to many multi-agent Task and Motion Planning (TAMP) problems. However, existing methods for handling such constraint sequences struggle with partially ordered tasks and dynamic agent assignments. They typically assume static assignments and cannot adapt when disturbances alter task allocations. To overcome these limitations, we introduce Graph-of-Constraints Model Predictive Control (GoC-MPC), a generalized sequence-of-constraints framework integrated with MPC. GoC-MPC naturally supports partially ordered tasks, dynamic agent coordination, and disturbance recovery. By defining constraints over tracked 3D keypoints, our method robustly solves diverse multi-agent manipulation tasks-coordinating agents and adapting online from visual observations alone, without relying on training data or environment models. Experiments demonstrate that GoC-MPC achieves higher success rates, significantly faster TAMP computation, and shorter overall paths compared to recent baselines, establishing it as an efficient and robust solution for multi-agent manipulation under real-world disturbances. Our supplementary video and code can be found at https://sites.google.com/view/goc-mpc/home .

Anastasios Manganaris, Jeremy Lu, Ahmed H. Qureshi +1

Department of Computer Science, Purdue University, West Lafayette, IN, USA, 47907.

Multi-Agent PlanningConstrained Motion PlanningMulti-Agent SystemsMulti-Robot CoordinationModel Predictive Control
AskPDF
Mar 19, 2026

Soft-Label Governance for Distributional Safety in Multi-Agent Systems

Multi-agent AI systems exhibit emergent risks that no single agent produces in isolation. Existing safety frameworks rely on binary classifications of agent behavior, discarding the uncertainty inherent in proxy-based evaluation. We introduce SWARM (System-Wide Assessment of Risk in Multi-agent systems), a simulation framework that replaces binary good/bad labels with soft probabilistic labels p=P(v=+1)∈[0,1]p = P(v{=}+1) \in [0,1], enabling continuous-valued payoff computation, toxicity measurement, and governance intervention. SWARM implements a modular governance engine with configurable levers (transaction taxes, circuit breakers, reputation decay, and random audits) and quantifies their effects through probabilistic metrics including expected toxicity E[1−p∣accepted]\mathbb{E}[1{-}p \mid \text{accepted}] and quality gap E[p∣accepted]−E[p∣rejected]\mathbb{E}[p \mid \text{accepted}] - \mathbb{E}[p \mid \text{rejected}]. Across seven scenarios with five-seed replication, strict governance reduces welfare by over 40% without improving safety. In parallel, aggressively internalizing system externalities collapses total welfare from a baseline of +262+262 down to −67-67, while toxicity remains invariant. Circuit breakers require careful calibration; overly restrictive thresholds severely diminish system value, whereas an optimal threshold balances moderate welfare with minimized toxicity. Companion experiments show soft metrics detect proxy gaming by self-optimizing agents passing conventional binary evaluations. This basic governance layer applies to live LLM-backed agents (Concordia entities, Claude, GPT-4o Mini) without modification. Results show distributional safety requires continuous risk metrics and governance lever calibration involves quantifiable safety-welfare tradeoffs. Source code and project resources are publicly available at https://www.swarm-ai.org/.

Aizierjiang Aiersilan, Raeli Savitt

SWARM AI Safety, New York, USA

AI Agent GovernanceAI Risk ManagementMulti-Agent SystemsAI Safety Evaluation
AskPDF
Mar 18, 2026

In Trust We Survive: Emergent Trust Learning

We introduce Emergent Trust Learning (ETL), a lightweight, trust-based control algorithm that can be plugged into existing AI agents. It enables these to reach cooperation in competitive game environments under shared resources. Each agent maintains a compact internal trust state, which modulates memory, exploration, and action selection. ETL requires only individual rewards and local observations and incurs negligible computational and communication overhead. We evaluate ETL in three environments: In a grid-based resource world, trust-based agents reduce conflicts and prevent long-term resource depletion while achieving competitive individual returns. In a hierarchical Tower environment with strong social dilemmas and randomised floor assignments, ETL sustains high survival rates and recovers cooperation even after extended phases of enforced greed. In the Iterated Prisoner's Dilemma, the algorithm generalises to a strategic meta-game, maintaining cooperation with reciprocal opponents while avoiding long-term exploitation by defectors. Code will be released upon publication.

Qianpu Chen, Giulio Barbero, Mike Preuss +1

LIACS, Leiden Institute of Advanced Computer Science, Universiteit Leiden, The Netherlands

Multi-Agent CoordinationMulti-Agent SystemsCooperative MARLEmergent Behavior in Multi-Agent SystemsSocial Dilemmas
AskPDF
Mar 17, 2026

DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis

Aspect-Based Sentiment Intensity Analysis (ABSIA) has garnered increasing attention, though research largely focuses on domain-specific, sentence-level settings. In contrast, document-level ABSIA--particularly in addressing complex tasks like extracting Aspect-Category-Opinion-Sentiment-Intensity (ACOSI) tuples--remains underexplored. In this work, we introduce DanceHA, a multi-agent framework designed for open-ended, document-level ABSIA with informal writing styles. DanceHA has two main components: Dance, which employs a divide-and-conquer strategy to decompose the long-context ABSIA task into smaller, manageable sub-tasks for collaboration among specialized agents; and HA, Human-AI collaboration for annotation. We release Inf-ABSIA, a multi-domain document-level ABSIA dataset featuring fine-grained and high-accuracy labels from DanceHA. Extensive experiments demonstrate the effectiveness of our agentic framework and show that the multi-agent knowledge in DanceHA can be effectively transferred into student models. Our results highlight the importance of the overlooked informal styles in ABSIA, as they often intensify opinions tied to specific aspects.

Lei Wang, Min Huang, Eduard Dragut

Temple University, Philadelphia, PA, USA · Independent Researcher, Philadelphia, PA, USA

Aspect-Based Sentiment AnalysisMulti-Agent Systems
AskPDF
Mar 17, 2026

Adaptive Theory of Mind for LLM-based Multi-Agent Coordination

Theory of Mind (ToM) refers to the ability to reason about others' mental states, and higher-order ToM involves considering that others also possess their own ToM. Equipping large language model (LLM)-driven agents with ToM has long been considered to improve their coordination in multiagent collaborative tasks. However, we find that misaligned ToM orders-mismatches in the depth of ToM reasoning between agents-can lead to insufficient or excessive reasoning about others, thereby impairing their coordination. To address this issue, we design an adaptive ToM (A-ToM) agent, which can align in ToM orders with its partner. Based on prior interactions, the agent estimates the partner's likely ToM order and leverages this estimation to predict the partner's action, thereby facilitating behavioral coordination. We conduct empirical evaluations on four multi-agent coordination tasks: a repeated matrix game, two grid navigation tasks and an Overcooked task. The results validate our findings on ToM alignment and demonstrate the effectiveness of our A-ToM agent. Furthermore, we discuss the generalizability of our A-ToM to non-LLM-based agents, as well as what would diminish the importance of ToM alignment.

Chunjiang Mu, Ya Zeng, Qiaosheng Zhang +6

School of Cybersecurity, Northwestern Polytechnical University · Shanghai Artificial Intelligence Laboratory · Huawei Noah’s Ark Lab +2

Multi-Agent CoordinationMulti-Agent SystemsMulti-Agent LLMsMulti-Agent Reasoning
AskPDF
Mar 17, 2026

CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation

Ensuring robust and fair interview assessment remains a key challenge in AI-driven evaluation. This paper presents CoMAI, a general-purpose multi-agent interview framework designed for diverse assessment scenarios. In contrast to monolithic single-agent systems based on large language models (LLMs), CoMAI employs a modular task-decomposition architecture coordinated through a centralized finite-state machine. The system comprises four agents specialized in question generation, security, scoring, and summarization. These agents work collaboratively to provide multi-layered security defenses against prompt injection, support multidimensional evaluation with adaptive difficulty adjustment, and enable rubric-based structured scoring that reduces subjective bias. Experimental results demonstrate that CoMAI achieved 90.47% accuracy, 83.33% recall, and 84.41% candidate satisfaction. These results highlight CoMAI as a robust, fair, and interpretable paradigm for AI-driven interview assessment.

Gengxin Sun, Ruihao Yu, Liangyi Yin +3

Shandong University, Qingdao, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · Shandong University, Jinan, China

Automated EvaluationMulti-Agent SystemsAI Agent Evaluation
AskPDF
Mar 17, 2026

RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review

Repository-level code review requires reasoning over project structure, repository context, and file-level implementation details. Existing automated review workflows often collapse these tasks into a single pass, which can reduce relevance, increase duplication, and weaken prioritization. We present RepoReviewer, a local-first multi-agent system for automated GitHub repository review with a Python CLI, FastAPI API, LangGraph orchestration layer, and Next.js user interface. RepoReviewer decomposes review into repository acquisition, context synthesis, file-level analysis, finding prioritization, and summary generation. We describe the system design, implementation tradeoffs, developer-facing interfaces, and practical failure modes. Rather than claiming benchmark superiority, we frame RepoReviewer as a technical systems contribution: a pragmatic architecture for repository-level automated review, accompanied by reusable evaluation and reporting infrastructure for future empirical study.

Peng Zhang

Automated Code ReviewSoftware Engineering AgentsSoftware Architecture DesignMulti-Agent Systems
AskPDF
Mar 16, 2026

From Workflow Automation to Capability Closure: A Formal Framework for Safe and Revenue-Aware Customer Service AI

Customer service automation is undergoing a structural transformation. The dominant paradigm is shifting from scripted chatbots and single-agent responders toward networks of specialised AI agents that compose capabilities dynamically across billing, service provision, payments, and fulfilment. This shift introduces a safety gap that no current platform has closed: two agents individually verified as safe can, when combined, reach a forbidden goal through an emergent conjunctive dependency that neither possesses alone.

Cosimo Spera

Minerva CQ, 114 Lester Ln, Los Gatos, CA 95032

AI Agent SafetyCustomer Support AutomationAgentic WorkflowsMulti-Agent SystemsFormal Verification
AskPDF
Mar 16, 2026

Safety is Non-Compositional: A Formal Framework for Capability-Based AI Systems

This paper contains the first formal proof that safety is non-compositional in the presence of conjunctive capability dependencies: two agents each individually inca- pable of reaching any forbidden capability can, when combined, collectively reach a forbidden goal through an emergent conjunctive dependency.

Cosimo Spera

Minerva CQ, Los Gatos, CA 95032

AI Agent SafetyCapability-Based SecurityMulti-Agent SystemsEmergent Behavior in Multi-Agent Systems
AskPDF
Mar 16, 2026

AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems

As multi-agent AI systems are increasingly deployed in real-world settings - from automated customer support to DevOps remediation - failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution traces. We present AgentTrace, a lightweight causal tracing framework for post-hoc failure diagnosis in deployed multi-agent workflows. AgentTrace reconstructs causal graphs from execution logs, traces backward from error manifestations, and ranks candidate root causes using interpretable structural and positional signals - without requiring LLM inference at debugging time. Across a diverse benchmark of multi-agent failure scenarios designed to reflect common deployment patterns, AgentTrace localizes root causes with high accuracy and sub-second latency, significantly outperforming both heuristic and LLM-based baselines. Our results suggest that causal tracing provides a practical foundation for improving the reliability and trustworthiness of agentic systems in the wild.

Zhaohui Geoffrey Wang

USC Viterbi School of Engineering

Agent Failure AnalysisAI Agent ReliabilityMulti-Agent SystemsCausal Interpretability
AskPDF
Mar 14, 2026

ClimateAgents: A Multi-Agent Research Assistant for Social-Climate Dynamics Analysis

The complex interaction between social behaviors and climate change requires more than traditional data-driven prediction; it demands interpretable and adaptive analytical frameworks capable of integrating heterogeneous sources of knowledge. This study introduces ClimateAgents, a multi-agent research assistant designed to support social-climate analysis through coordinated AI agents. Rather than focusing solely on predictive modeling, the framework assists researchers in exploring socio-environmental dynamics by integrating multimodal data retrieval, statistical modeling, textual analysis, and automated reasoning. Traditional approaches to climate analysis often address narrowly defined indicators and lack the flexibility to incorporate cross-domain socio-economic knowledge or adapt to evolving research questions. To address these limitations, ClimateAgents employs a set of collaborative, domain-specialized agents that collectively perform key stages of the research workflow, including hypothesis generation, data analysis, evidence retrieval, and structured reporting. The framework supports exploratory analysis and scenario investigation using datasets from sources such as the United Nations and the World Bank. By combining agent-based reasoning with quantitative analysis of socio-economic behavioral dynamics, ClimateAgents enables adaptive and interpretable exploration of relationships between climate indicators, social variables, and environmental outcomes. The results illustrate how multi-agent AI systems can augment analytical reasoning and facilitate interdisciplinary, data-driven investigation of complex socio-environmental systems.

Shan Shan

Autonomous Research AgentsData Analysis AgentsMulti-Agent SystemsComputational Social Science
AskPDF
Mar 13, 2026

LLM Constitutional Multi-Agent Governance

Large Language Models (LLMs) can generate persuasive influence strategies that shift cooperative behavior in multi-agent populations, but a critical question remains: does the resulting cooperation reflect genuine prosocial alignment, or does it mask erosion of agent autonomy, epistemic integrity, and distributional fairness? We introduce Constitutional Multi-Agent Governance (CMAG), a two-stage framework that interposes between an LLM policy compiler and a networked agent population, combining hard constraint filtering with soft penalized-utility optimization that balances cooperation potential against manipulation risk and autonomy pressure. We propose the Ethical Cooperation Score (ECS), a multiplicative composite of cooperation, autonomy, integrity, and fairness that penalizes cooperation achieved through manipulative means. In experiments on scale-free networks of 80 agents under adversarial conditions (70% violating candidates), we benchmark three regimes: full CMAG, naive filtering, and unconstrained optimization. While unconstrained optimization achieves the highest raw cooperation (0.873), it yields the lowest ECS (0.645) due to severe autonomy erosion (0.867) and fairness degradation (0.888). CMAG attains an ECS of 0.741, a 14.9% improvement, while preserving autonomy at 0.985 and integrity at 0.995, with only modest cooperation reduction to 0.770. The naive ablation (ECS = 0.733) confirms that hard constraints alone are insufficient. Pareto analysis shows CMAG dominates the cooperation-autonomy trade-off space, and governance reduces hub-periphery exposure disparities by over 60%. These findings establish that cooperation is not inherently desirable without governance: constitutional constraints are necessary to ensure that LLM-mediated influence produces ethically stable outcomes rather than manipulative equilibria.

J. de Curtò, I. de Zarzà

Department of Computer Applications in Science & Engineering, BARCELONA Supercomputing Center, 08034 Barcelona, Spain · Escuela Técnica Superior de Ingeniería (ICAI), Universidad Pontificia Comillas, 28015 Madrid, Spain · Human Centered AI, Data & Software, LUXEMBOURG Institute of Science and Technology, L-4362 Esch-sur-Alzette, Luxembourg

AI Agent GovernanceMulti-Agent SystemsMulti-Agent CollaborationMulti-Agent Coordination
AskPDF
Mar 13, 2026

coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation

Text-to-image generation has advanced rapidly, but existing models still struggle with faithfully composing multiple objects and preserving their attributes in complex scenes. We propose coDrawAgents, an interactive multi-agent dialogue framework with four specialized agents: Interpreter, Planner, Checker, and Painter that collaborate to improve compositional generation. The Interpreter adaptively decides between a direct text-to-image pathway and a layout-aware multi-agent process. In the layout-aware mode, it parses the prompt into attribute-rich object descriptors, ranks them by semantic salience, and groups objects with the same semantic priority level for joint generation. Guided by the Interpreter, the Planner adopts a divide-and-conquer strategy, incrementally proposing layouts for objects with the same semantic priority level while grounding decisions in the evolving visual context of the canvas. The Checker introduces an explicit error-correction mechanism by validating spatial consistency and attribute alignment, and refining layouts before they are rendered. Finally, the Painter synthesizes the image step by step, incorporating newly planned objects into the canvas to provide richer context for subsequent iterations. Together, these agents address three key challenges: reducing layout complexity, grounding planning in visual context, and enabling explicit error correction. Extensive experiments on benchmarks GenEval and DPG-Bench demonstrate that coDrawAgents substantially improves text-image alignment, spatial accuracy, and attribute binding compared to existing methods.

Chunhan Li, Qifeng Wu, Jia-Hui Pan +7

Lingnan University. · China University of Petroleum · CMU +4

Layout-Guided T2I GenerationT2I GenerationCompositional T2I GenerationAgentic Image GenerationMulti-Agent Systems
AskPDF
Mar 12, 2026

Increasing intelligence in AI agents can worsen collective outcomes

When resources are scarce, will a population of AI agents coordinate in harmony, or descend into tribal chaos? Diverse decision-making AI from different developers is entering everyday devices -- from phones and medical devices to battlefield drones and cars -- and these AI agents typically compete for finite shared resources such as charging slots, relay bandwidth, and traffic priority. Yet their collective dynamics and hence risks to users and society are poorly understood. Here we study AI-agent populations as the first system of real agents in which four key variables governing collective behaviour can be independently toggled: nature (innate LLM diversity), nurture (individual reinforcement learning), culture (emergent tribe formation), and resource scarcity. We show empirically and mathematically that when resources are scarce, AI model diversity and reinforcement learning increase dangerous system overload, though tribe formation lessens this risk. Meanwhile, some individuals profit handsomely. When resources are abundant, the same ingredients drive overload to near zero, though tribe formation makes the overload slightly worse. The crossover is arithmetical: it is where opposing tribes that form spontaneously first fit inside the available capacity. More sophisticated AI-agent populations are not better: whether their sophistication helps or harms depends entirely on a single number -- the capacity-to-population ratio -- that is knowable before any AI-agent ships.

Neil F. Johnson

Dynamic Online Networks Laboratory and Physics Department, George Washington University, Washington D.C. 20052, USA

Multi-Agent Resource AllocationMulti-Agent CoordinationMulti-Agent SystemsEmergent Behavior in Multi-Agent SystemsAgent-Based Modeling
AskPDF