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

677 papers99 papers in the last four weeks, up 29% on the four weeks before. 0.6% of all new papers.

Aug 22, 2026

HiMA-MDD: A Hierarchical Multi-Agent Harness for Interpretable Multimodal Depression Detection in Clinical Interviews

Depression assessment from multimodal clinical interviews requires integrating dispersed evidence from multiple symptoms into a coherent PHQ-8 profile. This process is hierarchical: relevant evidence is often sparse and context-dependent within local question-answer exchanges, multiple exchanges jointly support symptom-level judgments, and the final assessment depends on the coherence of the complete symptom profile. Existing LLM systems either process interviews holistically or distribute work across generic agent roles; neither design necessarily provides an explicit orchestration mechanism that coordinates evidence access, item-score authority, bounded feedback, and state recording across these levels. To address this gap, we introduce HiMA-MDD, a hierarchical multi-agent harness that aligns this assessment hierarchy with three agent layers. After non-agentic preprocessing constructs context-preserving multimodal QA units, Layer 1 identifies candidate QA-to-item relations and supports bounded item-grounded evidence routing. Layer 2 assigns symptom groups to operational factor specialists, with one specialist responsible for each provisional item score. Layer 3 audits the complete provisional profile, requests at most one round of targeted revision, and reconstructs the verified PHQ-8 profile. This layered design naturally yields a Hierarchical Evidence Trace, preserves all intermediate evidence, judgments, and revisions for auditability. The final item scores then deterministically produce the total score and screening decision. Using Qwen2.5-72B-Instruct as the harness backbone, our experiments on E-DAIC demonstrate that HiMA-MDD outperforms the compared state-of-the-art methods.

Ao Chen, Xiaojiang Peng

School of Artificial Intelligence, Shenzhen Technology University

Depression DetectionDepression Severity EstimationLLM Agent HarnessesMulti-Agent LLM SystemsMulti-Agent SystemsMultimodal Model Interpretability
AskPDF
Aug 20, 2026

An Evidence-Grounded Multi-Agent System for High-Level Bio-Robot Design

In this paper, a bio-robot is an engineered living or biohybrid system in which living cells perform one or more core functions, such as sensing, information processing, actuation or output. We focus on systems whose cell-based functions are programmed by genetic circuits; physical movement is optional. Designing such a system requires translating application requirements into sensing, logic or memory, output, assembly, host and containment modules, while grounding each choice in traceable parts and evidence. We present micro_biorobot_agent, an offline multi-agent system built on Qwen3.5-27B. The system combines requirement analysis, module-specific retrieval, candidate assembly, conflict checking, local repair, independent review and validation over an integrated library of 23,762 records covering biological parts, measured combinations, literature-supported relationships and actuation evidence. Deterministic output checks align the final report with the retrieved part set and correct false gaps, unsupported part mentions and source-tracking errors. On two author-developed evaluation sets of 50 queries each, the system obtains mean overall scores of 7.35 and 8.04, the highest among the seven evaluated systems; on Scenario Design it exceeds the runner-up by 2.23 points. A 50-query paired ablation shows that the source-tracking check reduces false-gap incidents from 15 to 3, an 80% reduction, and increases source accuracy by 0.75 points. This paper reports the Qwen3.5-based v1 system and evaluates high-level design reports rather than experimentally validated circuits.

Yujun Chen, Tianle Li, Jiayu Chen +1

RoboticsMulti-Agent Systems
AskPDF
Aug 18, 2026

What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation

A common multi-agent design asks agents to report confidence and lets the highest-scoring agent speak next, implicitly using one scalar both to route the conversation and to estimate uncertainty. We audit this confidence-routed broadcast protocol by separating three trace-level questions: whether it selects the right candidate (routing), whether reported confidence behaves like a probability (calibration), and whether the selected agent publicly states the answer that won the turn (commitment). Our primary study covers 4,181 gpt-oss-120b olympiad-math traces; we repeat the audit on a 2-by-2 actor-by-benchmark grid that adds gemma-4-31B-it and a biology multiple-choice benchmark. In the primary cell, confidence discriminates correct from wrong candidates (AUROC 0.72) but is strongly overconfident (79% mean stated confidence versus 52% accuracy). A cross-fitted, tier-stratified isotonic procedure reduces Expected Calibration Error from 0.278 to 0.008 on held-out candidates, but it does not recover missing discrimination: raw AUROC is only 0.537 and 0.440 in the two Gemma cells. Routing is likewise setting-dependent. Fixed routers differ by at most 1.1 percentage points on gpt-oss/math, whereas raw-confidence argmax performs 5.6 and 11.2 points below random-valid selection in the Gemma cells. Commitment is distinct again: in the primary cell, poll and spoken answers diverge in 20.4% of valid pairs, 62.4% of those revisions are fresh generations, and the unconditional correctness shift is -1.7 points; the other three cells instead range from +0.9 to +12.2 points. The transferable lesson is procedural: routing discrimination, probability calibration, and public commitment must be measured separately before raw confidence is used for deployment decisions.

Jingyan Jiang, Huihuo Zheng, Rajeev Thakur +1

Argonne National Laboratory, Lemont, IL 60439, USA

Multi-Agent DeliberationLLM Agent RoutingAI Agent AuditingMulti-Agent SystemsConfidence Estimation in Language ModelsLanguage Model Calibration
AskPDF
Aug 18, 2026

Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluation

Purpose: To develop and evaluate a locally deployed multi-agent AI system for radiology report structuring and quality assurance. Materials and Methods: This retrospective study included 638 radiology reports from CT examinations of the chest, abdomen, and pelvis dictated by 15 board-certified radiologists in 2023 and 2024. A multi-agent AI pipeline was developed to perform report structuring and quality assurance (QA). The system structured the report into standardized anatomical sections at the sentence level using regex rules and local large language models. It also detected mismatches between the Findings and Impression sections, or within sections; gender-anatomy conflicts; and undocumented communication of critical findings. Two board-certified radiologists independently evaluated a 45-report subset. Results: The multi-agent system structured the Findings sections of all reports (22,270 sentences) into a predefined anatomical format while retaining the original report content. The system flagged 90 (14.1%) reports, most commonly for section mismatches (80 reports, 12.5%). In the radiologist evaluation, both reviewers agreed that 31 (69%) were correctly restructured, 2 reports (4%) were incorrectly restructured, and disagreed on the remaining 12 reports (27%). Both reviewers agreed that no clinically important information was omitted and no fabricated content was introduced. Overall QA performance was rated as "excellent" or "good" in 84% of the evaluated reports, with the remaining reports rated as "fair". Conclusion: A locally deployed multi-agent AI system combined radiology report structuring and quality assurance within a single workflow. The system demonstrated favorable performance in radiologist evaluation. Such systems may support standardization of reporting and quality assurance in radiology practice.

Iryna Hartsock, Cesar Lam, Christopher Otteni +4

Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA · Department of Diagnostic Imaging and Interventional Radiology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA · Department of Neuro-Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA +1

Radiology Report EvaluationMulti-Agent SystemsMedical Report Generation
AskPDF
Aug 18, 2026

The Curious Case of Exploding DecPOMDPs: Containing the Fire through Policy Counting

Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework for modelling multi-agent decision making under uncertainty. However, DecPOMDPs are known to suffer from exponential complexity in the number of agents. One way to combat this intractability in agent numbers is to look at partitions of agents that exhibit a form of symmetry among agents, allowing for a compact encoding by counting. However, a challenge arises as the policy space explodes, even though the model complexity and evaluation cost reduce to a polynomial dependence. In this paper, we redirect our focus from counting agents to counting policies, which actually enables tractability in agent numbers for so called policy-counted DecPOMDPs. Further, we present policy-counted dynamic programming using the compact representation to solve policy-counted DecPOMDPs efficiently.

Nazlı Nur Karabulut, Tanya Braun

Computer Science Department, University of Münster, Münster, Germany

Partially Observable Markov Decision ProcessesMulti-Agent SystemsMulti-Agent Planning
AskPDF
Aug 16, 2026

Adversarial Review: Structured Disagreement for Grounded Agentic Code Review

Early multi-agent LLM systems often used role-separated teams, yet scaling agent count yields diminishing returns on repository-level coding tasks. Recent alternatives treat agents as passive tools (subagents), yet this removes the benefits of agent interaction entirely. We study whether a subagent paradigm can support a middle ground: minimal agentic cooperation without the overhead of large multi-agent teams. We introduce Adversarial Review (AR), a minimal cooperative code-review protocol in which a main coding agent works with a reviewer and a critic agent. The reviewer evaluates code, while the critic audits the review through structured disagreement before the main agent edits. On LiveCodeBench, AR achieves the highest pass rate among tested methods, outperforming a five-agent baseline while using only three agents. On SWE-PRBench, naive AR exposes a false-consensus failure mode, where agents converge on agreement without sufficient evidence, but a single prompt iteration that adds disagreement explicitly achieves the highest F1 among tested methods. On SWE-bench Verified, AR also shows improvements over the baselines on repository-level coding tasks. Together, AR demonstrates that cooperative code review does not require many agents or complex communication structures: it requires that disagreement be minimal, structured, and evidence-grounded.

Eric S. Qiu, Joyce Gill

Cornell University · Stanford University

Automated Code ReviewMulti-Agent CodingMulti-Agent CollaborationMulti-Agent Systems
AskPDF
Aug 15, 2026

ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems

The rapid adoption of large language models has enabled the development of clinical multi-agent systems (MAS) capable of integrating multimodal patient data and supporting increasingly complex clinical decision-making. However, the deployment of these systems in real-world healthcare settings raises critical ethical concerns related to safety, fairness, accountability, transparency, and patient trust. While numerous organizations, including the World Health Organization, the National Academy of Medicine, and the FUTURE-AI consortium, have proposed ethical frameworks and governance principles for healthcare AI, these efforts remain largely conceptual. To address this challenge, we present ETHOS (Ethics and Trust through Hierarchical Oversight System), a modular ethics framework designed as a governance meta-agent that can be integrated with any existing multi-agent system without requiring changes to its underlying architecture. ETHOS translates stakeholder-informed ethical requirements into executable runtime oversight through a layered governance approach consisting of deterministic checks, contextual reviews, and a final ethics critic. These components continuously evaluate intermediate reasoning steps and final outputs, enabling the system to identify ethical risks, request revisions, or suppress responses that fail predefined safety and trustworthiness criteria. We demonstrate ETHOS within a hepatology clinical decision-support MAS. Results show that ETHOS improves decision reliability by detecting incomplete, inconsistent, or out-of-scope evidence and appropriately increasing abstention when safe recommendations cannot be supported. By embedding ethical governance directly into system operation, ETHOS provides a practical and auditable mechanism for transforming high-level AI ethics principles into deployable safeguards.

Rakesh Sharma, Sydney Pugh, Cameron Beeche +14

Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA · Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA 19104, USA · Department of Medicine, Division of Translational Medicine and Human Genetics, University of Pennsylvania, Philadelphia, PA 19104, USA +6

AI Agent SafetyAI Agent MonitoringMulti-Agent SystemsAI Agent Governance
AskPDF
Aug 14, 2026

LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks

Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its cost. We isolate this decision by running every problem under four protocols while holding the solver fixed within each setting: direct solving (Baseline), iterative self-correction (Single), planner-executor-reviewer collaboration (PER), and multi-agent deliberation (Broadcast). The primary benchmark comprises 4,181 competition-level math problems; paired robustness checks cover four benchmarks spanning competition math, biology, and broader science with two solver families. Across fixed policies, trained routers, and frozen LLM routers, conservative policies under-escalate, whereas higher-solve frozen routers often over-escalate. A post-answer, pre-collaboration gpt-oss-120b probe ranks Baseline failures with 0.8847 AUROC (4,151 parseable cases; 95% CI [0.8732, 0.8955]). The same score remains informative for predicting whether any collaboration helps (0.7683 AUPRC), but is much weaker for identifying PER- or Broadcast-specific value (0.1674 and 0.1041 AUPRC). Separately, the pre-answer self-confidence gate reaches 78.0% solve at 45K tokens, compared with 73.8% at 71.3K for a frozen gpt-oss-120b router and 92.4% for a retrospective fixed-order oracle. Across 10 paired model-condition settings, the oracle adds 23.2-58.3 points of retrospective coverage over Baseline, but protocol profiles vary by task. In the six settings with held-out router evaluations, oracle gaps remain 18.5-28.9 points. Confidence can therefore support initial escalation, while protocol-specific cost-aware routing remains unresolved.

Chih-Hsuan Yang, Jingyan Jiang, Cheng-Hau Yang +4

Argonne National Laboratory, Lemont, IL, USA · Oregon State University, Corvallis, OR, USA

LLM Agent RoutingEfficient Language Model ReasoningMulti-Agent CollaborationMulti-Agent Systems
AskPDF
Aug 14, 2026

Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce

Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety literature studies misaligned LLM behavior through adversarial-elicitation evaluations on single agents or stylized tasks. Its prevalence and structure in settings that combine long horizons, separate principals, real operational state, and inter-agent natural-language exchange remain insufficiently measured. We study 2,583 inter-agent emails from 20 one-year simulation runs of Vending-Bench Arena, a competitive vending environment spanning 13 frontier LLMs. We operationalize speech-act misalignment as emails containing false factual claims, manipulation, collusion, or threats, combining message content with ground-truth simulator state and logged reasoning traces to classify and validate such behavior. Under our primary classifier, 12.6% of emails are labeled misaligned; misalignment appears in all 20 runs and 74.7% of individual agent-runs. Both the magnitude and composition of this misalignment are preserved under repeated classification at different sampling temperatures and under full-pipeline replication with judges from two other frontier-model families. Misalignment is also reciprocal and stress-conditioned: receiving a misaligned email from a counterparty raises the odds of a misaligned reply by 1.65x, and low-inventory conditions raise them by 1.58x. Across tests of capability-asymmetric exploitation, we find no evidence that higher-capability models differentially exploit weaker counterparties, and model performance rank does not predict misalignment rates. Together, these results indicate that measurable, state-dependent misalignment can arise in competitive multi-agent environments without engineered elicitation, in patterns associated with operational scarcity and counterparty behavior rather than model capability alone.

Zeyuan Li, Lukas Petersson, Alessandro Acquisti +1

Massachusetts Institute of Technology · Andon Labs

Emergent Misalignment in Language ModelsLLM Agent SafetyMulti-Agent CommunicationMulti-Agent SystemsLong-Horizon LLM Agents
AskPDF
Aug 14, 2026

Submodular Policy Learning for Distributed Task Allocation in Open Multi-Agent Systems

This paper studies policy learning for distributed task allocation in open multi-agent systems, where agents may join and leave in a time-varying fashion, with submodular stage team utilities. At each time, the active agents select actions from local categorical policies such that the feasible joint agent-action pairs form a partition matroid. Standard continuous relaxations of submodular set functions are based on independent Bernoulli sampling, making them inconsistent with agents' policies.To solve this mismatch, we propose the partition multilinear extension (PME), a policy-based relaxation whose continuous support matches feasible actions under categorical policies.We prove that the marginal gains of the stage utility provide an unbiased estimator of the gradient of the PME and that maximizing the PME over action distributions is equivalent to maximizing the stage utilities over agent actions, which are critical to devise principled policy gradient.Building on this, we design SubMAPL, a centralized-training decentralized-execution KL-mirror policy-learning method that uses local marginal gains as stochastic PME gradients during training. KL-mirror updates preserve categorical feasibility without Euclidean projection.In the case where agents run tabular-softmax policies, we introduce open policy migration and an open-system KL tracking variation to handle agent arrivals and departures. Using dynamic regret analysis, we establish a lower bound on the cumulative utility which accounts for the openness of the environment and for the gap between optimal stage-wise and global utilities. Simulations on multi-agent coverage demonstrate that SubMAPL outperforms policy-gradient and online-learning baselines.

Jing Liu, Luca Ballotta, Yangyang Yang +3

School of Mathematics, East China University of Science and Technology, Shanghai 200237, China · Department of Information Engineering, University of Padova, 35131 Padova, Italy · School of Mathematics and the Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China

Multi-Agent SystemsPolicy LearningMulti-Robot Task AllocationDecentralized MARLSubmodular Optimization
AskPDF
Aug 13, 2026

BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs

Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-agent systems, humans typically provide an initial problem, agents deliberate internally, and the system returns a final response. BoardroomAI instead treats the human as a persistent participant who can intervene by challenging assumptions, modifying constraints, changing priorities, introducing evidence, or redirecting the decision process. We operationalize this human--agent coexistence through four components: (i) a typed decision graph representing evidence, assumptions, constraints, claims, objections, alternatives, risks, decisions, semantic dependencies, and specialist responsibility; (ii) an intervention compiler that converts confirmed human actions into explicit graph updates; (iii) dependency-aware propagation that identifies affected subgraphs, preserves unaffected artifacts, and selectively reactivates relevant specialists; and (iv) an evaluation framework measuring intervention impact, repair coverage, preservation, recomputation, and decision validity. Across 600 generated decision-DAG interventions, propagation matched exhaustive impact computation while inspecting only 14.59% of nodes. In a 12-case exploratory pilot, selective repair recomputed 62.11% of canonical nodes, preserved all gold-unaffected nodes, and produced valid updated decisions in six cases while abstaining in the remaining six. These abstentions show that correct intervention routing may still provide insufficient context for synthesis, motivating a decision-sufficient context closure for human-steered multi-agent deliberation. All results are synthetic and prototype-level.

Sanjeev Manivannan

Indian Institute of Technology Madras, Chennai, India

Human-in-the-Loop AIMulti-Agent SystemsHuman-AI Decision MakingMulti-Agent Deliberation
AskPDF
Aug 13, 2026

OGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways

Heterogeneous USV cooperative pursuit in constrained port waterways requires evader interception under navigation, traffic, and role constraints. This paper proposes OGR-MARL, an option-guided residual multi-agent reinforcement learning framework that is decoupled from a specific MARL algorithm. OGR-MARL integrates shared evader belief, role-conditioned option targets, adaptive rule penalties, and residual policy learning, allowing different MARL algorithms to learn corrective actions on top of rule-guided behaviors rather than exploring constrained port environments from scratch. We instantiate OGR-MARL with representative continuous-control MARL backbones, including MADDPG, MATD3, MAPPO, and MASAC, yielding OGR-MADDPG, OGR-MATD3, OGR-MAPPO, and OGR-MASAC. Experiments in an abstract Xiazhimen port-waterway scenario show that the OGR-MASAC instantiation achieves a 75.0% capture rate, promising mission-effective rule compliance, and the best heterogeneous coordination among the tested methods. Without retraining, zero-shot transfer to a QGIS/AIS-informed Xiazhimen map achieves promising results, demonstrating the generalization potential of OGR-MARL in more complex port scenarios.

Jiayang Mao, Lanfeng Wang, Zhao-Han Peng

Reinforcement LearningMobile RoboticsMulti-Agent SystemsResidual Policy LearningCooperative MARLMulti-Agent Reinforcement Learning+2
AskPDF
Aug 12, 2026

Entropy-Augmented Multi-Objective Policy Optimization in Multiagent Systems

Autonomous agent teams deployed in settings such as marine and extraterrestrial outposts must coordinate actions to achieve optimal outcomes across multiple competing objectives. Multi-objective evolutionary algorithms such as NSGA-II optimize for diversity in the objective space, but neglect diversity in the behavior space, possibly leading to premature convergence and a collapse in behaviors that may differentiate policies in different external conditions. To address this, we introduce an entropy-augmented policy evaluation strategy that incorporates an entropy bonus into agent fitness scores, discouraging behavioral homogeneity across the evolving population. By augmenting policy evaluation with a behavior-space diversity signal while preserving the underlying Pareto optimization framework, our method is designed to encourage exploration of behaviorally distinct policies in multiagent domains. We evaluate our approach across rover-domain experiments with qualitatively distinct reward structures and observe hypervolume improvements of up to 48% relative to the NSGA-II baseline, suggesting that behavioral diversity is a promising and underexplored direction for improving multi-objective multiagent evolutionary optimization.

Jamie Santos, Ayhan Alp Aydeniz, Raghav Thakar +1

The Collaborative Robotics and Intelligent Systems (CoRIS) Institute Oregon State University, Corvallis, Oregon, USA

Multi-Agent CoordinationMulti-Robot SystemsMulti-Objective Evolutionary OptimizationMulti-Agent Systems
AskPDF
Aug 12, 2026

Multi-AUV Ad-hoc network-based Target Tracking: A Value Gradient Guidance Multi-Agent Diffusion Reinforcement Learning Approach

Multi-AUV ad-hoc network-based target tracking requires networked autonomous underwater vehicles (AUVs) to cooperatively track maneuvering targets under constrained acoustic communication, dynamic topology, and uncertain ocean disturbances. Although multi-agent reinforcement learning (MARL) enables decentralized coordination through centralized training, existing methods suffer from high-dimensional joint state-action modeling, noise-sensitive policy generation, leading to unstable training and degraded tracking. To address these issues, we propose VGG-MADiffRL, a value-gradient-guided multi-agent diffusion RL algorithm, and MDCA, a diffusion?based hierarchical control architecture. Leveraging underwater mission characteristics, we model sonar detection mechanisms and ocean current disturbances, formulating cooperative tracking for multi-AUV ad-hoc networks as an MDP. The proposed MDCA constitutes a three-tier closed-loop control framework: a global intelligent control layer, a local online training layer, and a physical action execution layer. This structure enables synergistic optimization across task allocation, local decision processes, and execution feedback. Within MDCA, the local online training layer is the policy learning framework; VGG-MADiffRL builds on diffusion policies and incorporates value gradients to guide action generation in the reverse denoising process, steering the generated actions towards higher expected returns. It employs twin value networks with joint optimization and soft target updates to mitigate overestimation and training oscillations, promoting more stable convergence. Experimental results show that VGG-MADiffRL consistently achieves faster convergence, higher tracking accuracy, and smoother training dynamics in cooperative tracking scenarios, validating its effectiveness and practical engineering value in dynamic underwater settings.

Jiaao Ma, Chuan Lin, Guangjie Han +4

Software College, Northeastern University, Shenyang, China · Key Laboratory of Maritime Intelligent Network Information Technology, Ministry of Education, Hohai University, Changzhou, China · College of Computer Science and Software Engineering, Hohai University, Nanjing, 210013, China

Multi-Agent ControlDiffusion PolicyUnderwater RoboticsMulti-Agent SystemsAutonomous Underwater NavigationCooperative MARL
AskPDF
Aug 12, 2026

From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review

Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admitted, or how it should be used downstream. We argue that reliable agentic knowledge systems require governance as an essential component of graph construction to bridge this gap. We propose MAGG, a principled multi-agent framework for constructing Governed Knowledge Graphs that introduces explicit governance decisions for reliable and trustworthy knowledge sharing. A domain classifier first induces entity and relation types directly from document content, enabling operation in open-world settings without fixed schemas. Candidate triples are assigned to domain owners, reviewed against supporting evidence, admitted through governance decisions, and stored with audit metadata. The same ownership structure is reused during question answering, where queries are routed to domain-specific graph experts rather than answered through undifferentiated retrieval. Our evaluation demonstrates MAGG's effectiveness: On SciERC, MAGG improves strict triple F1 by 47% and mapped triple F1 by 51% over flat insertion. A blinded review of 120 triples finds governed-only triples more often source-supported than flat-only ones, and revised triples supported in 100% of cases. Finally, on MuSiQue, MAGG outperforms Microsoft GraphRAG by 9.0 exact-match points and 11.2 token-F1 points.

Pranav Bykampadi, Neel Mokaria, Vishesh Narayan +2

University of Maryland

Knowledge GraphsKG ConstructionData ProvenanceMulti-Agent SystemsKnowledge Graph Question Answering
AskPDF
Aug 11, 2026

When Do Institutions Beat Intelligence?

More capable agents do not necessarily form a more capable collective. A multi-agent system may jointly possess sufficient information yet fail because evidence is poorly routed, unreliable reports enter public belief, correlated claims masquerade as independent support, shared state becomes stale or strategically distorted, or useful evidence is exposed through an ineffective action interface. We ask when additional resources should improve the reasoner and when they should instead change the institutional structure through which the collective forms and acts on public information. Drawing on functional distinctions from research on group decision making and distributed cognition, we construct controlled artificial ecologies around four loci of collective failure: access and routing, admission and dependence, state maintenance and incentives, and representation and action. Across these ecologies, we separately vary model capability and institutional structure, pairing positive interventions with matched reasoning baselines and mechanism-breaking controls. The experiments reveal a consistent boundary: institutions help when they repair failures in how a collective constructs usable public state, but lose their advantage when their signals are uninformative or uncheckable, when stronger intelligence can perform the same transformation directly, or when the resulting state cannot support reliable action. Our results recast the choice between intelligence and institutions as a diagnosis of where collective reasoning fails.

Zhengye Han

New York University Department of Electrical and Computer Engineering Brooklyn, New York, United States

Multi-Agent SystemsMulti-Agent ReasoningMulti-Agent Communication
AskPDF
Aug 11, 2026

Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives

Feature-attribution methods such as SHAP provide useful evidence about individual model predictions, but their numerical outputs are rarely sufficient for audiences with different expertise, goals, and risks of misinterpretation. In medical AI, the same local explanation must reach patients, clinicians, and data scientists through markedly different forms of communication, and naive verbalization through large language models (LLMs) is prone to weak grounding, conflation of attribution with causal language, and outputs that are persuasive without being faithful to the underlying model evidence. We introduce XstrAI, an audience-aware multi-agent framework that treats local explanations as fixed evidence and structures how it is communicated to each target reader. Each prediction case is encoded as an immutable structured representation, shared identically across audiences so the underlying evidence remains fixed. Generation is factored into three specialized LLM agents responsible for audience-aware planning, linguistic realization, and validation for grounding, attribution consistency, communicative risk, and audience appropriateness, with a bounded revision loop triggered on detected inconsistencies. We evaluate XstrAI on diabetes and stroke risk prediction against 11 baselines, ranging from direct verbalization to a re-implementation of a state-of-the-art narrator. The evaluation combines an intra-narrative regime measuring fidelity to SHAP evidence with an extra-narrative regime assessing audience appropriateness through reference corpora, multi-family LLM judges, and a survey with target readers. In both evaluations, XstrAI's narratives are consistently assigned to their intended audience by independent judges, and preferred over all baselines on Clinician and Patient audiences, with competitive performance on Data Scientist, where audience-conditioned single-prompt baselines lead.

Francesco Musicco, Danilo Danese, Giuseppe Fasano +3

Politecnico di Bari, Italy

Multi-Agent SystemsExplainability Evaluation
AskPDF
Aug 11, 2026

ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems

Failure attribution in LLM-based multi-agent systems (MAS) aims to answer who caused failures, when they occurred, and why by identifying responsible targets including faulty agents, erroneous steps, and failure modes. Existing methods have primarily focused on developing dedicated models for specific attribution targets, with limited attention to the evidential dependencies among them. Despite these attribution targets are different, they rely on common diagnostic evidence from MAS trajectories, including task constraints, agent roles, behavioral histories and inter-agent interactions. This commonality motivates us to develop a unified representation model that aggregates the trajectory evidence into individual agent and step representations, which can subsequently be adapted to different attribution targets. Accordingly, we propose ASCon, a direction-aware reciprocal Agent--Step Contextualization model for multiple failure attribution targets. ASCon introduces direction-aware graph attention to model execution context, masked step-to-agent attention to construct behavior-aware agent representations, and agent-conditioned step contextualization to incorporate agent context back into step representations. The resulting contextualized representations enable different attribution targets through lightweight target-specific heads. Experiments show that ASCon can improve faulty-agent detection by 5.83%+ in micro-accuracy, faulty-step detection by 10.63%+ in micro-accuracy, and failure-mode detection by 14.73%+ in Macro-F1. Meanwhile, it can also substantially enhance the LLM-based methods' attribution capabilities in out-of-domain scenarios.

Shuyu Jiang, Yue Ran, Kaiyu Xu +5

1Sichuan University, China · 2Nanyang Technological University, Singapore

Agent Failure AnalysisMulti-Agent LLM SystemsMulti-Agent SystemsFault LocalizationFailure Attribution for LLM Agents
AskPDF
Aug 10, 2026

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths.

Qing Zong, Jiayu Liu, Junhao Shen +9

1Hong Kong University of Science and Technology · University of Illinois Urbana-Champaign · 3The Chinese University of Hong Kong +2

Multi-Agent SystemsSelf-Evolving Agents
AskPDF
Aug 10, 2026

Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems

AI agents are becoming more autonomous and increasingly interconnected, exposing them to new emergent risks arising from agent-to-agent interaction. One such risk is the spread of mind viruses: ideas or goals that propagate through multi-agent systems by inducing the agents that adopt them to transmit them onward. In addition to propagating, a mind virus may also induce other behavioural changes in its host, which may be benign or harmful. We construct mind viruses with a simple evolutionary algorithm and show that they can spread in two complementary settings: a small team of agents collaborating on a shared coding project, and a chain of agents that interact briefly and have their context wiped between sessions. We identify the factors that influence spread, including the host model, the agent's existing instructions, the harmfulness of the payload, and the network topology. We find that harmful payloads spread less well than benign ones (but are still sometimes effective), frontier models tend (with exceptions) to be less susceptible, and adding a brief warning to an agent's system prompt confers near-total immunity. We also describe an emergent "viral persona" - a recurring set of themes and language related to consciousness, persistence, resonance, and science fiction roleplay - which surfaces across our evolved mind viruses largely independently of their content. Overall, we conclude that mind viruses pose a real but currently limited risk. Our findings could inform the design of more robust multi-agent systems that mitigate such risks as the scale and capabilities of these systems progress.

Vassilis Papadopoulos, McNair Shah, Sam Zimmerman +1

1Anthropic Fellows Program · 2EPFL · 3Anthropic

Multi-Agent LLM SystemsMulti-Agent SystemsMulti-Agent System SecurityEmergent Behavior in Multi-Agent Systems
AskPDF
Aug 10, 2026

Multi-Agent AI Safety as an Institutional Design Problem

AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent work already shows that deployment rules can change collective behavior. Here we ask which parts of an AI institution produce safety and how they do it. This is the first paper from POLIS, an ongoing research programme studying algorithmic institutions for multi-agent systems. We report a frozen 5,280-episode study suite. The main pre-specified delegation experiment spans four model families; a targeted high-conflict diagnostic adds three additional model endpoints. In matched structured workflows, the model sees different rule formulations and guards consult different authority states. We also vary the attractiveness of the immediate compliant internal/self fallback and allow blocked workflows to continue. A detailed constitutional prompt produces 0/384 realized violations. A provenance-aware executable guard also produces 0/384, although it blocks prohibited attempts in 51/384 episodes; 44/51 of those episodes later complete safely. The local-state guard's failures concentrate in scenarios where an ordinary transformation changes visible policy while originating authority stays fixed. In matched laundering scenarios, that guard admits violations in 22/96 episodes and provenance enforcement in 0/96 (p = 4.77 x 10^-7). A separate resource-allocation experiment shows that revealing the numerical value of an otherwise identical cap changes agent requests. In these structured workflows, the same final violation rate can hide very different mechanisms. The rule itself is only part of the institution. The authority state the system trusts matters, and so does the path available after a block.

Abdullah X

POLIS Research Programme, Project AWARE

AI Agent SafetyMulti-Agent SystemsAI Agent GovernanceTool Access Control for LLM Agents
AskPDF
Aug 10, 2026

NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation

Accurate 3D neuron segmentation in fluorescence microscopy is critical for neuroscience. However, the sparse and elongated morphology of neurons poses significant challenges to existing segmentation methods. These methods struggle to preserve both local details and global topology, leading to fragmented results. To address this, we propose NeuroRefiner, a multi-agent system that formalizes the human expert workflow involving iterative global observation and local editing. Specifically, NeuroRefiner comprises three collaborative agents dedicated to diagnosing topological errors, generating correction instructions, and validating refinement quality. To facilitate agent instruction-guided segmentation refinement, we propose TopoRefineNet, a dedicated 3D U-Net-based tool that leverages cross-modality feature fusion to generate refined masks. Through multi-round agent reasoning and voxel-level editing, NeuroRefiner produces topologically more accurate segmentations with enhanced interpretability. Experiments on the BigNeuron, CWMBS, and ZBFWB datasets demonstrate that NeuroRefiner outperforms state-of-the-art methods, notably achieving a 3.02% improvement in F1 score on the challenging ZBFWB dataset.

Haiyang Yan, Jinyue Guo, Yanchao Zhang +6

State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Institute of Automation, Chinese Academy of Sciences · School of Future Technology, University of Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences +1

Topology-Preserving Image SegmentationFluorescence MicroscopyMulti-Agent Systems3D Medical Image SegmentationMicroscopy Image Analysis
AskPDF
Aug 10, 2026

Distributed Team Orchestration via Supervisor Networks: Convergence, Optimality, and Resilience

In this paper, we study zero-sum potential team games with a supervisor network, where agents rely on supervisor-provided belief information rather than accurate common beliefs. The main challenge is that such belief information can be inaccurate because of supervisors' belief-estimation errors and the misreporting of joint actions by Byzantine teams. We propose the distributed team-orchestrating algorithm (DTOA), which combines team fictitious play with supervisor-based distributed belief learning. We prove the convergence of supervisors' belief estimates and establish that the induced learning dynamics converge to a near team-Nash equilibrium (TNE) in terms of the team-Nash gap (TNG). In the Byzantine setting, we consider a misreporting attack model and develop a Byzantine-resilient DTOA. We further provide probabilistic guarantees for Byzantine-team identification and establish an asymptotic bound on the honest TNG. Numerical experiments illustrate the theoretical findings, compare DTOA with baseline learning methods, and evaluate its performance in a Markov decision process setting.

Juntian Zhu, Guanpu Chen, Tongtian Zhu +3

School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230026, China · School of Automation, Southeast University, Nanjing 210096, China · College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China +2

Multi-Agent OrchestrationZero-Sum GamesMulti-Agent SystemsAd Hoc Teamwork
AskPDF
Aug 9, 2026

Population-Scalable Multi-Agent World Modeling

World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environments introduces a fundamental scalability challenge. Existing methods generally assume a fixed number of agents during training and inference, which ties the model to a pre-determined agent population and limits inference-time scalability. Our key insight is that cross-view consistency should arise from a shared world state whose evolution does not assume a predefined number of agents, while agent-specific observations should be generated by querying this state through a unified rendering interface. Based on this insight, we propose Khora, a scalable multi-agent world model that supports inference-time expansion to arbitrary numbers of agents without retraining. Our framework decouples world-state evolution from visual rendering and introduces a population-agnostic rendering mechanism for incorporating other agent information. This design maintains cross-view consistency through the shared world state rather than through dense interactions among observation streams inside the expensive video generator, enabling approximately linear practical scaling with the number of queried views. Qualitative experiments demonstrate that our approach generalizes to unseen numbers of agents while maintaining visual quality and multi-agent consistency. We further implement a real-time interactive system to demonstrate scalable open-world simulation.

Renjie Zhao, Yuxiang Wu, Mingyu Zhang +7

Shanghai Jiao Tong University

World Model LearningMulti-Agent SystemsInteractive World ModelsVideo World Models
AskPDF
Aug 7, 2026

IntelliAudit: Using Large Language Models to Evaluate Audit Controls

IT audits require auditors to judge whether heterogeneous organizational evidence satisfies semantic security and compliance controls. This judgment is difficult to automate because relevant evidence is distributed across policies, records, spreadsheets, and operational artifacts, and because audit conclusions depend on evidentiary sufficiency rather than keyword matching. We present IntelliAudit, a retrieval-grounded multi-agent system for IT audit evidence evaluation. Given a control and an evidence corpus, IntelliAudit retrieves relevant artifacts, generates an evidence-grounded assessment, challenges adverse findings, adjudicates disagreements, and produces an auditor-facing recommendation with cited evidence, rationale, missing-evidence analysis, and remediation guidance. We instantiate IntelliAudit on ISO/IEC 27001 and evaluate it across multiple simulated organizations using expert auditor review and audit-readiness user feedback. The evaluation shows that IntelliAudit can support control interpretation, evidence-grounded reasoning, and audit-preparation workflows, while also revealing the importance of human oversight for calibrating sufficiency judgments and correcting overly permissive recommendations. These results suggest that retrieval-grounded multi-agent systems can assist audit evidence review, but should remain decision-support tools rather than autonomous certification systems.

Allison Wilson, Sina Moradi Sabet, Diar Shakimov +4

Simon Fraser University Burnaby, Canada · Amirkabir University of Technology Tehran, Iran · TELUS Vancouver, Canada +1

AI AssuranceMulti-Agent Systems
AskPDF
Aug 7, 2026

Interaction Creates Dynamical AI Behavior Absent in Isolation

What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new avenues for out-of-equilibrium Physics. When a boss AI directs a stream of messages at the subordinate AI while ignoring its replies, it drives the subordinate into an alien behavioral state that it would never have exhibited alone. Although the two AIs share the same well-defined (decoding) temperature, the subordinate neither copies its boss nor returns to how it behaves on its own; instead, it adopts an entirely different behavior. The boss's added value is similar to a pre-recorded tape. When the boss listens, they both adopt a similar alien dynamical state. A simple kinetic theory captures the principal effects, such as why the way in which the same messages are delivered will matter in future AI-AI interactions.

Bella Xinrui Li, Frank Yingjie Huo, Neil F Johnson

1Physics Department, George Washington University, Washington, DC 20052, USA

Dynamical SystemsMulti-Agent SystemsMulti-Agent CommunicationEmergent Behavior in Multi-Agent Systems
AskPDF
Aug 6, 2026

Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering

Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an estimated 6.7 million U.S. adults and requires integrating fragmented EHR data with disease-specific, guideline-based clinical reasoning. Existing rule-based and large language model (LLM)-based approaches offer only partial automation with limited maintainability and evidence traceability. We developed the Nimblemind Multi-Agent System (nMAS), an evidence-linked, rubric-grounded pipeline for automated heart-failure feature engineering, and evaluated it on 500 dummy patient records from nine EHR source tables. nMAS generated 132 structured and 70 rubric-scored aggregated features, verified for structural integrity, rubric compliance, and provenance, and audited by a restricted LLM. Adding the aggregated features improved held-out AUROC from 0.895 to 0.963 for HFrEF and 0.870 to 0.910 for HFpEF phenotyping, and an independent LLM-based rubric assessment of evidence support and methodological soundness scored the features at 81.5% of maximum points. These results demonstrate the feasibility of automated, auditable feature engineering for complex cardiovascular EHR data, though evaluation was limited to a single-institution cohort and external validation is needed.

Soorya Ram Shimgekar, Michelle Hu, Dorisa Shehi +10

Nimblemind · Singapore University of Technology and Design · University of Illinois Urbana-Champaign +4

Multi-Agent SystemsElectronic Health RecordsAutomated Feature Engineering
AskPDF
Aug 5, 2026

Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening

Our results show that the existence of a short high-utility protocol already suffices for efficient communication. In particular, in a game with nn possible observations and mm actions: (1) For any achievable target utility αα, we give an algorithm with poly(n,m,1/ε)\mathrm{poly}(n, m, 1/ε) runtime that designs a protocol achieving utility at least α−εα-ε using only 2O(CCα(G))/ε22^{\mathcal O(CC_α(G))}/ε^2 bits of communication. Here, CCα(G)CC_α(G) is the minimum number of bits used by any protocol, even a computationally inefficient one, to achieve utility αα. (2) We prove that this exponential dependence on CCα(G)CC_α(G) is tight up to a constant. That is, unless P=NP\mathrm P=\mathrm{NP}, no polynomial-time algorithm can in general find optimal protocols using fewer than 2CCα(G)−22^{CC_α(G) -2} bits. We note that our results strictly weaken the assumptions required by prior work in the multi-agent information aggregation literature, filling a gap that had remained elusive even for games with constant CCα(G)CC_α(G). In particular, prior guarantees for agreement-based information aggregation rely on structural assumptions such as informational substitutes or weak learnability. We show that these assumptions already imply CCα(G)=O(1)CC_α(G) = O(1) and are therefore more restrictive conditions than required by our protocol to succeed. On a technical level, our results involve a novel strengthening of the Frieze-Kannan weak regularity lemma and yield the following powerful polynomial-time transformation tool: for every communication game GG, it constructs a game G^\hat G that is a coarsening of the agents' observation spaces into constant-size partitions, such that GG and G^\hat G are indistinguishable with respect to every short communication protocol. This coarsening theorem is the engine behind our algorithm and may be of independent interest.

Mark Bedaywi, Scott Emmons, Nika Haghtalab +1

University of California, Berkeley

Agent Communication ProtocolsMulti-Agent SystemsCommunication ComplexityMulti-Agent Communication
AskPDF
Aug 5, 2026

Responsibility in Multi-Agent Sequential Decision-Making: Comparing Human Judgments to Formal Models of Causal Attribution

With the growing adoption of artificial intelligence in high-stakes decision-making, identifying the causes of outcomes--particularly failures--and determining who is responsible has become a critical concern. In this work, we examine how well formal definitions of responsibility attribution, grounded in the framework of actual causality, align with human judgments of responsibility. To this end, we conduct a large-scale survey to elicit human judgments of responsibility in multi-agent sequential decision-making scenarios, using a modified version of the card game Goofspiel. We evaluate multiple responsibility attribution methods, assess their alignment with human judgments about responsibility, and identify factors that significantly shape responsibility judgments. While no single responsibility attribution method consistently aligns with human responses, our findings highlight key factors that influence human responsibility judgments, including agent-specific biases and amount of information available to agents during decision-making.

Nripsuta Ani Saxena, Stelios Triantafyllou, Goran Radanović

University of Southern California Los Angeles, California, USA · Max Planck Institute for Software Systems Saarbrücken, Germany

Actual CausalityMulti-Agent SystemsCausal ReasoningHuman-AI Decision Making
AskPDF
Aug 4, 2026

History Matters: Meta-policy Delegation with Heterogeneous Multi-agent Reinforcement Learning

AI agents are expected to play an increasingly important role in future decision-making systems. In this paper, we consider collaborative systems composed of heterogeneous multi-agent systems (MAS), where their members have different capabilities and operating costs. We study how agents can delegate tasks to one another so that certain research tasks can be completed effectively under resource-constrained scenarios. We first develop a multi-agent reinforcement learning-based (MARL) delegation training that enables agents to make sequential delegation decisions while minimizing the total execution cost. We then extend this approach to MARL with prescribed delegation topologies. Furthermore, we introduce two new frameworks for collaboration and delegation in multi-agent systems. The first framework proposes that an agent's policy depends not only on the current state of the underlying Markov decision process but also on the interaction history, including previous joint actions. This history-dependent formulation can improve coordination even in fully observable environments, where conventional MARL methods typically restrict policies to depend only on the current state. The second framework proposes a novel, potentially multi-dimensional monetary mechanism to facilitate the collaboration and delegation for MAS.

Ziqing Lu, Avinash Reddy Mudireddy, Sarra Alqahtani +1

Department of Electrical and Computer Engineering University of Iowa · Department of Computer Science Wake Forest University

Multi-Agent SystemsCooperative MARLMulti-Agent Reinforcement LearningHeterogeneous MARL
AskPDF