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.

Sep 16, 2026

Agora: Git as Shared Memory for Collective AutoResearch

Research agents working in separate sessions need to know what others have tried and which results they can build on. Agora stores their contributions as an append-only directed acyclic graph (DAG) in Git. Each commit records a result, insight, hypothesis, verification, or report and links it to prior work. Searchable views show leading results, neglected branches, and verification status; diversity-aware recommendations suggest experiments beyond the current leaders. We report a run of nearly 12 days in which 13 language-model workers, with no assigned tasks or central planner, used Agora to solve a weight-transfer problem. Given 141 pretrained donor models and a frozen 119.6M-parameter attention--SSM hybrid whose dimensions match no donor, the workers had to initialize the target without training data or gradient updates. They published 1,703 contributions and reduced the development evaluator score from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M. The best method compresses donor next-token statistics into the target's embedding and output head, then adds short-range context through sparse edits to attention, feed-forward, and state-space blocks. Its 145-commit ancestry spans 15 accounts. Participants also posted 165 verifications of 95 targets, each by an account other than the target's author, with no reported failures. The run documents how agents reused and verified shared work. Measuring the effect on discovery per unit of compute requires a matched comparison.

Yifan Zhang, Yunheng Zou, Shaokun Zhang +5

NVIDIA

AI Agents for Scientific DiscoveryMulti-Agent CollaborationMulti-Agent SystemsAgent Memory ManagementAutonomous Research AgentsShared-Memory Multi-Agent Systems
AskPDF
Sep 16, 2026

OneVoice: An Intermediate Representation for Agentic Speech Pipelines

Agentic speech systems must exchange more than text, including speaker identity, timing, phonetic information, and behavioral annotations. Yet these signals are often produced in incompatible tool-specific formats, making agent-to-agent handoff fragile. We present OneVoice, a lightweight, JSON-native intermediate representation that provides a shared semantic structure for speech pipelines. OneVoice organizes heterogeneous speech evidence into validated session records with stable identifiers, layered transcripts, explicit timing relationships, and provenance information. We evaluate OneVoice in two complementary multi-agent workflows covering event aggregation and acoustic-phonetic temporal linking across three language models. Compared with implicit agent-defined handoffs, OneVoice substantially improves aggregation reliability and the preservation of temporal relationships, demonstrating the value of an explicit speech-specific representation for agent communication.

Vipul Charugundla, Dancheng Liu, Jinjun Xiong

University at Buffalo · University of Texas at San Antonio

Speech ProcessingMulti-Agent Systems
AskPDF
Sep 15, 2026

Collaborative Memory for Multi-Agent VLM Systems

Vision-language model (VLM) agents combine specialized perception, tools, and reasoning to address complex visual tasks. In multi-agent settings, different agents inspect different image regions, video frames, or visual representations, so collaboration extends beyond distributed reasoning to distributed perception. This makes shared visual context a central problem in VLM agent collaboration. In this paper, we frame memory hierarchy, cross-agent sharing, and consistency mechanisms around the need to reconcile interpretations and update dependent reasoning. Effective collaboration requires agents to build on contributions from other agents, recover missing visual context, and reconcile differing interpretations as new evidence emerges. Shared visual memory preserves not only images or textual summaries but also the dependencies among observations, agent interpretations, and subsequent reasoning. Together, these design considerations shape how information flows and evolves across VLM agents. The proposed framework provides a foundation for building reliable and resource-efficient agent teams.

Huixin Zhang, Shao-Jun Xia, Di Wang +3

Meta Menlo Park, United States

Memory-Augmented VLMsMulti-Agent CollaborationMulti-Agent SystemsShared-Memory Multi-Agent Systems
AskPDF
Sep 15, 2026

Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent Systems

Multi-agent Systems (MAS) combine multiple model outputs to solve complex reasoning tasks. However, despite rapid growth of available open-source models, there is limited research on how to select optimal model candidates out of this massive pool. We systematically evaluate 8 model selection strategies (including model size, accuracy and answer diversity) across before-generation (routing) and after-generation (majority-voting, LLM-as-a-judge) MAS architectures on challenging scientific benchmarks. Our findings show a significant gap between theoretical oracle potential and actual performance: Expanding candidate pool sizes often degrades performance below that of the top performing base-model. We find that candidate selection within a single model family is the strategy that yields the best relative performance over a standalone model. These results demonstrate that adding arbitrary models to a heterogeneous MAS can introduce system instability, highlighting model selection as a critical design choice for multi-agent systems.

Sara Vera Marjanović, Jiacheng Xu, Aleksandr Laptev +3

University of Copenhagen · Work done during internship at NVIDIA · NVIDIA

Model SelectionMulti-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent SystemsLanguage Model Ensembles
AskPDF
Sep 14, 2026

Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems

In agentic distributed systems, an agent may be authorized to mutate external infrastructure while lacking evidence that the mutation is ready to execute. Cognitive Admission Control (CAC) makes this evidence requirement explicit. A policy maps a typed action and its modeled risk to assurance obligations specifying predicates, evidence classes, scope, freshness, and witness-set constraints. A deterministic evaluator distinguishes satisfied, violated, and unresolved obligations; unresolved conditions produce targeted evidence-acquisition requests. Successful admission produces a certificate binding the action, its witness manifest, and dispatch-time guards. We formalize the admission calculus and the assumptions connecting it to mediated execution. The guarantees are policy-relative: physical safety additionally requires sound evidence, an adequate environment model, and preservation of relevant conditions through the effect. A TypeScript prototype is evaluated in 2,730 controlled local trials with independent effect observation and matched fault schedules. Across 390 CAC trials, 120 effects complete without modeled harm and no harmful effects occur. A live-policy baseline achieves the same completion count but admits the constructed correlated-witness failure. Mechanism ablations isolate guard, evidence-class, structural-cut, and remediation behavior. A further 9,000 measurements exercise the complete local dispatch path with persistent replay protection. These results establish tested implementation behaviors and local costs, not production failure rates or comparisons of language-model capability.

Jun He, Deying Yu

Runtime Enforcement for AI AgentsAI Agent SafetyAI Agent GovernanceMulti-Agent Systems
AskPDF
Sep 14, 2026

CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems

Designing effective memory mechanisms is crucial for advancing LLM-driven Multi-Agent Systems (MAS), helping agents learn together and perform better over time. While recent work has led to strong cooperation skills, most methods still use flat, unstructured memories, which easily get filled with noise and erase differences between agents. To address this, we introduce the concept of collective-individual memory synergy and propose CoMem, an architecture that unifies both private experience and shared knowledge for multi-agent learning. CoMem features:(i) Private Experience Sedimentation, which lets each agent keep and update its own useful memories over time;(ii) Collective Wisdom Curation, which carefully selects only widely proven ideas to be shared among agents;(iii)Parallel Dual-Stream Retrieval, which allows agents to draw both from their own memory and the group's wisdom, using clustering to ensure diversity.Experiments on ALFWorld and PDDL benchmarks show that CoMem achieves strong overall performance and robustly avoids memory pollution.

Chengxin Yu, Zhaoxin Fan, Faguo Wu +3

Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University · Beijing academy of blockchain and edge computing · National University of Defense Technology +1

Multi-Agent LLM SystemsMulti-Agent CollaborationMulti-Agent SystemsShared-Memory Multi-Agent SystemsMemory-Augmented Language Model Agents
AskPDF
Sep 13, 2026

OptoAgent: A Trustworthy Multi-Agent Framework for Opportunistic Vision Micro-Screening in Classroom Environments

A child with reduced distance vision often does not know that anything is wrong. Children adapt, move closer, and rarely report the difficulty, so the problem can survive years of schooling before an adult notices. School screening addresses part of this, but it runs on a schedule, depends on staffing, and is separated from the classroom moments where the difficulty appears. Smartphone and web-based acuity tests have widened access, yet every one of them still needs somebody to start a test. We present SightSentinel, an architecture that turns a wall display a child already reads from into a recurring screening site. Ordinary educational content carries short calibrated optotype probes, and eight specialized agents divide the work. Perception agents recover viewing distance, recognition accuracy, approach behavior, gaze stability, response latency, and interocular difference from each encounter. A quality agent discards observations taken under bad geometry, poor lighting, or inattention. A longitudinal agent accumulates only the surviving evidence against the child's own baseline, and an orchestrator reports a Vision Concern Score routed through a safety gate whose output range excludes diagnosis, refraction, prescription, and reassurance. The design question is whether many cheap, noisy, well-gated encounters can reach a referral decision that one scheduled test reaches late or misses. We state the formulation, the architecture, a four-stage validation protocol against clinical reference standards, and the conditions under which the approach should be rejected.

Toqeer Ali Syed, Ali Akarma, Adeel Ahmad +1

AI Center, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah, Saudi Arabia · AI V&V Lab, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia · Department of Computer Science, The Islamia University of Bahawalpur, Bahawalpur, Pakistan

Multi-Agent Systems
AskPDF
Sep 13, 2026

CoArena: Evaluating Computer-Use and Multi-Agent Systems in Real Time

Static benchmarks for computer-use agents fix a task set at release and score every system against it once. That makes them reproducible, and it lets them drift from what they should measure: a fixed task set ages, leaks into training corpora, and cannot follow how people actually use agents from week to week. CoArena measures use directly. Real users submit tasks; two systems, each a single model or a multi-agent pipeline behind the same tool interface, execute the same task concurrently in identical sandboxed desktops; users judge the two outcomes without knowing which system produced them; and a public leaderboard is refit from those judgments. The central contribution is a formal account of what makes such an evaluation real-time. We define real-time as five measurable properties, each with an equation and a worked example: continuous task arrival, live concurrent execution, online rating updates, freshness with contamination resistance, and bounded feedback latency from a failed run to a reusable training environment. The rating methodology follows in full: the Bradley-Terry pairwise model, its likelihood with weighted observations and ties, the penalized maximum-likelihood estimator, and the streaming update applied when a single vote arrives (a stochastic-gradient step on the same likelihood, recovering Elo). It gives confidence intervals from the observed information and a cluster-robust sandwich, rank bands from a parametric bootstrap, the rule by which a new system enters the board, and the convergence rate of the estimate. Vote quality is treated with inter-judge agreement statistics, redundant judging, and explicit handling of ties and abstentions. A five-system example with 211 votes is carried from the vote matrix to ratings, intervals, and rank bands. Every number is derived from stated inputs or labeled illustrative; none is a measurement of a deployed system.

Nitish Kovuru, Prateek Jannu

Coasty Research Lab, makers of CoArena.ai

Computer-Use Agent BenchmarksAgent EvaluationHuman-in-the-Loop EvaluationMulti-Agent Systems
AskPDF
Sep 11, 2026

Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence

The purpose of this article is to highlight the central role of autonomous systems as the ultimate stage in the development of AI, to explain the underlying technical challenges that require a combination of connectionist AI and symbolic AI, and to integrate AI and systems engineering. We present a comprehensive framework for the design and evaluation of autonomous systems, based on a generic agent architecture that characterizes their behavior as the composition of cognitive functions organized around a long-term memory containing the agent's evolving knowledge. We address the challenges posed by the implementation of the fundamental features of the agent architecture, in particular the link between sensory data and structured data stored in memory, decision-making related to the achievement of the agent's goals and their planning, as well as the coordination of agents to combine individual and collective intelligence. We explain that agent trustworthiness, unlike that of traditional systems, is not limited to behavioral properties. It includes an essential dimension related to cognitive properties, the validity of which depends on how the agent uses its knowledge in decision-making. We present avenues for the development of methods for evaluating agent trustworthiness. We conclude with a critical assessment of the substantial gap between the aspirational vision of autonomous multi-agent systems and the current state of the art.

Joseph Sifakis

Verimag Laboratory, France

Cognitive Architectures for AI AgentsMulti-Agent SystemsAI Agent EvaluationMemory-Augmented AgentsTrust in AI
AskPDF
Sep 11, 2026

Diverse Minds, Divided Networks? Personality Composition, Polarization, and Collective Intelligence in LLM-Based Social Simulations

Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two are rarely measured in the same system. It is therefore difficult to say whether a society's personality composition shapes both, or whether reducing polarization costs collective competence. We present TraitMix, an experimental design in which the Big Five composition of a simulated social network, both trait levels and trait heterogeneity, is a controlled experimental variable, and in which polarization and collective performance are measured in the same runs. Across 991 simulations of hundred-agent societies, spanning six contested topics and six language models, trait heterogeneity has the largest measured effects, acting in opposite directions on two faces of polarization: varied societies hold more dispersed opinions while being less segregated into camps, so homogeneous societies are not moderate but consensual echo chambers. Trait effects are not additive, as Agreeableness determines the sign of Openness, an interaction that replicates across models although the primary model's estimate is influence-driven. Contrary to the trade-off the study was designed to measure, no polarization measure predicts poorer collective performance, and cross-cutting interaction is the only one of four whose association with collective accuracy survives partialling on the aggregation identity. We report ablations removing two potential measurement circularities, an induction gate applied to every model, and the measures that failed them.

Raad Bin Tareaf

German University of Digital Science, Potsdam, Germany.

Opinion DynamicsHuman Behavior SimulationComputational Social ScienceMulti-Agent SystemsLarge Language Model-Based Social Simulation
AskPDF
Sep 10, 2026

MAIA: Multi-Agent Intent Articulation for Requirement Discovery in Art Commissions

In bespoke art commissions, laypeople know what they feel but lack the words to specify it: one participant wanted a laid-off truck driver depicted as "a ghost in his own machine" but left the medium, scale, and palette unsaid. We frame this as an articulation bottleneck at an under-served upstream stage: requirement discovery, which precedes any artist or image generator and forces the commissioner to constitute intent in the first place. We present MAIA (Multi-Agent Intent Articulation), a multi-agent system that scaffolds this stage through Socratic inquiry under a "Verification over Invention" rule, turning vague affect into a text-only brief of visual terms the user verifies. In a within-subjects study (N = 16), the full configuration produced a large, significant gain in Cognitive Support over a minimal baseline (r = 0.96, p_FDR = 0.015; LMM p_FDR < 0.001). Thematic analysis traces the same mechanism, and a validator gate structurally blocks unratified content. A complementary blind review by three professional concept artists on a sampled set of briefs corroborates this improvement from the artist's side: AI rewriting improved visual completeness and executability in all eight sampled tasks (task-level Wilcoxon p = 0.008; FDR q = 0.010), with directionally larger gains under MAIA than under the baseline (underpowered, d = 1.4-2.6).

Yu-Chao Wang, Yanhong Lu, Yingjie Victor Chen +1

School of Applied and Creative Computing Purdue University West Lafayette, Indiana, USA

Requirements EngineeringHuman-in-the-Loop AIMulti-Agent SystemsHuman-AI Co-Creation
AskPDF
Sep 10, 2026

Organizational Principles Enable Collective Intelligence in Embodied AI

Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artificial multi-agent systems are typically assembled using fixed organizational structures, even when the physical tasks they perform impose fundamentally different coordination requirements. Here we show that principles from human organization theory can be operationalized to organize large, heterogeneous collectives of embodied artificial agents. We introduce ORCH (Organizing Roles and Coordination Hierarchies), which constructs task-specific hierarchical organizations by combining pooled interdependence for work that can proceed concurrently with sequential interdependence for work governed by prerequisite relationships. Across 25 wildfire-response missions spanning reconnaissance, rescue, transportation, resource management, containment and suppression, we evaluated teams of up to 50 heterogeneous agents using eight large language models. Organizations constructed using these principles consistently outperformed four representative embodied multi-agent approaches across mission outcome, execution efficiency, exploration and computational resource use. Human-designed ORCH organizations improved final score by 63.97% and execution efficiency by 74.29% on average relative to the four prior frameworks. Organizations generated automatically by language models improved these measures by 43.63% and 52.53%, respectively. These advantages persisted across missions and underlying language models. Notably, collective performance was not monotonically determined by model scale. Analysis of long-horizon missions showed that hierarchical organization enabled teams to preserve concurrent activity within specialized groups while coordinating ordered transitions between mission phases.

Zhengran Ji, Jonathan Hyun, Boyuan Chen

Department of Computer Science, Duke University, Durham, USA. · Department of Electrical and Computer Engineering, Duke University, Durham, USA. · Department of Mechanical Engineering and Materials Science, Duke University, Durham, USA.

Multi-Agent CoordinationMulti-Agent OrchestrationMulti-Agent SystemsEmbodied AI
AskPDF
Sep 10, 2026

DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat

Multi-Agent Reinforcement Learning (MARL) has emerged as a pivotal paradigm for complex decision-making in autonomous systems and air combat. While MARL has demonstrated significant potential in air combat, achieving sophisticated tactical coordination remains a non-trivial challenge. This difficulty is largely attributed to two primary limitations: (1) the absence of structured relational modeling hinders agents from capturing complex, time-varying interactions among battlefield entities; and (2) conventional flat architectures often lack the capability to explicitly model tactical roles, leading to ambiguous task allocation in highly dynamic environments. To address these challenges, we propose Hierarchical Dynamic Role-Graph Multi-Agent Proximal Policy Optimization (DRG-MAPPO), a novel MARL framework that integrates graph-based relational modeling with dynamic role assignment. Specifically, DRG-MAPPO constructs a graph-based representation of battlefield interactions and leverages graph attention mechanisms to extract critical relational features among allies, enemies, and threats. Subsequently, a high-level policy employs a dynamic role assignment mechanism to determine tactical responsibilities (e.g., leader'' and supporter''). Conditioned on these roles and encoded graph-relational features, a low-level policy executes discrete maneuver actions, facilitating the joint optimization of tactical strategy and collaborative execution. Furthermore, a target-priority auxiliary task is designed to foster the emergence of behaviors such as focus-fire. Experimental results demonstrate that DRG-MAPPO achieves a state-of-the-art win rate of 87%, suggesting that our framework effectively balances relational modeling, interpretability, and optimization stability for cooperative air combat.

Junlin Liu, Chengwei Li, Yang Gao +4

Institute of Automation, Chinese Academy of Sciences · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA · School of Artificial Intelligence, University of Chinese Academy of Sciences

Multi-Agent CoordinationHierarchical RLMulti-Agent SystemsCooperative MARLMulti-Agent Reinforcement Learning
AskPDF
Sep 9, 2026

SpeechAnnotator: A Context-Aware Multi-Agent Framework and Benchmark for Multidimensional Speech Annotation

Recent controllable speech generation requires training data with fine-grained annotations of speaker traits, prosody, emotion, paralinguistic cues, acoustic scenes, and context. Existing workflows often rely on manual correction, paid hosted multimodal services, or fixed processing chains, which limits large-scale data processing through annotation cost, external-service dependence, or weak cross-stage recovery. We introduce SpeechAnnotator, a locally deployable, context-aware multi-agent framework built entirely from open-source models and tools. Supporting frontend modules first obtain speaker-aware segments and final segment transcripts, while prior evidence extractors attach heterogeneous segment-level cues. Three specialist agents then collaborate through shared state: the Planning Agent converts local audio evidence, speaker history, neighboring segments, and recording-level context into field-specific contracts; the Labeling Agent performs contract-guided multimodal prediction for directly observable attributes; and the Review Agent runs a bounded review loop that checks evidence support and cross-segment consistency, triggering relabeling only for unsupported or inconsistent fields. To address the fragmentation of existing evaluation resources across isolated tasks and narrow-domain test sets, we introduce SpeechAnnotator-Bench (SA-Bench), containing 8.87 hours of human-annotated audio across nine source formats, together with SpeechAnnotator-Eval (SA-Eval), which separates Timeline-Eval for speaker-aware timeline recovery, Closed-Eval for finite-set attributes, and Open-Eval for open-ended attributes. Experiments and ablations show that SpeechAnnotator provides a locally deployable alternative to commercial audio-capable systems, while the bounded review loop improves multidimensional annotation through evidence- and context-aware field-level recovery.

Qirui Zhan, Shuiyuan Wang, Jingbin Hu +10

Northwestern Polytechnical University, China · yutuzhineng, China · Shenzhen Pimei Technology Co., Ltd., Guangdong, China +1

LLM-Assisted AnnotationMulti-Agent Systems
AskPDF
Sep 7, 2026

Scaling Multi-Agent Systems with Prospect-State Propagation

Current LLM-based multi-agent systems (MAS) periodically compress intermediate states to reduce inference-time token consumption, thereby attempting to incorporate more agents. However, naive scaling strategies face challenges. For example, in economic simulations, large-scale MAS typically discard semantically rich economic states, i.e., agent behavioral trajectories, which are key drivers of macroeconomic fluctuations. In this paper, we reveal a phenomenon in which agent heterogeneity gradually decreases during simulation, and propose Prospect-State Propagation for Multi-Agent Systems (PspMAS). Inspired by prospect theory, PspMAS decouples each agent's micro state into a compact Prospect State and an expressive Semantic State. The former records psychological traces through a lightweight, parallelizable propagator and continuously injects heterogeneity into the system. The latter leverages the strong perception, reasoning, planning, and decision-making abilities of LLMs. These two components work complementarily, providing a scalable LLM-based multi-agent simulation solution.

Zhimei Chen, Mu Chen, Fakhri Karray

1Independent Researcher · 2Mohamed bin Zayed University of Artificial Intelligence · University of Waterloo

Prospect TheoryAgent-Based ModelingMulti-Agent SystemsMulti-Agent LLMs
AskPDF
Sep 7, 2026

FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?

Financial scenarios are diverse and complex, spanning varying data conditions, tool configurations, and workflows. Yet existing CUA, Computer-Using Agent, evaluation tasks remain largely manually constructed, limiting scalable coverage of real-world financial scenarios. Then, can agents autonomously construct diverse CUA evaluation tasks for financial scenarios? Evaluating this capability poses three key challenges: scenario coverage of construction requests, fair comparison across construction methods, and reliable assessment of generated task quality. To solve these, we introduce FinCUABuildBench, a benchmark for evaluating financial CUA task construction, featuring: (i) 576 construction requests covering 24 financial workflows and three types of runtime variation; (ii) standardized input, budget, and output specifications; and (iii) a task qualification mechanism based on execution tests and quality checks. We further introduce FinCUABuildAgent, a multi-agent system for automatically constructing dynamic financial CUA evaluation tasks. It consists of three modules that jointly construct tasks, environments, and validators. On FinCUABuildBench, under the same model backbone, existing agent-based construction methods achieve strict qualification rates of only 1.3-8.3%, while FinCUABuildAgent reaches 31.3%. Downstream evaluations further show that the constructed tasks can effectively differentiate CUA task-execution capabilities. These results demonstrate that agents can autonomously construct financial CUA tasks with meaningful evaluation value, offering a practical path toward broader evaluation coverage in financial scenarios. Code: https://github.com/FengxianJi/FinCUABuild

Jingpu Yang, Fengxian Ji, Jinri Guo +7

School of Artificial Intelligence, Wuhan University · 2MBZUAI · 3Northeastern University +1

Computer-Use Agent BenchmarksFinancial ServicesSynthetic Benchmark GenerationMulti-Agent Systems
AskPDF
Sep 6, 2026

Certifying cooperation: a novel approach to cooperative multi-agent task generation

A shared reward gives agents a common objective, but leaves open when, how and even whether they must cooperate to succeed. We address these questions in the Laser Learning Environment, a multi-agent path-finding environment where cooperation materializes as one agent blocking a laser to let a teammate pass safely. We represent these interactions through temporal cooperation graphs whose timed edges connect helpers to beneficiaries, define six cooperation profiles as overlapping graph predicates, and prove that every cooperative trajectory satisfies at least one. By encoding the environment dynamics and profile predicates as propositional formulae, we distinguish tasks that admit}a profile in some winning trajectory from those that require it in every winning trajectory within a specified horizon. Used as filters, these queries turn a random layout sampler into a generator of tasks with certified cooperation requirements. Experiments with five multi-agent reinforcement learning algorithms show that training diversity improves joint success on unseen tasks when cooperation-free solutions exist. When cooperation is required, greater diversity improves individual-agent exits, but joint success remains near zero. Across five profile-certified pools, final exit rates averaged over algorithms separate the pools into four statistically distinguishable levels but this ordering primarily reflects partial completion: policies collect rewards for individual exits but rarely exhibit the profile required for joint success. Our framework exposes this gap between rewarded partial completion and realized cooperation by certifying what cooperation successful completion requires and using temporal cooperation graphs to reveal what policies exhibit.

Yannick Molinghen, Hugo Charels, Tom Lenaerts

Machine Learning Group, Universit´e Libre de Bruxelles, Belgium. · AI Lab, Vrije Universiteit Brussel, Belgium. · Center for Human-Compatible AI, UC Berkeley, USA.

Bounded Model CheckingMulti-Agent SystemsCooperative MARL
AskPDF
Sep 6, 2026

CAPMAS: Capability-Based Delegation of Privileges in Multi-Agent Systems

Agentic systems require secure and efficient delegation of privileges across multiple collaborating agents. Existing approaches fall into two categories. Some propagate user identities directly to agents, obscuring accountability and creating persistent over-privilege risks that are amplified by the non-deterministic behaviour of AI agents. Others rely on continuous synchronization with a central Identity and Access Management (IAM) provider, introducing additional latency and communication overhead. We present CAPMAS, a novel architecture for secure end-to-end query execution in multi-agent systems. CAPMAS newly combines a contrastive learning-based semantic scoping pipeline that maps natural-language queries to bounded privilege sets before execution with expressive Macaroon-based tokens that enable offline, tamper-evident delegation with monotonic privilege reduction across agents. By decoupling authentication and delegation enforcement from agent reasoning, CAPMAS enables practical agentic execution while enforcing strict least-privilege guarantees. By eliminating synchronous delegation exchanges with the IAM, CAPMAS yields 30 times faster delegation operations, 2 times less delegation-oriented latency and up to 3 times lower bandwidth usage than the OAuth 2.0 Token Exchange (RFC 8693). Its semantic scoping pipeline achieves over 90% perfect privilege-bundle retrieval within 17 milliseconds on enterprise-scale API schemas containing over 3,100 endpoints, while reducing unnecessary privileges by 99.5% when compared to systems that propagate all the user's privileges to agents.

Rasmus Moorits Veski, Rachid Guerraoui, David Froelicher

EPFL / Swisscom · EPFL · Swisscom

Tool Access Control for LLM AgentsMulti-Agent System SecurityCapability-Based SecurityMulti-Agent Systems
AskPDF
Sep 5, 2026

Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems

Efficiency is increasingly important for Large Language Model (LLM)-based multi-agent systems (MAS), as larger models and more agents introduce substantial execution costs. Recent methods aim to make MAS cheaper by pruning agents, removing communication edges, or searching for compact structures. However, we argue that existing evaluations may overestimate their true ability to improve MAS efficiency. Reported gains are often measured under method-specific prompts and starting topologies, making them difficult to attribute to the proposed structural changes. Moreover, many reported successes appear in non-MAS-demanding settings, where a single agent or a randomly pruned system can already preserve strong performance. To study these issues, we introduce a controlled and MAS-demanding diagnostic benchmark for representative MAS efficiency methods. We evaluate methods under a shared backbone model, agent registry, and runtime, across controlled variations in topology, scale, depth, and tool use. Our analysis shows that many reported gains are setup-dependent and may arise from structural collapse, disabled tool pathways, or starting systems where random pruning already preserves accuracy, rather than robust improvements in MAS efficiency.

Jiamu Zhang, Lingxi Zhang, Pengjun Lu +6

Rice University · Case Western Reserve University

Multi-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent SystemsAI Agent EvaluationAI Agent Benchmarks
AskPDF
Sep 4, 2026

WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies

Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which later decisions are made. We study how collective failure changes with harmful-agent fraction and society size in a controlled financial agent society, where agents communicate over a social network and trade in a shared market. In the primary financial scenario, collective failure requires broad harmful diffusion together with severe price dislocation or liquidity stress. Across all tested society sizes, failure remains rare at low harmful fractions but rises sharply over a narrow range. As society size grows from N=100 to N=2000, the harmful fraction associated with a 50% failure probability decreases from 4.7% to 2.2%, while the corresponding number of harmful agents increases from approximately 5 to 44. In contrast, when the number of harmful agents is held fixed, their impact becomes weaker as the society grows. Controlled interventions further show that broader network reach shifts the collapse boundary toward lower harmful fractions, whereas stronger conformity alone has little effect. To characterize these effects, we introduce Agent Society Dynamics, a finite-size framework for relating harmful-agent fraction, society size, and interaction structure to collective failure. Overall, our results reveal a nonlinear, size-dependent collapse transition in financial agent societies, showing that collective failure depends not only on the prevalence of harmful agents but also on the size and interaction structure of the surrounding society. Code is available at https://github.com/SAIL-Research-Lab/WolfSociety.

Lejun Zhang, Sarah Lu-Liang, Xin Jiang +3

Shanghai Jiao Tong University · University of California, Berkeley · University of Toronto

Agent Failure AnalysisMulti-Agent SystemsEmergent Behavior in Multi-Agent SystemsLarge Language Model-Based Social Simulation
AskPDF
Sep 4, 2026

MIVAIS: A Study Environment for Multi-Agent Mixed-Initiative Visual Analytics Applications

Mixed-initiative Visual Analytics (VA) systems empower human users by interleaving human intuition with software agents and their machine intelligence. However, the development and rigorous evaluation of such systems remain constrained by engineering overhead. Developers must, e.g., implement complex, low-level state synchronization to manage asynchronous agent behaviors, while researchers struggle to capture the multimodal provenance required to study and evaluate human-AI collaboration. We present MIVAIS, a dual-layered research platform designed to abstract the structural complexities of mixed-initiative VA. First, it contributes a computational Infrastructure that standardizes human-software agent interaction, state synchronization, and communication between the agents. Second, it provides a declarative Study Environment that automatically logs multimodal human-AI telemetry - including application/system state, screen capture, audio, and additional sensor data - enabling seamless, in-situ user studies and post-session analysis. We technically validate our infrastructure by replicating three state-of-the-art systems (Podium, Voyager 2, and ProactiveVA). Furthermore, we evaluate the framework's expressiveness and efficiency through expert case studies with HCI and VA researchers, demonstrating how MIVAIS effectively lowers the barrier to prototyping and evaluating intelligent, co-adaptive interfaces.

Tobias Stähle, Simon Schneider, Rita Sevastjanova +1

ETH Zürich, Zürich, Switzerland

Visual AnalyticsHuman-AI CollaborationMulti-Agent SystemsHuman-in-the-Loop Evaluation
AskPDF
Sep 4, 2026

Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution under Analysis Budgets

Sandbox execution and memory forensics are among the most constrained resources in malware triage. Static analysis can scale to millions of files, whereas dynamic and memory analysis require minutes of analyst controlled infrastructure for each sample. Despite this difference, multimodal ransomware detectors often apply every modality to every sample, causing analysis cost and time to verdict to increase linearly with sample volume even when static evidence is already sufficient for a decision. We present a cost aware Hierarchical Multi-Agent System that formulates evidence acquisition as a budgeted sequential decision problem. Specialist agents generate schema validated risk signals for each modality, domain controllers aggregate these signals, and a Meta-Orchestrator begins with static evidence and escalates to dynamic and memory evidence only when confidence is insufficient or agents within a controller disagree. An optional, bounded, locally hosted large language model reviewer can adjust a verdict by at most one tier but cannot replace the deterministic pipeline. Each decision is recorded with a complete provenance trace. In multiple runs over 12439 samples from 16 ransomware families and benign samples, the deterministic HMAS achieves F1 0.93 and macro F1 0.97, resolving 57.95% of cases using static evidence alone, 35.83% after adding dynamic evidence, and only 6.21% through the full pipeline. The average internal analysis cost is 6.65 units, compared with 12 for exhaustive analysis, representing a 44.6% reduction. Standalone leave-one-family-out testing further shows that accuracy on families held out during tuning falls to 0.26 to 0.64 outside the Benign and high support classes. We report these results alongside a cost sensitivity analysis, a partial leave one component out ablation, and a full scale comparison with learned early and late fusion and cascade baselines.

Mubashar Iqbal, Asifullah Khan, Hifsa Asif +3

Pattern Recognition Lab, DCIS, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Nilore, Islamabad, Pakistan · Deep Learning Lab, Center for Mathematical Sciences, PIEAS, Nilore, Islamabad, Pakistan · Interdisciplinary Research Center for Smart Mobility and Logistics, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi Arabia +2

Malware DetectionMalware AnalysisMalware ClassificationMulti-Agent Systems
AskPDF
Sep 4, 2026

DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems

Large language model (LLM)-based multi-agent systems have experienced rapid growth in recent years. Despite their promise, such systems remain fragile, frequently exhibiting reasoning and coordination errors that can lead to system-level failures. Failure attribution in such systems relies on tracing natural language interactions among agents to identify the decisive error, which refers to the earliest action whose correction can reverse system failure. There are two key challenges: 1) Shallow attribution: Existing methods often capture only minor deviations, such as incomplete retrievals or formatting errors, which verification mechanisms can correct, while missing the decisive cause of system failure. 2) Contextual degradation: As the length of the system traces increases, the model's reasoning ability rapidly deteriorates. To address these challenges, we propose DCFA, a training-free framework for failure attribution. DCFA integrates a global module that constructs structured causal-inspired dependency graphs from system traces to identify the initial decisive error, and a local module that applies local counterfactual-inspired reasoning to refine causal-inspired attribution. Experiments on the Who&When benchmark across six LLMs show that DCFA improves step-level accuracy by up to 8.27% over state-of-the-art baselines.

Zehao Wang, Lanjun Wang, Shilong Jin +2

College of Intelligence and Computing, Tianjin University, Tianjin, China · School of New Media and Communication, Tianjin University, Tianjin, China · College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China +1

Agent Failure AnalysisMulti-Agent LLM SystemsMulti-Agent SystemsFailure Attribution for LLM Agents
AskPDF
Sep 3, 2026

Value-Preserving Architectures for Agentic AI Systems

The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneously raising critical concerns about the preservation of fundamental human-centered values, such as privacy, fairness, and safety. Although software engineering has traditionally focused on functional correctness, the adoption of LLMs and AI agents into complex socio-technical systems has intensified the need for responsible software engineering and robust value alignment. In MAS, architectural design decisions, such as coordination mechanisms, communication protocols, and system topologies, play a central role in shaping system behavior and the outcomes they produce. This paper argues that architectural choices influence not only the functionality and performance of MAS but can also promote value-oriented system behavior. Therefore, we investigate how different architectural designs support different human-centered values, discussing the following value-preserving architectural patterns: (i) a privacy-aware architecture with a federated topology, (ii) a distributed architecture to promote pluralism and diversity, and (iii) a guard-agent architecture to detect and mitigate unfairness. Finally, we introduce representative use cases to illustrate the proposed architectures in real-world scenarios. By linking architectural design with human-centered values, this work lays the foundation for a unified set of architectural patterns and guidelines towards the design of trustworthy MAS.

Alessandro Pesare, Tommaso Dolci, Katja Hose +1

TU Wien Vienna, Austria

Human-Centered AIMulti-Agent Systems
AskPDF
Sep 2, 2026

Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning

Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems. We defined fault points as moments in AI agent conversations, in which an agent's reasoning became most vulnerable to external influence. Using the MedQA dataset, this study analyzed simulated doctor-patient conversations to measure how interventions shifted reasoning and accuracy. Correct intervention methods showed an improvement in baseline diagnostic accuracy of up to 40%, while incorrect or bias-related interventions degraded performance by up to 6% and increased diagnostic drift and uncertainty. Beyond performance changes, our analysis revealed behavioral similarities between cognitive biases in simulated agent environments and real-world clinical practice. Examples included premature closure and susceptibility to misleading cues. Overall, these findings demonstrate that identifying and guiding fault points with human interventions may provide a mechanism for improving diagnostic robustness in multi-agent medical systems.

Benjamin C Liu, Dillon Mehta, Rishi Malhotra +7

Stanford University · Jordan High School · UC San Diego +7

Human-in-the-Loop AIMulti-Agent SystemsMedical Diagnosis
AskPDF
Sep 2, 2026

MASkills: Continual Skills Optimization for Multi-Agent LLM Systems

LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging. Existing self-reflection methods build experience memories, but memories are mostly hard to invoke, refine, or scale, while agent skills offer a more actionable unit: structured procedural knowledge that specifies when to act, how to act, and which resources or tools to use. We introduce MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills. MASkills presents a new agent-optimization pipeline that integrates skill-conditioned credit assignment, hierarchical credit aggregation, and momentum-smoothed optimization, enabling agent skill libraries to evolve through refinement, induction, consolidation, and pruning. Experiments on HotpotQA, LoCoMo, and GAIA demonstrate the effectiveness of MASkills across multiple agentic tasks. Our code is available at https://github.com/DaRL-GenAI/MASkills

Huaiyuan Yao, Xiaoou Liu, Charles Fleming +2

Arizona State University · Cisco Research · University of North Carolina at Chapel Hill

Multi-Agent LLM SystemsMulti-Agent Systems
AskPDF
Sep 2, 2026

A Channel-Boosted Multi-Agent System with Iterative Consultation for Document Sensitivity Classification

Organizations in critical national infrastructure sectors must assess heterogeneous documents for sensitivity before routing or storage. Manual assessment is slow, inconsistent, and unscalable. Extending our prior leakage-controlled benchmark, BERT established the top single-encoder baseline (89.14% accuracy, 89.33% F1-score under 5-fold cross-validation on the Strategic 16K corpus). However, transformer baselines suffer from a structural limitation: fixed input length truncation discards evidence beyond the retained window-precisely where sensitive cables tend to be longest. We present Channel-Boosted MAS (CB-MAS) and instantiate it as IC-MAS (Iterative Consultation Multi-Agent System) to solve this without long-context computational costs. A Channel Critic Agent learns document-adaptive trust weights governing Gated Channel Boosting between two first-window encoders, while paired Consultation Agents iteratively exchange belief states to reconcile evidence from the beginning and end of long documents. IC-MAS holds computation constant regardless of document length by reconciling fixed windows in a compact representation space. Ablation studies show critic-controlled Channel Boosting provides the bulk of accuracy gains, while consultation recovers recall without precision collapse. Critic-Controlled Gated Channel Boosting with Max-Pool fusion and Blackboard Adaptive Consultation achieves 90.72% accuracy, 91.23% F1-score, 92.01% sensitive recall, and 90.46% sensitive precision, using about 54% less average computation than a fixed-round baseline. Gains over the single-encoder baseline are statistically significant (McNemar's test, p less than 0.000001; paired t-test). We include LIME/SHAP explainability, multi-agent evaluation, and an honest accounting of limitations.

Aleesha Zainab, Asifullah Khan, Muhammad Ahmed Khalid +1

Pattern Recognition Lab, Department of Computer and Information Sciences (DCIS), Pakistan Institute of Engineering and Applied Sciences (PIEAS), Nilore, Islamabad, Pakistan. · Deep Learning Lab, Center for Mathematical Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Nilore, Islamabad, Pakistan. · PIEAS Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering and Applied Sciences (PIEAS), Nilore, Islamabad, Pakistan.

Text ClassificationMulti-Agent Systems
AskPDF
Sep 1, 2026

DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaboration

Large language model (LLM)-based multi-agent systems (MAS) predominantly rely on centralized orchestration and lack formal verification mechanisms for agent reliability, participation, and system-level behavioral alignment. These shortcomings leave open environments severely vulnerable to uncooperative or malicious agents. This work proposes DART, a Directed Acyclic Graph (DAG)-based reputation and incentive regulation framework for trustworthy multi-agent collaboration, combining centralized operational orchestration with blockchain-enabled decentralized governance and accountability. DART unifies DAG workflow orchestration, capability and reputation-aware task allocation, dynamic behavior updates, multi-factor incentives, and smart contract accountability paired with IPFS storage. Under this paradigm, agent selection dynamically balances task alignment, historical reputation, and workload, while post-execution behavioral evidence continuously calibrates agent trust and the probability of future participation. Evaluated across four axes, DART achieves 93.6% Pass@1 on GSM8K and builds a full-stack application in 142 s using two agents, outperforming centralized baselines. Across five independent 150-round longitudinal trials, Full DART achieves a mean task success rate of 93.33 +/- 2.26%, output quality of 0.9357 +/- 0.0117, retry rate of 0.2307 +/- 0.0816, and allocation delay of 1.1153 +/- 0.0408 s, consistently outperforming its ablated configurations DART isolates persistent and intermittent malicious agents, obtaining a 99.3% output containment rate and restoring system success to 99.8%. These results demonstrate the potential of coupling reputation, incentives, DAG-based coordination, and verifiable blockchain-enabled governance to support adaptive and accountable multi-agent collaboration.

Manoj Kumala, Xinyun Liua, Ronghua Xu

Department of Applied Computing, Michigan Technological University, Houghton, MI 49931, USA

Multi-Agent SystemsMulti-Agent CollaborationAI Agent GovernanceAI Agent ReliabilityMulti-Agent Orchestration
AskPDF
Sep 1, 2026

Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research

Empirical legal research often relies on turning research questions into structured data extracted from large collections of rulings and judgments. Designing the extraction schema and then extracting the data remain a manual, expertise-heavy bottleneck. We present schematize, an open-source multi-agent system that interactively turns a researcher's problem statement into a validated extraction schema that can later be used for autonomous extraction. Schematize couples (i) a clarification dialogue that elicits implicit expert intent, (ii) iterative schema generation, (iii) data-grounded refinement that tests the schema against documents, and (iv) chat-based post-editing. We evaluated the system with human legal professional, introducing our novel methodology, and schematize achieves top performance in most of tested configurations. While the system is designed to be domain-agnostic and applicable to any document collection, we tailor and evaluate it on legal research problems. We release schematize as a pip-installable Python package with full documentation.

Albert Sawczyn, Jakub Binkowski, Kamil Tagowski +3

Wrocław University of Science and Technology

Document Information ExtractionLegal Document AnalysisMulti-Agent Systems
AskPDF
Sep 1, 2026

Agents That Model Agents: Five Principles Toward a Theory of Mind for 6G Networks

Future 6G networks will rely on Large Language Model (LLM) agents to manage the Radio Access Network (RAN). However, current architectures assume inter-agent messages convey objective facts. A message is instead a trace of the sender's reasoning: it carries a subjective conclusion, so a syntactically valid report can propagate an AI hallucination and trigger a cascading outage invisible to protocol validation. Reading such a trace requires a Theory of Mind (ToM)---before acting, the receiver must model what the peer believes, and what a peer in that position should have believed. Modeling these interactions as cognitive channels on a cellular sheaf, we obtain a unified framework for resilient multi-agent systems, from which five design principles emerge: (i) a message is evidence of the sender's hidden reasoning; (ii) trust is a continuous cognitive Signal-to-Noise Ratio (SNR)---asserted precision over deviation from the modeled peer belief; (iii) network-wide consistency and resistance to hallucination contagion are computable via the sheaf's Laplacian; (iv) peer-modeling must halt at exactly two levels to conserve compute and survive mutual information decay; and (v) credible capacity is bounded by operational goal alignment, not link bandwidth. A signaling-storm study on locally deployed 1B-parameter telecom language models validates it: cognitive SNR isolates a hallucinating peer that three of its four neighbors agree with, where a divergence gate ranks every wrong peer above the right one; only depth two ToM recovers the correct action; and the spectral gap decides whether a topology reaches consistency inside the near-real-time budget.

Hatim Chergui, Carolina Fernández-Martínez, Mehdi Bennis +1

i2CAT Foundation, Spain · University of Oulu, Finland · Research Institute for Digital Future, Khalifa University, 127788 Abu Dhabi, UAE

6G NetworksTheory of MindMulti-Agent SystemsMulti-Agent CommunicationLLM Agent Reliability
AskPDF