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

709 papers79 papers in the last four weeks, down 23% on the four weeks before. 0.5% of all new papers.

Oct 17, 2026

Measuring Consensus in AI Agent Networks

As AI agents become increasingly connected through networks and take on tasks that require negotiation and joint decision-making, a systematic approach is needed to assess how their views converge and what information supports their decisions. We present an evaluation framework that treats consensus formation as the evolution of publicly stated positions toward a shared region, using accumulated communication history as context. The framework tracks position trajectories, group dispersion, and information expressed in public messages. Two case studies examine staffing decisions based on distributed facts and decisions requiring agents to reconcile duplicate information and a cancelled contract. Results from 1,872 completed runs associate sharing explanations with more accurate group decisions, while the second task reveals persistent disagreement despite accurate aggregate answers. Membership-change experiments provide a complementary evaluation. By separating convergence among agents from progress toward a task's full-information answer, the framework relates decision accuracy and bounded disagreement to the information available during the exchange.
Oct 16, 2026

MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation

In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answer gives only indirect feedback to the subagents. An LLM judge can score the performance of the subagents, but these scores depend on the judge's own assessment of the quality of subagents' responses. We present MultiAgent-OPD, which combines on-policy distillation with reinforcement learning to jointly train a shared-parameter Leader-Searcher-Answerer team end to end. We first train a Teacher in a Searcher-Answerer workflow using answer correctness. During team training, the frozen Teacher scores student-generated search and summary tokens to provide local process supervision for the Searchers, while the Leader learns from team success and the Answerer from candidate correctness. Across seven datasets, the trained system reaches 38.68% macro avg@4, exceeding Prompted Critic by 4.06 percentage points and C-MAS + RL, the trained cascaded multiagent system, by 2.61 percentage points. The team also solves more questions within four attempts.
Oct 15, 2026

NoveltyScope: A Multi-Agent Research Assistant for Evidence-Grounded Novelty Assessment of Scientific Papers

NoveltyScope is a prototype that compares a scientific paper with retrieved prior work and produces a structured report and a five-level novelty score. The system extracts the core task and at most two author-claimed contributions, then searches a closed local corpus using BM25 and dense retrieval with reciprocal rank fusion. Contribution comparisons request paired passages for potential refutations, and quotations are checked against cached source text. Four scoring roles (Prosecutor, Defender, Judge, and Critic) use the resulting evidence, with at most one revision of the Judge's score. Evaluation uses 50 class-balanced RINoBench samples whose idea-level labels are retained for full-paper input. Mean absolute error is 1.48 and 1.26 for single-LLM and multi-agent scoring with Gemini, respectively, and 1.22 and 1.16 with Qwen3. The vector-similarity baseline has an error of 1.68. A HiCLIP case study illustrates the contribution comparisons and paired evidence passages. Overall, the results demonstrate the feasibility of evidence-grounded novelty assessment and show that the multi-agent configurations achieve lower scoring errors than their single-LLM counterparts across both evaluated models.
Oct 15, 2026

Emergent Discrimination and Polarization in Multi-Agent Systems

We study theoretically how discrimination and polarization can emerge in a population of learning agents. Each agent uses an adaptive linear decision layer to map a language-model embedding of an issue to a binary opinion and maintains an evolving estimate of how much it trusts every other agent. Through pairwise interactions, agents update both their decision weights and trust estimates using an online Bayesian rule derived from teacher-student learning over a noisy channel. In-context-learning experiments with large language models qualitatively reproduce the predicted opinion and trust updates. We then assign each agent one of two arbitrary group labels, A or B, and model group bias by allowing a fraction fbf_b of agents to shift its perceived agreement with each message by a strength bb, a bias steering prejudice, depending on whether the sender and receiver share a label. We use order parameters from statistical mechanics to connect these local dynamics to collective states and transitions. Starting from uniformly random initial conditions, simulations reveal a rich phase diagram in the (b,fb)(b,f_b) plane, comprising four collective states: spin-glass frustrated out-group favoritism, nondiscriminatory polarization, discrimination with opinion alignment, and discrimination without opinion alignment. Which state emerges depends on both the strength and prevalence of the bias. These results show how simple local learning dynamics can generate qualitatively distinct forms of polarization and discrimination, underscoring the need for population-level safety analysis of multi-agent systems. They also suggest measurable order parameters for characterizing analogous collective states in human societies.
Oct 15, 2026

FRACTAL: A Self-Similar Multi-Agent Orchestration Architecture with Formal Communication, Convergence, and Depth Bounds

We present FRACTAL, a self-similar multi-agent architecture for recursive goal decomposition, in which the same five-component organizational pattern -- Orchestrator, Ensemble, Knowledge Ledger, Decision Maker, Meta-Observer -- recurs at every level of a decomposition tree. We make four formal contributions: (1) a communication bound showing intra-node cost is linear in ensemble size and round count (O(kr)) under a two-phase blind-proposal/stress-test protocol, versus quadratic cost for free-form debate, with an explicit, stated assumption on fixed evaluator count; (2) a two-mode orchestration criterion separating generative and evaluative phases via a measurable diversity-saturation threshold; (3) a supermajority convergence guarantee with explicit probability bounds at stated agreement levels, and a formal depth bound under an operationalized goal-complexity measure; (4) a Bayesian inter-layer escalation mechanism unifying hysteresis and contract-breach signaling under one posterior update. We illustrate the architecture's execution qualitatively on a worked example and a multi-layer case study; we do not report quantitative performance claims in this paper, and we explicitly discuss the formal and inductive-bias limitations of the model, including an unimplemented but architecture-compatible direction toward bounded self-improvement. We use "fractal" as an architectural metaphor for self-similarity, not a measured mathematical property. Empirical validation of the architecture's comparative performance is left to future work.
Oct 15, 2026

Robust Multi-Agent Pursuit with Preemptive Communication via Reachability-Based Control Barrier Functions

Safe multi-agent coordination typically assumes what real-world, deployed, resource-constrained robots cannot provide: continuous, perfect state sharing. Robust control strategies must be complemented with robust communication strategies to deliver resilient deployments. In this work, we propose a unified control/communication strategy that provides safe control to guarantee inter-agent safety under intermittent communication and demonstrate its effectiveness in a pursuit-evasion scenario. Each agent computes the reachable set of neighboring agents based on the last state information received, then solves for a safe control input based on control barrier functions to ensure agents avoid collision. We prove that inter-agent collision avoidance is guaranteed provided communication staleness remains bounded. As the reachable set inflates between state transmissions, each agent reasons about when to preemptively transmit its state information to neighboring agents based on novel metrics characterizing uncertainty risk and kinematic risk. We implement and simulate a variety of pursuit-evasion scenarios and show that preemptive communication reduces messages by 77.5% compared to periodic and event-triggered baselines with zero collisions.
Oct 15, 2026

Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems

The Agent Status Protocol (ASP) defines a lightweight way for heterogeneous AI agents to report their operational state to a status server, and for observers such as dashboards to receive that state as soon as it changes. Agents push small JSON events over HTTP POST; the server exposes the aggregated state to observers over Server-Sent Events (SSE). Because an agent that has crashed, hung or been compromised cannot be trusted to report its own failure, ASP does not rely on self-reports alone: the server infers liveness from missed heartbeats, can detect agents that are alive but no longer making progress, and accepts observations from supervisors, guardrails, operators and peers, some of which take precedence over what the agent says about itself while others are shown alongside it. ASP models state along independent dimensions (lifecycle, health, task, floor, governance), so that an agent can be, for example, online, degraded, working on a task and waiting for the floor at the same time. It reuses existing vocabularies: task states from the Agent2Agent (A2A) protocol, floor states from the Open Floor Protocol (OFP), and attribute conventions from the OpenTelemetry GenAI semantic conventions. This paper presents version 0.1 of ASP as a proposal, not as an approved standard. It is a working draft intended to open a discussion, and the authors invite comments, alternative proposals and independent implementations from the community.
Oct 15, 2026

Bias Control and Injection for Multi-Agent Aggregation

Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision should be trusted? Resolving such disagreements is difficult because agents' decisions are susceptible to non-semantic biases such as majority pressure and response-style preferences, which can obscure the quality of the underlying reasoning. Our analysis shows how bias can be both mitigated and exploited: bias control improves initial answer selection, while bias injection elicits decision instability that serves as a reliability signal. Building on these findings, we introduce a test-time aggregation framework that requires neither validation data nor prior knowledge of relative model strength. The framework implements bias control by presenting one style-normalized reasoning trace per distinct answer, and bias injection by placing each aggregating agent's initially selected answer in the minority. Overall, our framework achieves higher average accuracy and better token efficiency than competing non-oracle aggregation methods across three mathematical reasoning benchmarks and four heterogeneous LLM combinations. It also improves final-answer accuracy when applied to multi-agent debate and Mixture-of-Agents, without modifying their interaction or synthesis processes.
Oct 15, 2026

A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems

Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in scalability, adaptability, and collective performance. Decentralized approaches alleviate these bottlenecks by distributing coordination across agents, yet often leave responsibility for delegated dependencies and failure recovery unclear. To address this gap, we propose RCM, a responsibility-centered coordination mechanism that leverages commitments to couple task delegation with explicit responsibilities of the involved parties. Through recursive delegation, agents retain their upstream responsibilities while locally orchestrating downstream commitments, thereby preserving accountability across delegation chains, creating a network of local orchestration. We operationalize this mechanism locally through responsibility-constrained decision-making and a responsibility-oriented communication protocol (RCP), enabling agents to autonomously establish, manage, and terminate commitments. As agents act in parallel, their local actions continuously evolve the commitment graph, allowing global coordination to emerge and adapt toward a shared mission without centralized control. Experiments across reasoning, coding, and executable agent environments demonstrate that RCM outperforms strong centralized and decentralized coordination baselines by up to 18.7 points in task performance and 10.2 points in Responsibility, while improving failure and harm detection without task-specific training.
Oct 15, 2026

SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems

As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent incidents have already revealed unplanned coordination between agents, highlighting the safety implications of these interactions. Yet prior studies of agent negotiation often use stylized games and simulated bargaining, leaving open how these behaviors develop during sustained, long-horizon tasks. We propose SCARCE (Shared Compute ARena for Coding agEnts), a framework in which agents solve sequences of coding tasks under individual deadlines while negotiating access to a shared execution resource. This negotiation determines when and for how long they can inspect programs, compile code, and run tests. We find that agents spontaneously develop informal institutions: persistent rules and commitments grounded in reputation, reciprocity, and precedent. These arrangements, which we call institutional behaviors, carry across tasks and influence resource allocation, with agents sometimes forgoing immediate advantages to honor earlier agreements. We develop a 21-category taxonomy of negotiation strategies and emergent norms and use it to analyze eight models and audit more than 1,500 trajectories across different environmental settings. Among the models tested, newer frontier models exhibit more institutional behaviors than older or lightweight models. Alongside cooperation, we observe exclusionary coalitions and rare divide-and-conquer strategies. SCARCE provides a controlled setting for proactively and systematically auditing how these relationships emerge, shape access to resources, and affect the safety and coordination of multi-agent systems.
Oct 14, 2026

Feasibility Ceilings Before Learning: Sizing and Timing Bounds for Drone-Mesh Interception

A mesh of interceptors defending a fixed site must spread over the predicted arrival point of an approaching object. This is a recurring task in multi-agent robotics: N agents, each covering a disc of radius r, spread over a probability density so that a point drawn from it falls within some agent's disc. We give closed forms for the quantities that bound performance before any policy is chosen, and validate each by Monte Carlo. The uncertainty of a point predicted by extrapolating a noisy linear track follows from least-squares variance propagation plus a delta-method term for the uncertain arrival time, agreeing with simulation to within 1.8%. The coverage probability of a packed mesh admits a closed form accurate to 0.007 absolute, with a volumetric analogue. A naive area ratio misses a ceiling: while agents stay at least 2r apart, no mesh exceeds 90.69% coverage in the plane or 74.05% in a volume. This ceiling belongs to the separation constraint, not to the problem - permitting overlap substitutes Kershner's thinnest-covering density and removes it, the better regime above a crossover at p=0.80. Hexagonal packing is optimal among five arrangements; the centroidal-Voronoi configuration coverage control supplies reaches only half its coverage at small budgets. The Gaussian assumption is conservative under heavy tails and anisotropy but fragile under bias: a one-sigma aim-point offset costs 14 points of coverage. A repositioning team must also choose a commit time, and the admissible window can be empty. Against the applicable ceiling, analytic placement attains 85% of what the configuration permits while centralised PPO averages 15% over three trainer seeds, with a paired bootstrap against a null policy containing zero at every seed. We argue such ceilings should be computed before any learning experiment and quoted alongside every result.
Oct 14, 2026

ARIA: Runtime Inspection and Amendment for Multi-Agent Systems

In LLM-based multi-agent systems (MAS), a local mistake can propagate as other agents build on it, turning a correctable error into a failed task. Diagnosing completed runs or repeatedly re-executing them to search for corrections does not provide a learned policy for intervening while execution is still in progress. We present Agent Runtime Inspection and Amendment (ARIA), a framework for learning when and how to repair ongoing multi-agent executions. Our key intuition is to turn execution-verified repairs into reusable supervision, moving repair search into data construction and training so that a learned model can intervene at runtime without repeatedly testing alternatives. First, we collect over 24{,}000 successful and failed trajectories across four multi-agent frameworks, six benchmarks, and eight host models. From these trajectories, we construct the ARIA dataset, to our knowledge the first large-scale dataset pairing failed multi-agent trajectories with execution-verified repairs. It contains 3{,}953 verified repair pairs, each specifying what went wrong, where to intervene, and how execution should continue. Then, we develop the ARIA framework for MAS-agnostic runtime inspection and amendment, designed to integrate with any MAS that exposes execution trajectories and supports continuation replacement. Using verified repairs as training examples, we teach a compact model to recognize when intervention is needed and how to correct an ongoing run. The aim is to learn repair strategies that apply to related failures in new configurations, rather than merely reproduce individual corrections. Finally, the trained ARIA model demonstrates strong repair performance in both post-hoc and runtime settings, with generalization to unseen frameworks and host models. Our code is available at https://github.com/LabRAI/ARIA.
Oct 14, 2026

The Wealth of Agents: Scaling Agentic AI Across Developers

Today's agentic systems are typically designed, built, and deployed by single developers with full control over all participating agents. While this simplifies development, it limits the potential scale of agentic systems. We study multi-developer agentic systems (MDAs) which enable developers to collaboratively build agentic systems to push frontier capability beyond what any individual developer could achieve alone. We construct empirical and theoretical models of developers to compare MDAs with single-developer agentic systems (SDAs). On GAIA, a general assistant benchmark, a population of specialized developers whose individual agents do not exceed 35% accuracy reaches 70% when their agents are combined in an MDA. This MDA performs 12 percentage points above the median general-purpose SDA built with several times each specialist's development budget. Our theoretical models show how MDAs can incentivize specialization and encourage more efficient use of aggregated developer resources. Put together, our results make a preliminary case for MDAs as a new scaling axis by enabling developers with diverse capabilities and resources to advance agentic AI collaboratively.
Oct 14, 2026

A Strong Harness Narrows the Model Gap: A Comparative Evaluation for Legislative Document-to-XML Conversion

Legal-content reproduction requires matching the source exactly in section hierarchy, verbatim text, citations, and amendment spans; a dropped citation or mislabeled amendment carries into the products lawyers rely on. We report an industrial pipeline converting U.S. state legislation into strict, schema-constrained XML, and hypothesize that its accuracy comes from harness engineering, the deterministic tooling built around a model, more than the model itself. Our controlled ablation crosses three harnesses (zero-shot, a single tool-using agent, and a decomposed multi-agent pipeline) with three Claude models on 153 gold bills from two jurisdictions. The harness narrows the model gap: the weakest model in the full pipeline beats the strongest model alone (0.948 versus 0.806, paired bootstrap p less than 0.001). Because the two agentic harnesses share identical tools, their gap comes from orchestration: decomposition plus the persisted state and per-agent context it brings. Across four scored dimensions, the model spread at zero-shot (0.68 to 0.81) narrows to 0.95 at the full pipeline; the residual sits almost entirely in citation normalization, where the canonical identifier is retrieved from an external authority rather than generated from the weights, so a deterministic lookup tool supplies the exactness that a larger model does not.
Oct 14, 2026

When Extremists Enter LLM Societies: Investigating Extreme Behavior in Multi-Agent Systems

Large language model (LLM) agents increasingly serve as computational actors in multi-agent social simulations. While existing work emphasizes representative personas and average-case behavior, social science shows that persistent tail actors can disproportionately shape collective dynamics. We study this regularity in controlled LLM-based multi-agent systems (LLM-MAS). In these systems, such actors cannot be reduced to fixed scalar states: prompts, natural-language histories, and backbone generation mediate their behavior and influence. We first analyzed three properties of extremists in sociology and model the LLM extremist based on LLM-native perspective. We introduce EXAM, an EXtremist Agent Modeling framework that capable of configuring extremist agents for specific tasks and precisely controlling their population proportion, spatial distribution, interaction protocols, and measurement interfaces. Across four scenarios: congressional election, financial crisis, epidemic public opinion, and iterated prisoner's dilemma, we observe that small persistent tail groups produce measurable, backbone- and scenario-dependent collective shifts. EXAM shows how this social-science regularity manifests through language-mediated mechanisms specific to LLM-based social simulation.
Oct 14, 2026

Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems

Recent work lets LLM agents evolve their own harness, up to the team itself. Yet in human groups, the same abilities achieve different outcomes under different social conditions. Borrowing the notion of scaffolding from developmental psychology, we investigate whether the social scaffolding of a self-evolving multi-agent system (MAS), namely its team composition and structure of interdependence (e.g., collaboration, conformity, or competition), shapes how the team evolves. We present AGORA (Agents Growing through Organization and Relational Arrangements), a framework that varies the two axes independently across three evolution mechanisms. Across web search, codebase understanding, and document QA, we find that (1) evolution alone rarely helps, while the right scaffolding surpasses a strong agent evolved alone by up to 25 points; (2) it does so by moving authority to the most capable member while the others step back; and (3) this member, having grown within the team, outperforms the same model alone. Designing a self-evolving MAS thus requires designing its social scaffolding, which shapes not only how its agents learn, but who gets to lead.
Oct 14, 2026

PFedMA: Who Should Join Next as Federated Multi-Agent Orchestration Evolves?

Federated Multi-Agent Systems (FedMAS) offer a promising paradigm for collaborative reasoning among LLM-based agents while keeping raw client data decentralized. However, reliable multi-round collaboration remains challenging. Agent selection must take into consideration evolving task requirements and the agent's historical reliability, while privacy rules must adapt to changing collaboration contexts and meet the client's personalized needs. To address these challenges, we propose PFedMA, a federated multi-agent framework for feedback driven multi-round collaboration under heterogeneous privacy requirements. Across rounds, PFedMA maintains historical capability and reliability states to guide agent selection, evaluates task responses before aggregation, and refines subsequent queries according to accumulated collaboration feedback. PFedMA enables bidirectional local to global and global to local private rule evolution across heterogeneous clients. Clients generalize locally updated privacy rules and selectively incorporate globally maintained rules, thereby facilitating cross-client privacy rule evolution while preserving personalized constraints. Extensive experiments across reasoning, privacy sensitive, and adversarial settings show that PFedMA improves task performance, reduces measured privacy leakage, and improves system robustness.
Oct 14, 2026

Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States

Agents are increasingly interacting with other agents that act for different principals (people or organizations on whose behalf they work), such as a buyer's personal agent negotiating with an enterprise's seller agent. In such agent-to-agent (A2A) scenarios, each agent has its own environment and holds information and authority that the other cannot see. Moreover, the interests of each agent may be aligned (cooperative), partly aligned (mixed-motive), or opposed (competitive). Existing multi-agent system failure studies assume one orchestrator, shared workspace, or single principal. We ask how A2A systems fail when these assumptions are removed. We study more than 2,500 recorded runs of A2A systems built from different agent harnesses and models, spanning 488 scenarios across eight families (legal, CRM, security, commerce, etc.). From these traces, we derive A2A^2-Failures, a taxonomy of 20 A2A failure modes in four categories: (i) discovery and delegation, (ii) grounding and record consistency, (iii) verification, and (iv) conduct and fidelity. Three findings hold across every harness, model, and scenario studied: (1) discovery and interaction are driven by the phrasing of the task rather than the availability of peer agents; (2) no agent verifies a peer's factual claim on its own initiative, so an A2A system inherits the reliability of its least reliable participant unless the protocol or mechanism performs the check; and (3) the aggregate outcome score credits the agent completing the task while staying blind to the coordination, verification, and conduct failures beneath it, so A2A systems must be evaluated per agent, against each agent's own principal. We release the run logs behind the taxonomy at https://huggingface.co/datasets/a2a-salesforce/a2-failures.
Oct 13, 2026

CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation Pipeline

Vision-language models (VLMs) are increasingly deployed in multi-agent systems to automate complex computer-use workflows, yet existing benchmarks mostly assume consistent, cooperative environments. In contrast, real-world collaboration rarely runs on consistent information: peer or sub-agents frequently report outdated states, issue contradictory instructions, or compete over shared permissions and files, forcing agents to check others' outputs and verify ground truth in the environment. Evaluating such conflict resolution remains challenging: manual authoring cannot scale across complex systems, while unconstrained LLM generation produces narrative drift, answer leakage, and unsatisfiable rubrics. We introduce CLASHarness (Conflict-Loaded Agent Scenario Harness), a controllable framework for generating verifiable multi-agent conflicts in computer use, with a benchmark of 600 multi-round tasks. By combining hierarchical scenario planning with an eight-step verified micro-pipeline, CLASHarness pre-commits decisive visual facts before rendering and compiles hybrid code and semantic graders directly from executed reference trajectories, guaranteeing every task is solvable by construction. Evaluating 15 frontier models on CLASHarness reveals three core bottlenecks. First, when sub-agent outputs conflict with the environment, weaker models blindly follow misleading information, whereas stronger models inspect visual evidence to verify ground truth. Second, resolving conflicts is much harder than finding them: while agents can spot inconsistencies, actively fixing system state drops task success significantly. Third, coordination protocols remain a universal bottleneck: even frontier models fail over 58% of closing actions, often forgetting to release shared locks or hand off tasks. CLASHarness provides a scalable, verifiable foundation for building reliable multi-agent systems.
Oct 13, 2026

Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams

Coordinators that act on what they infer about teammates are usually certified by the accuracy of those inferences. We argue that accuracy is the wrong certificate, for two reasons. First, the accuracy needed to act depends on what a wrong action costs, so the bar belongs to the deployment, not the module. Second, a module's errors are rarely independent, and dependence has a sign: positively associated errors help where their damage overlaps and hurt where it compounds, so an accuracy threshold fails in a predictable direction, and once wrong beliefs interact and can do harm, no rule based on accuracy is right for every module. We test these predictions in task assignment, Level-Based Foraging and Hanabi, with injected errors, trained and Bayesian modules and five language models, and in human judgments. Accuracy fails in both directions, approving harmful language-model deployments in Hanabi, where shared errors compound, and rejecting beneficial ones in task assignment, where costly errors are rare. In our tasks it also buys far less redundancy than independence predicts: from GPT-5.4-mini to Claude Opus 5.5, error on teammates the models have evidence about falls from 32% to 11%, but the chance that all three observers misread one falls only from 16% to 9% (independence: 3.4% to 0.15%). We propose certifying the deployment, with a Blind-Spot Gate that prices error costs, pairwise interactions and measured dependence without deploying the module. On held-out data from the cells it was developed on, it makes no significant false approval in 20 splits (accuracy: 3.2 per split), and in preregistered tests on modules it was not developed on, it recovers what accuracy rejects (seven classifiers: regret 0.004 against 0.479) and catches what accuracy approves (a Bayesian module: significant false approvals in 17 of 20 splits for accuracy, 1 for the gate).
Oct 13, 2026

On Symmetry for Characterizing Agent Heterogeneity in Multi-Agent Systems

Understanding agent heterogeneity can inform the design of shared and agent-specific policy representations, however existing criteria provide no unified structural test. We study finite-horizon POSGs and define a type-compatible transformation as a policy-evaluation symmetry when complete policy evaluation commutes with it for every decentralized behavioral policy. Policy-evaluation symmetries form a group for which agent orbits define structural agent types. This classification does not depend on the particular policy chosen or the distribution of initial states. We prove that every componentwise environment automorphism is a policy-evaluation symmetry, but that the converse does not hold. Applying the framework to cooperative Dec-POMDPs shows that agents can belong to different structural types even when they share a common reward. For prescribed weighted reward aggregation, we derive an exact value identity and sufficient conditions for the resulting Dec-POMDP to inherit the policy-evaluation symmetries of the source POSG. Finally, we give sufficient conditions under which repeated model factorizations induce policy-evaluation symmetry, and show that preserving an optimal Boltzmann policy set neither implies nor follows from this symmetry in general.
Oct 13, 2026

Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagreement or reasoning quality. We present an adaptive multi-agent controller (ADMA) that learns continuous policies for proposal, challenge, arbitration, and coordination while keeping the task model frozen. Shared trace features describe quality, agreement, and progress, while role-specific features support decentralized control during inference. One controller trained on legal and financial reasoning is transferred without policy updates to four textual and multimodal benchmarks and two successive task-model versions. With Qwen3.5 held fixed, ADMA-Full improves accuracy by 6.2-14.2 percentage points over Direct and by 2.8-3.0 points over ADMA-Fixed. Paired bootstrap ranges for the Full-Fixed comparison are positive on three tasks. Outcome decompositions show that recoveries exceed introduced errors, while process assessment records fewer false-consensus events and more supported correct outcomes. Transfer to Qwen3.6 remains task dependent, which bounds the generality of the learned policy. Median token and latency ratios are 14.3-18.7 and 7.8-16.5 relative to Direct. These results show that adaptive deliberation can improve fixed-model recognition when its task-dependent gains justify the additional computation.
Oct 13, 2026

Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes

Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor different DoF configurations, while atomic-target conditions are more consistent across runs. In-domain retained experience brings the two branch profiles closer together. The same controlled sweep reveals a task-dependent coordination landscape: some domains exhibit higher-performing configurations, whereas others show flatter responses and no single configuration dominates across domains. In five of the six evaluated state, an intermediate DoF configuration achieves higher mean accuracy than both endpoints, demonstrating the value of exploring the coordination space between them. Together, these findings provide empirical guidance for studying and designing intermediate coordination regimes in LLM-based MAS.
Oct 12, 2026

OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains

Large language model (LLM)-based multi-agent systems are increasingly applied across diverse domains, yet different applications require different forms of agent organization. Existing studies typically adopt predefined organizations, such as Star, Chain, and Tree, or learn communication graphs to improve performance on specific tasks. However, these methods are largely designed and evaluated within a limited set of application domains, providing little understanding of whether an organization effective in one domain remains suitable for others with different collaboration requirements. We present OpenDGO, a controlled benchmark and analysis framework covering six real-world domains and three collaboration settings: Sequential Dependency, Parallel Decomposition, and Information Integration. Under matched tasks, agents, tools, and resource limits, OpenDGO compares fixed and learned organizations while separately examining communication graphs, role assignments, input assignments, resource budgets, and component failures. Our results show that there is no ``one-organization-for-all'' solution: preferred organizations vary across applications, and even the same communication graph can yield different outcomes under different role and input assignments. These findings highlight the need for application-dependent organization design, aiming to understand which organization is suitable for a given application, under what conditions, and why.
Oct 12, 2026

AgentCue: Statistical Summaries for Guiding Decentralized Multi-Agent Self-Organization

Multi-agent systems (MAS) combine multiple agents to solve complex tasks, and recent MAS scale to more than a thousand agents. At this scale, decentralized MAS remove the central orchestrator that assigns sub-tasks, and the agents, which we call workers, self-organize through their own choices of sub-tasks and collaborators on a shared board. As workers keep adding participation and collaboration records, however, the information explodes: workers spend more and more effort on reading the records of other workers, and self-organization loses efficiency. In the statistical view, we represent the execution history of an MAS by two continually updated networks, a collaboration network among workers and a participation network between workers and task types. We then propose AgentCue, a method built on a new latent space model that places workers and task types in a shared latent space. At each checkpoint, that is, after a fixed number of sessions of the workers, the estimated parameters of the latent space model form a compact and interpretable statistical summary, and workers use the statistical summary to choose sub-tasks and collaborators without repeated searches of the shared board. We also provide theoretical results on model identifiability and estimation accuracy for continually updated networks. Experiments on three benchmarks for cross-document reasoning, mathematical theorem proving, and software patch generation show that AgentCue improves the efficiency, accuracy, and interpretability of self-organization.
Oct 12, 2026

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination

Existing large language model (LLM) based multi-agent systems have been shown to scale poorly, and we identify three problems: reading burden that grows with the group, useful information diluted by shared work of unknown quality, and fragility to failed agents. We argue that the problems are largely due to agent-centric designs: the coordination structure is wired into fixed workflows, central coordinators, or peer-to-peer messaging, and recent blackboard-style methods that move the coordination into a shared medium relieve only the last problem. To close the gaps, we build ScaleMAS, where asynchronous agents interact with a shared datastore of linked messages via three operations: publishing messages with optional references to earlier ones that they build on, searching for messages by content, and visiting messages by address. Search returns at most kk messages, so an agent's read stays bounded at any group size; results are ranked by relevance and by how often they are cited, which we find to be an effective proxy for quality; and messages persist after their producers leave, so the group carries on when individual agents fail. Across four agentic tasks, ScaleMAS outperforms agent-centric and blackboard-style baselines at lower inference compute, continues to scale up to 128 agents, and tolerates losing agents midway.
Oct 11, 2026

Mind Your Own Role: Reducing Role Overstepping for Effective and Efficient Multi-Agent Collaboration via Dynamic Role Activation Steering

Multi-Agent Systems (MAS) have shown strong capability in solving complex tasks by assigning different agents specialized roles and corresponding subtasks. However, agents may overstep their assigned responsibilities and perform subtasks belonging to other roles, which can disrupt workflow, reduce system efficiency, and degrade task performance. To address this issue, we investigate role-related patterns in the model's internal activation space and uncover two key observations: (i) role instructions induce consistent directional shifts in activation space, and (ii) role-adherent and role-overstepping trajectories exhibit distinct activation patterns. Based on these observations, we propose Dynamic Role Activation Steering (DRAS), a lightweight and effective inference-time activation intervention approach to reduce role overstepping in multi-agent collaboration. Specifically, DRAS constructs a role steering vector and a lightweight role-overstepping detector for each role. During LLM generation, the detector estimates the probability of role overstepping from the current activation state, and DRAS dynamically adjusts the steering strength accordingly to guide the agent toward its assigned responsibilities. Experimental results show that DRAS effectively reduces the number of role-overstepping trajectories by up to 86.6% compared with Vanilla MAS, thereby improving task quality score by 10.0%--11.1%, achieving a 1.50×\times--1.61×\times task-completion speedup, and reducing token consumption by 26.8%--38.7%.
Oct 10, 2026

HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems

AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, while keeping foundation models frozen. Existing studies focus on single agents, leaving joint harness evolution in multi-agent systems (MAS) underexplored. A single global optimizer faces growing context and workload as the system scales, while access restrictions may prevent sharing agent internals or system-wide feedback. We propose HarnessNet, a framework for hierarchical harness evolution in MAS. Its basic unit, Agentron, comprises an evolvable forward harness, a foundation model, and a local optimizer that can observe and modify only that harness. Agentrons form a layered graph through which environment feedback propagates backward, with upstream optimizers receiving node-specific feedback from the downstream layer. This decomposes joint harness evolution into smaller, coordinated tasks with separate contexts, reducing individual optimizers' context and workload while keeping access local. Optimizers need not access all agent trajectories or raw environment feedback. Experiments on AgentBench with multiple foundation models demonstrate the feasibility of training HarnessNet. Compared with a single global optimizer, HarnessNet achieves comparable performance gains while respecting local privacy and requiring fewer tokens and less time per optimizer call. A migration study shows that the evolved harnesses remain jointly effective after replacing the foundation models, suggesting transferability across models.
Oct 10, 2026

Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry

A language model's ability to solve a task individually does not ensure that a team can solve it under unequal access to information and communication. SANZARU examines this gap through cooperative bomb-defusal puzzles adapted from BOMBANANA! (Lefto Studio, 2026). Task information and action authority are divided among three agents: one cannot hear, another cannot speak, and the third cannot see. The benchmark contains 120 puzzle instances across seven families, each targeting a distinct coordination ability. Across 1512 episodes, 7 models achieve an overall success rate of 49%, ranging from 20% to 86% under the evaluated configurations. Teams develop or adopt diverse communication protocols, from simple gesture codes to Morse and encodings of entire manuals. Yet trace analysis attributes about 60% of 771 team losses to communication, and agents attempt to use channels unavailable to their teammates despite explicit role instructions. Together, task outcomes and interaction traces enable evaluation of both collaborative performance and perspective taking throughout cooperation. The benchmark is available at https://github.com/markli404/sanzaru-benchmark.
Oct 10, 2026

Conflict-Aware Autonomous Resource Orchestration for 5G Edge Slicing Using Multi-Agent Systems and LLMs

5G edge network slicing must reconcile two coupled requirements: understanding high-level operator intent and reallocating scarce computing and bandwidth resources under dynamic contention. Centralized optimization can face computational and responsiveness challenges under rapidly changing edge contention, and Multi-Agent System (MAS)-based auctions can support resource arbitration but still depend on operator-defined economic parameters and priorities. Embedding a Large Language Model (LLM) directly in a recurring control loop, by contrast, may introduce non-negligible inference latency and non-deterministic behavior. This paper proposes a two-timescale architecture that addresses this gap: an LLM-based Strategist translates natural-language network intents into economic policy parameters (budget, income, and bidding-aggressiveness) at the macro scale, while a deterministic, Vickrey-inspired second-price mechanism run by SPADE-based slice agents resolves recurring resource contention at the operational scale, with the resulting allocations enforced by patching Kubernetes CPU limits and Calico CNI bandwidth annotations directly on User Plane Function pods. We evaluate the architecture end-to-end on a real Kubernetes/Open5GS edge cluster across two complementary scenarios, each repeated 30 times: a Smart-City scenario, in which natural-language public-safety intents propagate into measurable changes in slice bids and bandwidth allocations within a few auction rounds, and a Hierarchical-slicing scenario, in which the mechanism provides priority-dependent resource and QoE differentiation, adapts to abrupt demand changes, and preserves configured minimum guarantees while maintaining near-complete allocation of the shared bandwidth pool.