Multi-Agent Coordination

Ask about this topic

Overview

Multi-agent coordination studies how agents with partial information, different capabilities, or competing incentives can act together in settings such as robot teams, traffic networks, resource allocation, and language-model workflows. Common approaches include decentralized and centralized multi-agent reinforcement learning, game-theoretic planning, role and task assignment, and communication through messages, shared memory, or learned coordination policies. Recent work also develops orchestration protocols and benchmarks for language-model agents, measuring not just task success but information use, role adherence, safety, and coordination failures. A central tension is that communication and additional agents can improve complex teamwork but also introduce overhead, propagate errors, or make performance worse; individual reasoning ability alone does not guarantee effective cooperation.

Latest papers

CardsList

520 papers84 papers in the last four weeks, up 91% on the four weeks before. 0.5% of all new papers.

Oct 29, 2026

EvoTeam: Multi-Agent Collaboration via Evolving Teams

LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team collaboration. Recent studies have therefore extended evolution to the collaboration level, using collective execution experience to adjust team organization, and inter-agent interactions. Nevertheless, evolving collaboration across heterogeneous tasks remains challenging, as existing approaches often constrain team reorganization within a shared structure and reuse interaction rules across incompatible team contexts. In this paper, we propose EvoTeam, a collaboration-centric evolution framework that jointly evolves team organization, interaction rules, and individual agent skills through execution experience. It maintains a library of reusable teams, selecting or creating agent teams and guiding collaboration through team-specific interaction rules. Collaboration experience accumulates within compatible team contexts, while individual skills remain reusable across teams. Experiments across four benchmarks demonstrate its effectiveness. Our code is available at https://github.com/DEEP-JLU/EvoTeam.

Qinuo Cao, Xin He, Dianxuan Fu +7

Jilin University · Nanjing University of Science and Technology · Shanghai AI Lab

Multi-Agent CollaborationMulti-Agent SystemsMulti-Agent LLM SystemsMulti-Agent CoordinationSelf-Evolving Agents
AskPDF
Oct 27, 2026

Multi-Agent Reinforcement Learning for Global Climate Policy Cooperation

International climate policy requires coordination among countries whose mitigation decisions impose local costs but generate global benefits. Classical game-theoretic and integrated assessment approaches can study these incentives, but typically rely on prescribed behavioural assumptions or equilibrium concepts. Recent work has therefore explored Multi-Agent Reinforcement Learning as a way to model climate-policy cooperation as an emergent outcome of repeated strategic interaction. We extend an existing MARL climate framework with a multi-stage negotiation mechanism in which agents propose agreements, accept or reject commitments, and face penalties for non-compliance. This allows us to study how agreement design affects learned mitigation behaviour, compliance, and climate outcomes. In an idealized setting with four homogeneous agents, we find that non-binding agreements do little to overcome free-riding, while moderate non-compliance penalties improve cooperation and reduce warming. However, excessively strong penalties discourage ambitious commitments, revealing a trade-off between enforcement and participation. We position the framework as a methodological contribution for testing agreement design rather than a predictive model of real negotiations.

Anne Moll-Elsborg, Oskar Bohn Lassen, Francisco Camara Pereira

Technical University of Denmark, Department of Technology, Management and Economics

Multi-Agent CoordinationMulti-Agent Reinforcement LearningMulti-Agent Negotiation
AskPDF
Oct 26, 2026

Compatibility and future-proof testing for multi-agent systems

Independently developed autonomous agents, such as autonomous vehicles, must guarantee joint compatibility, such as safety and task-completion requirements, when they operate in a shared environment. Existing methods require a centrally designed specification, or interaction mechanism before any agent is deployed. However, such centralized design is unrealistic when agent designs are confidential to their developers, and it is not flexible enough to accommodate future agent designs. We study a bi-level structure in which a regulator coordinates developers by publishing seed agents, and each developer independently tests its agent to ensure that it is compatible with every seed-compatible agent, a property we call future-proofness. Under this structure, joint compatibility is guaranteed for any agents that are designed and tested independently, without any coordination with each other. In this work, we first formulate compatibility for general multi-agent systems and show why it is not trivially implied by seed-compatibility. We then characterize the future-proof agents as the closure of the seed and show that this closure is monotone in the seed. Finally, we study a class of executable tests that involve interaction with the seed alone, and we ask to what extent such tests can distinguish the future-proof agents.

Yueshan Li, Lorenzo Fiaschi, Andrea Censi +1

Institute for Dynamic Systems and Control, ETH Zurich, Zurich, Switzerland

Multi-Agent SystemsMulti-Agent Coordination
AskPDF
Oct 26, 2026

The Inbox as a Coordination Primitive for LLM Agent Societies

Language-model agents increasingly coordinate in large groups, and current agent protocols focus on delivering messages. For these agents, however, the scarce resource is not delivery but reading: every message costs tokens, and the context is finite. Current infrastructure works by push: the sender decides when a message enters the recipient's context, so the recipient reads in arrival order and drops the oldest messages once its context is full. We study the alternative, pull, in which messages wait in an inbox outside the context and the recipient's own rules decide what it reads and keeps. We argue that the inbox is a coordination primitive: each agent sets its rules privately, and those rules decide whether other agents' requests reach it. In simulated societies of up to 16,000 agents, with every decision an LLM judgment, we report three findings. First, push fails as an agent takes part in more coordination at once: an agent leading 20 negotiations with a full memory proposes options already rejected 97% of the time, because it has dropped the oldest replies. Second, an inbox is necessary under heavy, noisy traffic. Where first come, first read misses every request, an inbox that first reads messages carrying a refundable deposit still finds about 60% of the agents a request needs, at every size from 1,000 to 16,000. On a real email network, losses compound: when half the agents adopt such an inbox, forwarded search recovers only 5% of full adoption, against 42% for one-hop search. Third, an inbox comprises four decisions (what to read, what to keep, what a sender pays, and what a reply may say), and the best rule for each depends on the traffic and the agent's role. Multi-agent coordination under load requires an inbox layer designed for the traffic each agent receives.

Karthik Sreedhar, Leo Yuan, Pradyumna Chari +1

MIT Media Lab, Cambridge, USA

Multi-Agent CoordinationMulti-Agent CommunicationMulti-Agent LLMsLLM Agent Orchestration
AskPDF
Oct 26, 2026

PolicyMediator: Multi-Regional Policy Learning through Mediation Agents with Evolving Skills in OPC Ecosystems

One-person companies (OPCs) are emerging enterprises operated by individual entrepreneurs through digital platforms and LLM-based AI agents. These highly skilled entrepreneurs are characterized by being digital nomads, with limited reliance on local ecosystems. Governments in China use distinct regional support policies to attract mobile OPCs, turning local support into a cross-regional coordination problem. OPCs compare regions to maximize their own utility, but imperfect policy perceptions may cause them to reject otherwise suitable locations. Existing policy-learning methods optimize resources under fixed perceptions, while consensus-formation methods aggregate views without feeding cognitive changes back into policy learning. This disconnect produces mismatched location choices and inefficient regional policy adjustment. We introduce PolicyMediator, a cognition-constrained leader-multi-follower Stackelberg framework with bilateral mediation. The mediator explains verified policies to OPCs to build awareness and trust, and reports their needs and unresolved concerns to governments for policy learning. Its self-evolving skills retain, revise, or prune strategies using verification, allocation, capacity, and objective trajectories rather than mediation success alone. Across six-region simulations in China with five OPC types, five scenarios, and three OPC-simulator backbones, PolicyMediator ranks first in all 15 OPC-backbone--scenario combinations. Over the eight-baseline mean, it improves the aggregate government objective, combining economic performance, employment benefit, and policy-access equality, by 42.4% and average OPC utility by 40.9%.

Jie Li, Bin Guo, Georgina Curto +3

Northwestern Polytechnical University, Xi’an, China · United Nations University Institute in Macau, Macau, China

Policy LearningPolicy OptimizationMulti-Agent CoordinationMulti-Agent Negotiation
AskPDF
Oct 26, 2026

Centralized Critics for N-Agent Ad Hoc Teamwork

Centralized training with decentralized execution (CTDE) has become the dominant paradigm in multi-agent reinforcement learning (MARL), motivating extensive study of what privileged information should be made available to the critic during training. While prior work has examined the role of global state in fully cooperative settings, the design of centralized critics for N-agent ad hoc teamwork - in which dynamically varying set of learning agents must coordinate with an arbitrary set of uncontrolled teammates drawn from an unknown distribution - remains poorly understood. We study this question by comparing two natural classes of advantage estimators: controlled history estimators, which condition only on the observation and action histories of the learner's own agents, and joint history estimators, which additionally condition on the histories of the uncontrolled teammates. We prove that both estimators are unbiased and characterize the conditions under which the joint history estimate attains strictly lower variance than its controlled counterpart. Empirically, joint history critics match or outperform controlled history critics across a range of NAHT tasks, yielding improved sample efficiency and final returns. Together, these results provide both a theoretical justification and an empirical recommendation for incorporating uncontrolled agent histories into centralized critics for N-agent ad hoc teamwork.

Andrew McAlinden, Caroline Wang, Steven Shi +3

Ad Hoc TeamworkMulti-Agent CoordinationCooperative MARLCentralized Training with Decentralized Execution
AskPDF
Oct 26, 2026

Networked Humanoid Intelligence: Communication, Coordination, Collaboration, and Social Interaction

Humanoid robots are moving from laboratory platforms toward connected fleets that share workspaces, infrastructure, tasks, and knowledge with other robots and humans. As deployments grow, the operation and improvement of each humanoid depend on information exchanged across the network. However, existing research has largely studied humanoids as individual systems. This survey examines networked humanoid intelligence through four functions of information exchange: communication, coordination, collaboration, and social intelligence with human interaction. We first establish the foundations of networked humanoid systems, define the question addressed by each function, and connect them through a common factory scenario. We review the literature along six dimensions: interaction architecture, exchanged information, physical coupling, operating timescale, system scale, and embodiment. We separate results obtained with physical and simulated humanoids from those based on other robotic platforms or disembodied agents, because the latter do not fully capture humanoid-specific constraints such as balance, whole-body motion, contact, and physical interaction. We examine hardware, datasets, and benchmarks, and distinguish risks handled locally from those networking introduces, such as stale information or unsafe knowledge propagation. Finally, we identify open problems in control-aware networking, compact body-centric messages, physically grounded coordination, network- and embodiment-aware knowledge sharing, fleet-level social consistency, and accountable human oversight.

Loc X. Nguyen, Huy Q. Le, Ji Su Yoon +3

School of Computing, Kyung Hee University, Republic of Korea · The University of Sydney, Australia

Humanoid RoboticsMulti-Agent CommunicationMulti-Agent CoordinationHuman-Robot CollaborationHuman-Robot Interaction
AskPDF
Oct 26, 2026

CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems

Multi-agent systems (MAS) require both effective coordination and specialized task execution. Existing prompt optimization approaches typically couple these functions within agent-specific prompts. We introduce Coordinator-Executor Prompt Optimization (CEPO), a general framework for improving prompt optimization in MAS. CEPO separates system-level coordination from agent-level execution through a shared coordinator prompt and agent-specific executor prompts, and guides their updates according to their respective roles. This structure allows shared coordination rules to be refined consistently across agents while keeping execution instructions separately adjustable. CEPO provides the prompt structure and optimization guidance, while existing prompt optimizers perform the underlying search. Extensive experiments spanning 11 benchmarks across four domains demonstrate that applying CEPO to four existing prompt optimizers consistently improves their performance. Ablations and qualitative analyses support the proposed design, while controlled studies on a document-understanding MAS further demonstrate improved optimization budget efficiency and performance scaling with the number of agents.

Jongha Kim, Seohyun Lee, Jonathan Minho Chung +2

Korea University · KAIST · Google Cloud AI Research

Prompt OptimizationMulti-Agent System OptimizationMulti-Agent Coordination
AskPDF
Oct 25, 2026

The Coordination Tax and the Heterogeneity Dividend: Break-Even Conditions for Multi-Agent LLM Pipelines

Multi-agent LLM pipelines built on interoperability protocols such as the Open Floor Protocol (OFP) or A2A are usually justified on capability grounds, with their runtime cost treated as an overhead of unknown size. Comparing such a pipeline with one model call is underspecified, because a pipeline can give each role a different model. We give a closed-form model that sets the coordination tax (decomposition overhead plus per-handoff protocol cost) against the heterogeneity dividend from routing work to a cheaper model, with a break-even threshold and a feasibility bound, α<1/rα< 1/r, and measure every term, with OFP as the protocol under test, on 135 HumanEval and ClassEval tasks in 2430 runs of six architectures with Claude Opus 5.5 and Haiku 5.5. The protocol adds 7.2 ms per handoff, 0.11% of pipeline wall time. Decomposition does not pay on these tasks: a planner-coder-reviewer pipeline costs 3.22x as much as a single strong call, takes 3.24x as long, and solves no more tasks. Moving planner and reviewer to the cheap model cuts the pipeline's cost to 0.39x but changes pass@1 by -6.7 points, leaving it dearer, slower and less accurate than the single call, and the break-even forecast misses by -19% because the cheap roles inflate token volume. The saving lies in choosing a model per task instead: an oracle choice between the two single calls solves 94.3% of runs at half the strong call's cost per solved task.

Andreas Zettl, Diego Gosmar

Member, VoiceInteroperability.ai Linux Foundation AI & Data Berlin, Germany · Member, VoiceInteroperability.ai Linux Foundation AI & Data Turin, Italy

Multi-Agent LLMsLLM Agent EfficiencyMulti-Agent CoordinationLLM Routing
AskPDF
Oct 24, 2026

Collective Collaboration of Recursive Autonomous Agents

Smart factories must translate order-level objectives into production tasks at multiple scales and combine the capabilities of individual units into an overall delivery capability. To address repeated adaptation of organizational mechanisms across equipment, workshops, and factories, as well as coordination across levels under changing production conditions, this paper develops a framework for the collective collaboration of recursive autonomous agents (RAAs). A common task and capability interface supports the recursive decomposition of production objectives from the top down and the aggregation of conditional capabilities through peer collaboration from the bottom up. Composite units can therefore participate in higher-level organizations as agents of the same kind. We formulate organizational models for leaf and composite units, specify interface closure under composition and conditions for finite task expansion, and develop operational mechanisms linking task decomposition, resource commitments, result aggregation, and coordination within the scope affected by change. A production network integrating machining, inspection, and logistics across multiple workshops illustrates how a common organizational kernel is instantiated at the equipment-service, workshop, and factory scales. The framework connects recursive organization with explicit task responsibilities, capability conditions, and execution interfaces for manufacturing systems.

Ziqing Zhou, Linqiang Hu, Yuning Chen +4

Multi-Agent CollaborationMulti-Agent SystemsMulti-Agent CoordinationSmart ManufacturingHierarchical Planning
AskPDF
Oct 23, 2026

Coral Discovery: The Division of Cognitive Labor in Autonomous Research

A research community is only as strong as the way it divides its cognitive labour. The philosopher Philip Kitcher argued that researchers should not all pursue the most promising approach. Credit rules, not a central plan, keep some of them on other lines. We bring this question to autonomous research, where Large Language Model agents improve programs against a deterministic grader. Agents that share only a score follow the leader and converge onto one approach. Coral Discovery gives the community a direction board. A verifier labels every attempt with a direction, the mechanism earning the score, and a method, one change within it. Per direction, the board tracks how much each eval improves the score, adds an exploration bonus for little-tried directions, prices the option of opening a new direction, and suggests how many agents each direction deserves. Credit is earned against a direction's own best, so a lagging direction keeps its agents. Agents finish their lines, then treat the board as advice. We test on nine tasks with the same model and budget, without grader access except for Kernel. Coral Discovery beats the strongest open autonomous multi-agent system on 6 tasks, ties on 1, and loses on 2. Against published numbers, it is best or tied on 4. It improves the reported Kernel result from 1103 to 1095 cycles and passes 1103 at eval 275, under half of the 596 used before. It sets a new Polyominoes state of the art, 91.78 against 87.0. Direction labels show that the leading scores rest on directions a score-only community never entered. Code will be released shortly.

Xinxing Ren, Qianbo Zang, Ziyan Wang +9

Coral AI Labs · Università di Trento · Harvard University +3

Autonomous Research AgentsMulti-Agent CoordinationAutomated Algorithm Discovery
AskPDF
Oct 23, 2026

Neuromorphic Decision Dynamics for Deadlock-free Safe Navigation in Congested Environments

Safe navigation in congested environments requires both collision avoidance and coordinated passage. We introduce neuromorphic decision dynamics (NDD), a decentralized, event-based controller, that provides navigation in congested spaces with guarantees on safety, liveness, robustness, and scalability. NDD makes safe-and-live deconfliction a controllable, locally tunable emergent property of local agent interactions, without requiring communication, preassigned priorities, models of neighbors' objectives or future actions, or estimates of group size or global network properties. By design, NDD couples the dynamics of internal decision and attention states with changing physical states and locally observed relative motion. Each agent continuously modulates its speed along its prescribed path, responding as soon and as much as conflict resolution requires. Agents self-organize into disjoint, locally engaged groups that resolve conflicts concurrently. When any group's conflict becomes safety-critical, decision-action feedback destabilizes collective indecision, and coordinated conflict-resolution emerges that stabilizes a safe traversal order within the group. Order persists as conflicts clear, but groups may split or merge as agents autonomously adapt to new conflicts and those with resolved conflicts resume their nominal motion. We derive explicit conditions on sensing range, feedback gains, response time scales, and actuation limits that guarantee collision avoidance and traversal-order formation in finite time with no deadlock or livelock for finite, heterogeneous agent populations of arbitrary, changing size. Computational cost scales with the number of local interactions sensed by each agent. Large-scale simulations, comparisons with existing approaches, and hardware experiments demonstrate NDD in complex congested scenarios and validate its scalability.

Himani Sinhmar, Vaibhav Srivastava, Naomi Ehrich Leonard

Department of Mechanical and Aerospace Engineering, Princeton University, NJ, USA. · Department of Electrical and Computer Engineering, Michigan State University, MI, USA.

Decentralized Multi-Agent Motion PlanningMulti-Agent CoordinationCollision AvoidanceEmergent Behavior in Multi-Agent Systems
AskPDF
Oct 23, 2026

The Butterfly Defects: Tracing Cooperation in LLM Agent Networks

As large language models (LLMs) increasingly operate as interconnected agents, a fundamental question emerges: does individual cooperation translate into collective cooperation? We investigate this question through the Iterated Prisoner's Dilemma (IPD), moving from dyadic interactions to homogeneous and heterogeneous networks of open-weight LLMs. Our findings reveal that cooperation is highly sensitive to model composition and seemingly minor linguistic changes. Models that cooperate with identical peers can shift toward defection in mixed populations. A simple uncertainty cue can increase or decrease cooperation, redistribute costs, and affect unexposed agents several hops away. Even reversing action-label order can dramatically alter behavior, with uncertainty framing sometimes amplifying this sensitivity. Together, these findings challenge the notion of cooperation as a stable model-level property, revealing how strategic behavior depends on interaction partners, network positions, and the language used to frame decisions.

Maria Sampani, Maria Lymperaiou, Angeliki Dimitriou +3

National Technical University of Athens

Multi-LLM CollaborationMulti-Agent CoordinationPrompt Sensitivity
AskPDF
Oct 22, 2026

DuoCook: An Overcooked-Inspired Benchmark for Visual Planning and Coordination

Coordinating two players in a cooking task requires a vision-language agent to track changing scene states, sequence recipe steps, and allocate shared resources under a time budget. We introduce an Overcooked-inspired benchmark for evaluating these capabilities in Unreal Engine environments constructed using coding agents. A single vision-language model controls both players from top-down visual observations, selecting high-level actions while the engine executes navigation. The benchmark contains 20 maps in five categories. These categories support evaluation of centralized coordination under equipment contention, changing terrain, and handoff dependencies. A prop legend and pot ingredient-count indicators provide explicit visual cues, while grid-based destinations support spatial grounding. The evaluation compares four VLMs on all 20 maps, measuring task score, order completion, delivery precision, action acceptance rate, and model API expenditure. A memory ablation on the same 20 maps examines the effect of a shared, self-authored notebook while retaining six-response action history in both conditions. The strongest evaluated model, gpt-6-astra, achieves 26.2% mean order completion. Notebook memory has mixed score effects across models, with positive mean differences for Claude and Qwen and negative differences for GPT and Gemini.

Ziyi Jiao, Heng Zhang, Drishti Regmi +3

Department of Computer Science, University of British Columbia · University of California, San Diego

Multi-Agent CoordinationEmbodied Agent BenchmarksVLMs for Robotics
AskPDF
Oct 21, 2026

SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning

Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems to generalize across complex, temporally extended tasks with diverse inter-agent coordination requirements. We introduce a specification language that combines temporal-logic task specifications with operators for expressing such requirements. We propose SpecMAGIC, a hierarchical framework that leverages the automaton structure of task specifications for subtask decomposition. A centralized high-level planner identifies and allocates compatible subtask sequences across agents, while decentralized low-level policies execute individual subtasks. This enables zero-shot generalization to new tasks by composing reusable subtask policies according to new specifications, without retraining. We establish soundness and probabilistic completeness of the high-level planner. Experiments on multi-agent navigation tasks show that SpecMAGIC substantially outperforms existing approaches on unseen task specifications and maintains strong performance as the number of agents increases.

Zijian Guo, İlker Işık, H. M. Sabbir Ahmad +1

Division of Systems Engineering, Boston University · Department of Electrical and Computer Engineering, Boston University

Multi-Agent Reinforcement LearningMulti-Agent CoordinationMulti-Agent PlanningHierarchical RL
AskPDF
Oct 21, 2026

ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination

Forming an accurate theory-of-mind (ToM) is key to successful multi-agent collaboration and requires reasoning under uncertainty to capture multiple possible partner states. This is hard to do in the text representation space native to large language model (LLM) agents, which more easily describe a single partner state. To address this challenge, we introduce ToM2Vec, which learns to form abstract theories-of-mind in a rich latent space via a fixed budget of continuous reasoning tokens. During training, supervision for these tokens comes from the partner's actual thoughts, which the ToM tokens are trained to abstract and match. At test-time, ToM tokens are generated by each agent and act as conditioners for that agent's thoughts and actions. Across several environments covering collaborative, competitive, and mixed-motive settings (Overcooked-AI, multiparty negotiation, Decrypto, Hanabi, and Collab Escape/Capture), we evaluate ToM2Vec's ability to support multi-agent interactions and collaboration, finding consistent improvements over the base model and a variety of competitive trained and prompted baselines. We show that latent reasoning is critical, with performance dropping when reasoning is expressed in text. Moreover, we show that ToM2Vec training generalizes to partner model families not seen at train-time, including a proprietary model (GPT-5.4). In our analysis, we provide evidence that the latent tokens encode a ToM, rather than task-specific information: ToM2Vec's tokens improve the agent's ability to directly answer questions about partner beliefs, desires, and next actions.

Nithin Sivakumaran, Ali Payani, Hyunji Lee +2

UNC Chapel Hill · Cisco · The University of Texas at Austin

Multi-Agent CoordinationTheory of MindMulti-Agent LLMsContinuous Latent Reasoning
AskPDF
Oct 20, 2026

Brittle by Design? Multi-Scenario Reinforcement Learning for Robust Mission Coordination in Systems of Systems

As systems engineering (SE) shifts from monolithic systems to Systems of Systems, Mission Engineering (ME) has emerged as a new line of thinking in SE. Mission environments are uncertain and dynamic, and outcomes depend on how mission assets interact with them, rendering static architectures brittle and calling for flexible yet analytically rigorous ME approaches. We propose an intelligent mission coordination methodology integrating high-fidelity digital mission models with Reinforcement Learning (RL) for adaptive task allocation. Using a Digital Engineering (DE) infrastructure comprising a digital mission model and agent-based simulation, we formulate mission tactics management as a Markov Decision Process and train an RL coordinator with Proximal Policy Optimization to map mission states to tactical actions from realized outcomes. An aerial firefighting mission with three scenarios demonstrates the approach. First, all trained coordinators significantly outperform random and heuristic baselines. Second, single-scenario coordinators can be brittle: the coordinator trained on the more forgiving scenario degrades to random tactics performance in more demanding scenarios, whereas the demanding-scenario coordinator retains most of its advantage when transferred. Third, within the same training budget, a coordinator trained on both scenarios concurrently matches the scenario-specific coordinators in their own scenarios and significantly outperforms every other policy. Sensitivity analyses on ignition location, weather, scenario, and training curricula show that the variability represented during training shapes post-deployment performance. This proof of concept shows DE-enabled mission simulations combined with RL offer a reusable methodology for improving ME practice, which can be extended to fleet design and selection from a mission-first perspective.

İbrahim Oğuz Çetinkaya, Sajad Khodadadian, Taylan Topcu

Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA

Multi-Agent CoordinationRobust RLMulti-Robot Task Allocation
AskPDF
Oct 20, 2026

Automated Multi-Agent Organization Design: From Architecture Search to Organizational Learning

Agentic system design is increasingly shifting from hand-crafted prompts and workflows toward automated search over agentic programs and interaction structures, with multi-agent systems receiving growing attention. Yet a central question remains unresolved: when does an automatically generated multi-agent structure exhibit a functionally meaningful division of responsibility? We argue that automated multi-agent design should move beyond searching for effective architectures toward identifying which responsibilities are functionally necessary, how they should be allocated, and when they should change. To explore this, we propose Automated Multi-Agent Organization Design (AMOD), which treats organization itself as a first-class design object, explicitly modeling how agent teams are composed, what functional responsibilities the agents assume, how they coordinate, and how collective decisions are made. We formulate AMOD as an execution-driven design loop. For each task, an automated designer instantiates an organization by assigning functional responsibilities and coordination rules to a set of agents. After execution, task outcomes, intermediate artifacts, and interaction traces are examined to identify which responsibilities may be missing, duplicated, or ineffective, and the organization is revised accordingly. We also propose testing discovered responsibilities by removing them, replacing them with generic roles, or changing their assignment under matched resource budgets, with complementary evaluations. AMOD provides a principled foundation for evidence-based and adaptive multi-agent organization design.

Shao-Jun Xia, Yuner Zhang, Huixin Zhang +3

Carnegie Mellon University, Pittsburgh, United States · Northeastern University, Boston, United States · University of Southern California, Los Angeles, United States

Multi-Agent SystemsMulti-Agent System OptimizationMulti-Agent Coordination
AskPDF
Oct 19, 2026

PACT: Plan-Augmented Coordination via Trace-Graphs for Dynamic Multi-Agent Combinatorial Optimization

Multi-agent approaches have been investigated recently as a means of improving the scalability of reinforcement learning for neural combinatorial optimization. Existing methods assume that all problem instance information is known upfront. However, real-world problems are often dynamic: relevant information is progressively revealed as the agents take actions (e.g., arriving at an edge in a routing problem only to discover it is untraversable). In such cases, existing methods fail to coordinate agents to explore and exploit the progressively revealed information. To address the arising coordination challenge, we introduce PACT (Plan-Augmented Coordination via Trace-graphs). PACT augments the environment graph with auxiliary nodes representing the plans of agents, which are connected to the resource nodes to indicate future dependencies. The proposed message-passing scheme over the augmented graph grounds inter-agent coordination in the environment and enables proactive, rather than reactive, conflict resolution. We show that PACT improves solution quality in dynamic problems relative to baselines and exhibits the best transfer to larger instances on which, remarkably, it outperforms centralized oracles with privileged access to instance uncertainty.

Xiao Zhou, Alex Schutz, Victor-Alexandru Darvariu +1

Oxford Robotics Institute University of Oxford OX1 3PJ, Oxford, United Kingdom.

Multi-Agent System OptimizationMulti-Agent CoordinationRL for Combinatorial OptimizationNeural Combinatorial Optimization
AskPDF
Oct 17, 2026

MELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery

Multi-agent scientific discovery with large language models raises a coupled learning problem: research assignments determine both which experiments are pursued and the experiences from which agents adapt. We introduce MELD, a unified hierarchical test-time training framework that jointly adapts a team-level Coordinator policy and agent-level individual Scientist policies within a single discovery process. The Coordinator generates a joint portfolio of search branches and research directives over a shared derivation tree, while Scientists develop hypotheses and execution plans implemented by a shared frozen Executor. Both levels receive alternating GRPO-style parameter updates under a shared smooth best-of-budget objective, allowing team organization and individual research behavior to co-evolve in a recursive self-improvement loop. Our analysis establishes objective alignment for the hierarchy, characterizes conditions for coordination gains over independent parallel discovery and the first-order benefit of private adaptation, and derives a finite-budget regret bound for adapted models. On 22 MLGym and MLE-bench tasks, MELD is best on 20 of them and achieves the highest aggregate normalized scores on MLGym, using a 4B backbone for coordination and research. Most baselines use proprietary Scientists, and all systems share one frozen Executor.

Sizhe Tang, Zuyuan Zhang, Zeyu Fang +1

George Washington University

Multi-Agent LLM SystemsLarge Language Model-Guided Scientific DiscoverySelf-Improving AgentsMulti-Agent CoordinationTest-Time Training
AskPDF
Oct 16, 2026

Jarvis: Coordination Deserves a Brain of Its Own in Agentic Interactive Models

Interactive models increasingly hand complex reasoning and tool use to a slow brain in the background, leaving a realtime front model free to sustain full-duplex dialogue. Yet the user may refine, cancel or replace a request while its task runs, so a plan or result that made sense a moment ago goes stale. Each new utterance must therefore be read against the work in flight, but the front model follows only the conversation and the back end sees only its own task. Coordination deserves a brain of its own, one that sees both. We introduce Jarvis, a coordination harness where models judge and code enforces. Its typed decision model, JEV, reads each turn against the live tasks and picks among operations built from a versioned task record. Code checks every choice against the current state before applying it, so no decision can act on a task version the user has replaced. Jarvis also rechecks plans before they execute and results before they are spoken, and counts an answer as delivered only once the user has heard it in full. We build two instances of this design. Jarvis-Audio runs unchanged on three full-duplex speech models. Jarvis-Omni adds vision and rechecks the evidence behind an answer before and during playback, since a scene can change while nobody speaks. With the front model and back end held fixed, replacing Qwen Audio Agent with Jarvis raises tau-Voice task success more than sixfold, from 29 to 192 of 278 tasks, and the gains hold on every benchmark and front model. Against published systems, Jarvis-Audio reaches 69% Pass1 on Full-Duplex-Bench v3 with an open 9B front model, versus 60% for GPT-Realtime. These results suggest that how the two brains are coordinated matters as much as how strong they are.

Yuxiang Wang, Shengbo Cai, Zhixian Zhao +7

The Chinese University of Hong Kong, Shenzhen · Tencent Hunyuan · Amphion Technology Co., Ltd.

LLM Agent HarnessesMulti-Agent CoordinationMulti-Turn Dialogue ManagementFull-Duplex Spoken Dialogue SystemsMultimodal Agents
AskPDF
Oct 16, 2026

VLA-Fabric: Learning Interaction for Composable Multi-Arm VLA Agents

Vision-language-action (VLA) models are rapidly expanding what individual robots can accomplish, yet many real-world manipulation settings require multiple arms to operate as a coordinated system. Existing approaches organize multi-arm coordination in different ways, including centralized joint policies, high-level task or role assignment, and locally executed policies that react to teammates. However, how complete action-producing VLAs should explicitly interact with one another during action generation remains largely unexplored. We introduce VLA-Fabric, which organizes one complete VLA per arm while preserving local perception and action ownership, and enables coordination through learned interaction across policy boundaries. We first systematically study where such interaction should occur, how peer information should be aggregated, and how the interaction should be learned, revealing complementary coordination functions spanning shared context, peer-specific latent information, and action-stage interaction. We then re-instantiate these functions in a structurally different VLA architecture, showing that the coordination principle is not tied to a particular tensor layout or backbone implementation. Finally, we compose teams of three and four arms and evaluate them in simulation and physical experiments. On all four physical tasks, Full interaction improves success over independently trained local policies by 16--40 percentage points. Together, these results suggest that explicit interaction among complete VLA policies offers a scalable path toward networked embodied intelligence.

Chenglong Zhang, Shuaijun Liu, Feiyang You +3

The Hong Kong University of Science and Technology (Guangzhou)

Multi-Agent CoordinationMulti-Robot CoordinationVision-Language-Action ModelsRobotic Manipulation
AskPDF
Oct 15, 2026

Learning Self-Orchestration in Decentralized Agent Swarms

The capabilities of an agent swarm depend on both its individual members and how they coordinate. Yet existing multi-agent systems often train agents within fixed orchestration structures, separating the learning of individual capabilities from the organization of collective behavior. We introduce market-based post-training (MPT), a framework for jointly learning action policies and self-orchestration in decentralized agent swarms. Agents express their willingness to participate through bids, which determine who acts and how collective outcomes provide local training credit. Learning both action and bidding behavior allows individual capabilities and patterns of participation to adapt together without a central coordinating agent. We evaluate MPT on embodied crafting, robot navigation, and deep research. Results show gains over monolithic post-training and confirm that agent participation indeed evolves with learning. With the same post-trained action policies, learned self-orchestration outperforms alternative coordination strategies. Ablations show that both action and bidding benefit from learning, and that learned bids provide more effective action-training signals. Beyond the original training objectives, trained swarms adapt faster to related tasks and achieve better performance with larger populations at inference time. Larger populations also suffer smaller performance losses under agent dropout, demonstrating that learned self-orchestration supports reuse, scaling, and robustness in decentralized agent swarms. More details are available on our project page at https://guoweixu.com/mpt/.

Guowei Xu, Zhenting Qi, Amani Kiruga +2

Harvard University

Multi-Agent OrchestrationMulti-Agent CoordinationDecentralized MARLCooperative MARL
AskPDF
Oct 15, 2026

Auditable and Deployable Multi-Agent Motion Planning via Posetal Games from Legal Guidelines

When robots are deployed in the real-world, they must interact with other agents and accomplish their own goals while adhering to legal constraints. These potentially conflicting objectives are often only partially prioritized, making scalarized objectives or fully specified hierarchies unsuitable. We present a framework for multi-agent motion planning under legal requirements based on games with partially ordered preferences (posetal games). Scenario-independent legal guidelines order abstract legal concerns, from which we automatically derive agent preferences and a legal game for any concrete scenario. Agents may refine their legal preferences with private objectives, and regulators may refine the guideline as laws evolve. We prove that such customizations can only remove equilibria and thus preserve legality. To coordinate agents without explicitly communicating private preferences, we introduce belief play, which provably recovers the true equilibria from conservative local games, and a distributed iterative best-response protocol requiring less information. We apply the framework to maritime navigation, systematically lifting pairwise traffic rules to multi-vessel encounters. On seven encounters with up to four vessels, every rule violation of the committed equilibria is certified as forced by the legal hierarchy or unsatisfiable, and defectors are identified from public information in all tested cases. These results indicate that guideline-based posetal games offer an auditable route from partially specified laws to multi-agent motion planning.

Florian Lercher, Karan Mahesh, Yujun Huang +6

Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. · School of Computation, Information and Technology, Technical University of Munich, 85748 Garching, Germany. · Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. +2

Decentralized Multi-Agent Motion PlanningMaritime NavigationMotion PlanningConstrained Motion PlanningMulti-Agent Coordination
AskPDF
Oct 15, 2026

Decentralized LLM Workflows via Sequential Auctions

We present a scalable framework for solving multi-step tasks through a decentralized market of self-interested agents. Prior theoretical work demonstrated that agents organized through sequential auctions can converge to a globally optimal policy in a Markov decision process (MDP), but relied on the restrictive assumption of the existence of perfect clones as a model of perfect competition. In reality, exact clones drive agent profit to zero, violating the natural risk-reward incentives of participants. Conversely, we empirically demonstrate that the opposite extreme, absence of competition, also leads to market failure and value extraction collapse. Between these two extremes, we investigate how heterogeneous agents can survive in markets that span the critical middle ground of imperfect competition. To be profitable, agents learn to strategically shade bids to secure positive individual profit margins, while still ensuring that the marketplace functions effectively enough so that collaborative tasks posed by market consumers can still be solved. We formulate and evaluate four bidding algorithms (Mirror Descent, Thompson Sampling, Bayes-Optimal, and PPO) across three auction protocols (1st-Price, 2nd-Price, and Credit-Conserving Vickrey). Across a diverse set of domains, we demonstrate that imperfect competition successfully sustains necessary agent profit margins while maintaining high task success rates at low costs.

Ian Gemp, Shubhendu Trivedi, Adam Fisch +7

Google DeepMind · Google Research · University of Waterloo

Agentic WorkflowsAutomated BiddingMulti-Agent CoordinationHeterogeneous MARL
AskPDF
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.

Thi-Nhung Nguyen, Viet-Thanh Pham, Linhao Luo +2

Department of Data Science & AI, Monash University

Multi-Agent CoordinationMulti-Agent SystemsMulti-Agent OrchestrationMulti-Agent Communication
AskPDF
Oct 14, 2026

What and Where in Identifying and Quantifying Conventions in Humans and AI Agents

Cooperative success rests in part on implicit communication. Partners converge on conventions: regularities that give an action meaning beyond its direct effect. Yet conventions are usually observed only indirectly: a score drop when partners are swapped shows that a convention existed, but not what it was or where it was used. In the card game Hanabi, the exact probability that a play fails can be computed from the hints received and the cards in view. Players who use conventions succeed more often than this prediction allows; the resulting margin is the convention gap. Off-belief learning provides a hierarchy of agents (levels 1-5) whose first level uses no conventions by construction and whose later levels use progressively more. For humans and these agents on one scale, we ask what the conventions are and where they are used. On what: in two independently collected corpora of human games, humans show a larger gap than every agent level. On the conventions both populations use, however, humans do no better than level 2. The human advantage is concentrated in a situation that no agent level learns to use: hints that point to a card other than the ones they touch. On where: conventions depend on what the player already knows about the card, not on how recently it was hinted, and they are used most in the mid-game; humans use them earlier and later in the game than the agents. In interventions on the agents, blocking a single high-gap situation costs little, because meaning reroutes to other situations, but blocking several together costs far more than the sum of the single costs. Thus, the convention gap turns conventions from an inferred cause of score loss into a measurable, comparable, and causally testable object.

Makoto Fukushima, Tim Puphal

Honda Research Institute Europe

Multi-Agent CommunicationMulti-Agent CoordinationGame-Playing Agents
AskPDF
Oct 14, 2026

What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds

Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances. Existing evaluations of social agents mainly rely on LLM judges that rate the conversation, without checking the resulting plan. We introduce HICO-Bench, a benchmark of 180 everyday coordination scenarios, such as resource allocation, scheduling, and authorization, in which two agents with private information converse and then independently record the plan they agreed on. A program checks Feasibility (the two records match and satisfy both participants' private conditions), and an LLM judge checks Integrity (the conversation supports the recorded plan); passing both is a Verified Success. Each scenario has two versions that share the same public context but differ in one private condition, so the correct plan differs between them. Across thirteen LLMs, 36% of conversations rated highly for goal completion fail Verified Success. To learn from outcomes that arrive only at the end of a conversation, we propose Paired-Credit Policy Optimization (PaCPO). After each turn, PaCPO asks the agent for a tentative plan, checks it in both versions of the scenario, and rewards the turns after which the tentative plans fit their respective versions. PaCPO raises Qwen3-8B's Verified Success from 20.4% to 28.3%.

Caixin Kang, Ke Wang, Yuchuan Wu +5

Alibaba Token Hub, Alibaba Group · The University of Tokyo

LLM Agent EvaluationLLM Agent TrainingMulti-Agent CoordinationAI Agent BenchmarksMulti-Agent CommunicationCredit Assignment in RL
AskPDF
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.

Seojin Hwang, Youngmin Choi, Hwanhee Lee

Chung-Ang University

Multi-Agent LLM SystemsMulti-Agent SystemsSelf-Evolving AgentsEmergent Behavior in Multi-Agent SystemsMulti-Agent Coordination
AskPDF
Oct 14, 2026

PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making

Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from fragmented decision-making across medical specialties, a critical coordination failure that leads to adverse drug events and rehospitalizations. To address this coordination challenge, we introduce PRISMATIC, a multi-agent architecture where specialized agents, each representing a workflow role, collaboratively generate and refine treatment plans. Operating on a blackboard architecture, the system first structures patient information from clinical notes, then iteratively develops safe, rational, and interpretable drug regimens. The agents' collaboration is governed by two novel adaptive coordination mechanisms: (1) Dynamic Self-Updating Weight Adjustment (DSWA), a long-term mechanism that adjusts the influence weights of agents based on historical case outcomes, enabling the system to adapt and trust more reliable specialists over time. (2) Discrepancy Feedback Precise Calibration (DFPC), a short-term mechanism where agents provide iterative feedback to resolve disagreements and eliminate prescription conflicts for the current patient. Experiments on patient records from the MIMIC-IV database show that PRISMATIC significantly reduces drug conflicts, improves prescription coverage, and enhances treatment consistency compared to strong LLM baselines. Our work demonstrates that structuring clinical co-treatment as a multi-agent coordination problem offers a promising path toward safer and more coherent multidisease management.

Ziyang Ling, Shuyu Lu, Ziyi Chen

University of Science and Technology of China, Hefei, China · The University of Texas Health Science Center at Houston, Houston, United States

Drug-Drug Interaction PredictionClinical Decision SupportMulti-Agent LLM SystemsMulti-Agent Coordination
AskPDF