Multi-Agent System Optimization

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 130

Oct 6, 2026cs.MA

Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor

Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among specialized agents. However, existing MAS frameworks tightly couple task reasoning with coordination operations, including task selection, role assignment, message routing, and context management. As interactions grow, using powerful LLMs for these bounded control decisions introduces substantial token overhead and latency, limiting the scalability of agentic Web services. In this paper, we investigate whether coordination can be decoupled from expensive reasoning without compromising collaborative performance. We propose S1-MAS, a token-efficient multi-agent framework based on System One-guided computational division of labor. S1-MAS assigns bounded coordination decisions to lightweight System One models while reserving open-ended reasoning for capable LLM workers. Specifically, a lightweight controller selects inspection conditions, chooses subsequent tasks, and determines termination, while a compact reader retrieves condition-relevant evidence from authorized sources to support these decisions. Through a decision-evidence loop, selected tasks dynamically determine worker roles and source access, enabling adaptive collaboration without task-specific training. Extensive experiments on seven diverse benchmarks demonstrate that S1-MAS achieves superior accuracy while substantially reducing the inference cost. Across individual comparisons with AgentVerse, DyLAN, and SelfOrg on seven benchmarks, S1-MAS reduces GPT-4o token consumption by 44.9%-97.2% and measured end-to-end latency by 37.8%-93.0%. These results highlight its potential for scalable and cost-effective agentic Web applications.

Zihan Zhou, Xinzhe Hu, Hanxu Yang +2

University of Electronic Science and Technology of China · Southwestern University of Finance and Economics

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination LLM Agent Orchestration Multi-Agent Collaboration

Oct 5, 2026cs.GT

Parallelism or Concession? Concurrency-Aware Procurement Negotiation for Agentic Commerce

Agentic buyers can cheaply fork a procurement task into many parallel negotiations, but concurrency is not free: every thread consumes resources, and simultaneous agreements create cancellation and commitment risk. We study a one-unit post-order sourcing problem with a single hard-deadline negotiation window, in which a planner jointly chooses the number of seller-facing negotiators and a common procurement price cap. The model combines a product-specific acceptance curve with fulfillment loss, per-thread cost, and excess-commitment cost. We establish three structural results. First, holding the per-thread acceptance target fixed, the marginal value of another negotiator decays geometrically, yielding a conditional concurrency threshold. Second, under a convex quantile curve, parallelism substitutes for concession: more concurrent negotiators imply a weakly lower per-thread acceptance target and price cap. Third, when prices are more dispersed, Agentic buyers benefit by searching harder for bargains, but suffer when they instead try to guarantee procurement by offering higher prices. We operationalize these results in the Concurrency-Aware Negotiation Optimizer (CANO), a deterministic optimizer that jointly determines the optimal negotiation concurrency and procurement price cap for an agentic procurement system. Across different analytic market configurations and extensive Monte Carlo, finite-data, non-Gaussian, and correlated-seller stress tests, CANO consistently outperforms common heuristic policies while validating the predicted structural properties.

Xiaolin Xu, Donghao Zhu

School of Business Nanjing University Nanjing, Jiangsu, China · Institute of Business Sciences University of Tsukuba Bunkyo-ku, Tokyo, Japan · University of Tokyo Market Design Center Bunkyo-ku, Tokyo, Japan

Multi-Agent System Optimization Automated Negotiation Automated Bidding Agentic Commerce

Sep 30, 2026eess.AS

Multi-agent Auditory Scene Analysis: Improved Localization Speed and Robustness by Multi-beamformed Speech Quality Feedback

A real-time auditory scene analyzer (ASA) aims to carry out the tasks of locating, separating and classifying the sound sources present in a given acoustic environment. Recently, an effort has been made into modelling an ASA as a multi-agent system, with each one of its agents performing one of the aforementioned tasks and communicating their results to the rest of their peer agents. These communication routes are used as feedback loops to fix local errors at a global level, providing robustness while reducing local complexity. An example of the benefits of this approach is the optimization of speech quality by correcting in real-time the estimated location of the speech source of interest. However, their optimization speed has been shown to be considerably slow. One possible reason is that it solely relies on a series of single quality estimations (provided by a reference-free quality estimator model) that vary considerably from one window to the next, which results in a difficult search space to optimize. In this work, a new optimization mechanism is proposed that instead relies on a series of sets of quality estimations over a range of locations, providing a clearer view of the search space, simplifying its optimization. The proposed ASA now has a considerably smaller optimization time, is more accurate, and is more stable when being evaluated in real-life acoustic scenarios to correct higher levels of localization errors, all while being less complex than previous efforts. The only trade-off is that there is an increase in the response time of the quality estimation agent, but the complete ASA is still able to run in real-time. The performance shown in this work again shows the benefits of modelling an ASA as a multi-agent system.

Caleb Rascon

Instituto de Investigaciones en Matematicas Aplicadas y en Sistemas, Universidad Nacional Autonoma de Mexico, Circuito Escolar 3000, Coyoacan, 03740, Ciudad de Mexico, Mexico.

Multi-Agent System Optimization Direction-of-Arrival Estimation Audio Understanding Multi-Agent Systems

Sep 29, 2026cs.AI

Topological Coherence for Self-evolving Multi-agent Systems

Complex tasks inherently couple workflow structure, agent responsibility, collaboration, and memory access: task regions delimit responsibility and tool scope, cross-region dependencies give rise to handoffs, and ownership boundaries delimit private and selectively shared memory. Existing methods can jointly optimize agent and communication structures, yet such optimization does not by itself require responsibility, handoff, and memory boundaries to remain consistent with task dependencies. We term this requirement topological coherence. We introduce TOCOMAS, a Topology-Coherent Multi-Agent System. TOCOMAS grounds a task graph in tool interfaces, organizes compatible task nodes into reusable responsibility domains, and derives dependency-induced and profile-conditioned collaboration together with boundary-regulated memory visibility. During online self-evolution, TOCOMAS proposes coupled changes to agent, collaboration, and memory policies, retaining for subsequent tasks only candidates that satisfy structural constraints and improve evaluated reward. Across BBEH, WorkBench, SWE-Bench-Verified, and CoMemBench, TOCOMAS improves task success over baselines across backbones. CoMemBench also shows gains over the self-evolving baseline in verified progress, handoffs, and memory isolation.

Sen Zhao, Ruiqi Kong, Zuyu Zhang +4

Academy of Advanced Interdisciplinary Studies, Chongqing University of Posts and Telecommunications, Chongqing, China · School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China · Towngas, China +1

Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Orchestration Multi-Agent Collaboration Self-Evolving Agents

Sep 29, 2026cs.MA

FlowMAS: Learning Multi-Agent Workflow Topology via Information-guided Generative Flow Network

Automated multi-agent systems offer clear advantages over manually designed ones in scalability and adaptability, but existing workflow topology methods still face important limitations. Search-based methods are often computationally expensive, textual-gradient-based methods rely on coarse-grained feedback, and existing generation-based methods are not well suited to discrete workflow topologies with complex dependencies. To address these limitations, we propose FlowMAS, a multi-agent workflow topology method based on Generative Flow Networks (GFlowNets). FlowMAS models workflow generation as reward-guided flow over the topology space and introduces three components: a GFlowNet-based topology generation backbone, a curiosity-driven module for structure-aware exploration, and an information-guided optimization module for evaluating intermediate topologies. Concretely, the curiosity-driven module encourages exploration of structurally novel workflows, while the information-guided module measures both the information contribution and the communication efficiency of different operators to favor more informative and effective collaboration patterns. Experiments on six benchmark datasets with three LLM backbones show that FlowMAS consistently outperforms multiple baselines.

Haitao Wang, Chenjing Liang, Haipeng Zhang +6

Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University, Xiamen, China · School of Computer, National University of Defense Technology, China

Multi-Agent LLM Systems Multi-Agent System Optimization LLM Agent Workflow Optimization

Sep 15, 2026cs.MA

Decomposition Buys Integrity, Not Yield

Multi-agent systems split a task across a tree of agents and justify the split with folklore: smaller contexts, cleaner separation, parallelism. We ask what the split does to how much of what the leaves discover reaches the root. Model a decomposition as a tree in which an agent handed

b

items keeps any one with probability

r(b)

. If

r(b)=1/b

, every tree delivers exactly one finding, for every task size and every shape; we verify this to

2.4 \times 10^{-15}

on 20,000 random irregular trees. If

r(b)=Cb^{-δ}

, a depth-

k

tree over

N

findings yields

C^k N^{1-δ}

: task size and architecture separate, and architecture contributes only

C \le 1

per level, so flat is optimal for yield and no arrangement of agents escapes the exponent

δ

. On 600 production deep-research traces

δ= 0.34

[0.30, 0.38], by three identifications that do not share a failure mode. At a hop where item boundaries come from the tool rather than a text heuristic, and where

b=1

occurs 550 times,

C = 0.571

[0.527, 0.615] is observed rather than extrapolated, over 16,082 hops. A tier also costs alignment: on 1,012 annotated multi-agent traces one brief in sixteen goes off-target, giving

μ= 0.939

and a per-tier penalty

Cμ= 0.536

. Depth is bought on two other axes. The root context is the only state that persists and the only one that cannot cheaply forget, and depth cuts its exposure from

N

items to

N^{1/k}

. Depth is also cheaper: production flat agents bill as

N^{1.39}

, not the

N^2

an append-only context predicts, and at equal spend two tiers overtake flat at 403 findings. Across every parameter we measured the model says 0.7% to 11.3% of production sessions are worth delegating, against 7.8% that do. A hazard model on 743,819 production tool calls finds that delegation does not respond to a filling context and is instead an opening move.

Rong He

Multi-Agent System Optimization Deep Research Agents Task Decomposition

Sep 15, 2026cs.MA

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

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

Sara Vera Marjanović, Jiacheng Xu, Aleksandr Laptev +3

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

Model Selection Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Systems Language Model Ensembles

Sep 9, 2026cs.AI

UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model

Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the final answer, allocates later calls, and decides when to stop. It is expressive, but it also concentrates three control decisions in an opaque, order-sensitive model call. We ask whether the manager needs to be generative at all. UnitBoost replaces that model with a defined meta-level operator: a task-given unit map turns worker outputs into slot-value proposals, a constrained argmax assembles the output, and the slots left unfilled or unsupported become an explicit residual for the next round. The operator is order-free, records unit provenance, and gives a simple guarantee: without coupling constraints, unit-wise maximization under the same admission score dominates selection of any complete candidate. On three held-out benchmarks, it exceeds the best single candidate chosen with gold labels by 0.060-0.195 absolute task-score points and input-matched generative managers by 0.048-0.076. Replacing only the management step improves six compound-system configurations by 0.013-0.182. Residual-directed rounds raise FanOutQA cell F1 from 0.4778 to 0.5524; matched controls show that the true residual outperforms random targets and ordinary rereading, while a label-free supply signal flags exhaustion after one unproductive round. The same analysis measures three conditions in which no such gain is available (one indivisible unit, unavailable unit identity, and an endpoint that charges for every emitted unit) and quantifies cross-unit coupling as a repair cost. The manager gives up semantic freedom and gains order invariance, unit provenance, and testable failure conditions.

Xing Zhang, Guanghui Wang, Yanwei Cui +2

AWS Generative AI Innovation Center

Multi-Agent System Optimization LLM Agent Orchestration Iterative Refinement Multi-LLM Collaboration

Sep 8, 2026cs.AI

GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data

Automated alpha factor discovery searches symbolic trading signals from price-volume panels and order-book data under a fixed evaluation budget. Existing single- and multi-agent program-search systems can overfit predictive proxies that fail after execution costs and repeatedly explore redundant factor families, limiting execution robustness and behavioral diversity. We introduce GoAnt, a quality-diversity multi-agent search framework that combines non-communicating Explorer, Exploiter and Connector workers with a shared adaptive Mental Map and a compact Queen dispatcher. The Mental Map organizes candidates by leakage-free execution profiles and retains one elite per niche, while the Queen reallocates the evaluation budget from explicit search-state summaries. We also define a map-independent effective-yield protocol that counts high-quality, mutually nonredundant factors directly from each method's evaluation records, giving archive-based and map-free systems the same ruler. On real A-share microstructure data spanning 2023--2026, GoAnt reaches quality-weighted yields of 41.8 and 47.6 in price-volume and order-book settings, improving the strongest baseline by 57% and 97% under matched budgets. Its locked populations retain 0.64 and 0.67 of in-sample quality out of sample, compared with 0.61 and 0.63 for a static map.

Stella Zhao, Tommy Sha

University of Minnesota, Minneapolis, MN, USA · Stony Brook University, Stony Brook, NY, USA

Multi-Agent System Optimization Quantitative Finance Automated Algorithm Discovery Quality-Diversity Optimization Algorithmic Trading

Sep 8, 2026cs.AI

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple agents, yet their performance depends on the prompt design of each agent. For MAS prompt optimization, textual gradient methods that guide prompt updates using natural-language feedback have emerged as a leading paradigm. In this paper, we identify limitations in two stages of existing textual gradient approaches: gradient extraction and gradient aggregation. In gradient extraction, previous works select a target prompt without verifying whether modifying it resolves the failure, and derive gradients without agent-level supervision over the corresponding agent's intermediate output. In gradient aggregation, individual gradients are randomly grouped and concatenated, often mixing unrelated failure modes and producing prompts that fail to generalize. To address these limitations, we propose AgentGrad, a prompt optimization framework for multi-agent systems based on sequential intervention and semantic textual gradient abstraction. For each failure, sequential intervention modifies the behavior of one agent at a time to identify the target agent whose modification resolves the failure. The modified output of the target agent then serves as agent-level supervision for extracting a fine-grained gradient. Semantic textual gradient abstraction clusters semantically similar gradients to prevent mixing unrelated failure modes, and abstracts each cluster into a generalized gradient that captures the shared corrective pattern. Experimental results show that AgentGrad achieves state-of-the-art performance across five MAS benchmarks while reducing wall-clock optimization time by

2.5\times

and optimization cost by 21.8% on average compared to the next-best baselines.

Jaewon Chu, Jinwoo Seo, Jaewon Cho +4

Korea University · KAIST · Meta AI +1

Multi-Agent LLM Systems Multi-Agent System Optimization Prompt Optimization

Sep 8, 2026cs.MA

Reachability-Certified Subteam Decomposition for Locally Interacting Multi-Agent MDPs

Persistent communication limits force a multi-agent system to decide which agents may coordinate throughout a rollout. Current proximity alone is insufficient: separated agents may interact later, whereas a large pair reward may remain unreachable until it is heavily discounted. We introduce Reachability-Certified Subteam Decomposition (RCSD) for finite multi-agent Markov decision processes with factorized physical dynamics, finite-range ordered pair rewards, and almost-sure motion bounds. RCSD combines a speed-limit lower bound on pairwise contact time with a reward envelope to form a current-state affinity. For any capacity-valid persistent partition, the sum of cut affinities bounds the reward-deletion error of every unchanged stationary Markov state-feedback policy. A product of team-optimal policies for the resulting cut MDP incurs at most twice this certificate in regret against the centralized optimum. Both bounds are worst-case tight. On a controlled five-agent family, RCSD-Exact reduces aggregate normalized execution regret by 56.0%, 28.8%, and 25.3% relative to uniform, distance-only, and envelope-only partitions. A separate stochastic two-dimensional study finds no bound violation over 384 exact-partition and 1,440 restricted-controller evaluations. Exact four-agent evidence favors RCSD over uniform and distance-only grouping; raw evidence for current contact is borderline and envelope-only is unresolved. Across balanced 8-20-agent strata, controller-library utility is mixed: pointwise paired intervals favor RCSD over distance and current contact, include zero for uniform, and favor envelope-only and Value-MIP over RCSD. Partition construction remains subsecond in median up to 100 agents; this last result does not include affinity formation or MDP planning.

Xiangwu Wang, Chengwei Cao, Hongyuan Tang

University of Hong Kong · University of California, San Diego · Carnegie Mellon University

Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Planning

Sep 7, 2026quant-ph

Riemannian Optimization for Multi-Player Quantum Games on Product Unitary Manifolds

Quantum game theory is an extension of classical game theory that uses quantum principles in game theory. The Eisert-Wilkens-Lewenstein (EWL) quantum game is an early example of the two-player classical Prisoner's Dilemma transformed into a quantum Prisoner's Dilemma. In the EWL game, the players choose pure quantum strategies represented by unitary matrices. This extension can resolve the classical dilemma by enabling cooperative equilibrium with higher payoff. In this paper, we first discuss the Extended EWL (EEWL) for multiplayer quantum games with mixed strategies. In EEWL, each player controls a set of unitary operators as quantum actions and uses a classical mixed strategy over these actions. The payoffs are defined as expectation values of Hermitian reward operators acting on a shared quantum state, which is generated and measured according to the EEWL protocol. We then propose the Unitary Strategy Matrix Exponential Algorithm (USMEA), a geometry-aware sequential algorithm for the EEWL mixed-strategy setting, in which each player jointly learns a trainable set of local unitary actions and the associated classical mixing probabilities. Thereby it acts as a learning-and-control layer for multi-agent quantum decision systems. We analyze the convergence properties of USMEA under standard smoothness and step-size conditions and validate the theory with numerical experiments. These results show how classical optimization methods can be systematically integrated into the design and analysis of engineered quantum strategic interactions.

Alireza Habibi, Setareh Maghsudi

Faculty of Electrical Engineering and Information Technology, Ruhr University Bochum, Bochum, Germany

Multi-Agent System Optimization Riemannian Optimization

Sep 1, 2026cs.AI

Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems

Vehicle Routing Problems (VRPs) are fundamental combinatorial optimization problems with widespread applications in various scenarios. The advanced optimization solvers can effectively solve such problems. However, modeling complex VRP variants for solvers often requires substantial domain expertise, which limits the accessibility of advanced optimization technologies. In this paper, we propose Reinforcement Learning Enhanced LLMAgents(RLEA), a multi-agent framework designed to automate the modeling of complex VRPs. RLEA introduces a lightweight neural Planner trained with Soft Q-learning to efficiently orchestrate the actions of LLM-based agents. In addition, we equip the system with an evolutionary memory module and retrieval-augmented generation, enabling the agent to leverage both accumulated experience and external solver knowledge during program generation and refinement for solving VRPs. We evaluated 48 distinct VRP variants across various solvers. The experimental results demonstrate that RLEA outperforms the previous state-of-the-ar method, achieving a 16.67% higher success rate while significantly reducing runtime errors. These results validate that integrating reinforcement learning with LLM-based reasoning is highly effective for automated optimization modeling. The appendix is available at: https://doi.org/10.5281/zenodo.19134435.

Yi Chen, Zikang Yu, Jiahai Wang +3

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China · Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore

Multi-Agent System Optimization LLM-Guided RL Vehicle Routing Natural Language to Optimization Modeling

Aug 11, 2026cs.AI

MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graph

As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that systematically improves them. Current approaches optimize agent systems without accumulating transferable knowledge, accumulate knowledge without compositional reasoning over it, and lack a mechanism for that knowledge to self-evolve through operational evidence. MEGA (Meta Evaluation-Grounded Adaptation) addresses these gaps as a self-evolving infrastructure: each optimization cycle produces durable assets, compositional reasoning over those assets guides subsequent optimization, and operational evidence refines both the accumulated wisdom and the reasoning that governs it. Layer 1 distills reusable wisdom from agent sessions through behavioral-pattern clustering and empirical A/B validation, transforming each process into a durable asset. Layer 2 decomposes these assets into atomic PCR (Primary-Context-Resultant) units within a typed Wisdom Graph and performs deductive, abductive, and inductive reasoning to expand implicit relations; it then assembles context-specific execution plans through compositional retrieval that surfaces bridging knowledge unreachable by embedding similarity alone. Layer 3 performs multi-agent collaborative optimization over heterogeneous agent workflows (code nodes, LLM calls, and tool-using agents), attributing improvement effects to specific strategy changes through controlled evaluation that eliminates data variance. Evidence fed back from Layer 3 drives the self-evolution of both the curation strategies that govern wisdom composition and the optimization trajectories accumulated across runs. The result is an infrastructure in which optimizing an agent system and evolving the knowledge that guides optimization are one and the same process.

Jung Hwan Lee, Kyu Ho Lee, Gwang Hoon Yoo

Mind AI Tech Report

Multi-Agent System Optimization Agent Harness Optimization LLM Agent Workflow Optimization Graph-Based Agent Memory Self-Evolving Agents

Aug 7, 2026cs.AI

EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples. Experience from these samples is rarely consolidated into reusable system updates, while accuracy-oriented designs may incur high token costs. We introduce EMAS (Evolving Multi-Agent System), which uses this experience to revise MAS topology and prompts without updating LLM parameters, either to improve accuracy or to reduce cost. EMAS converts traces into structured diagnoses that specify a revision operation and target. It generates a candidate revision only when the same diagnosis recurs across samples and applies it only if paired validation against the current MAS meets the corresponding acceptance criterion. Across four benchmarks and two LLMs, EMAS attains the highest task-weighted overall accuracy for both backbones and is best or tied in six of eight model--benchmark settings. Within two evolution epochs, EMAS achieves relative gains of 6.30% and 20.10% in task-weighted accuracy on Kimi-K2-6 and Qwen3.6-27B, respectively. On MBPP with Qwen3.6-27B, EMAS raises accuracy from 55.09% to 89.12% while reducing token use per task by 62.2%. These results show that EMAS can turn experience from new samples into reusable updates to MAS topology and prompts.

Chao Fei, Qingyi Si, Kaihua Liang +3

King Abdullah University of Science and Technology (KAUST) · Fudan University

Continual Learning for LLM Agents Multi-Agent System Optimization Prompt Optimization Self-Evolving Agents

Aug 1, 2026cs.MA

BANDMAS: Causality-Inspired Semantic Packet Scheduling for Bandwidth-Efficient Multi-Agent Collaboration

LLM-based multi-agent systems make decisions based on the aggregated information via exchanging messages across specialized agents. Forwarding every generated message among agents increases application-layer traffic. Yet, it introduces tremendous input tokens for agent processing, potentially raising inference latency and computational overhead. Existing approaches attempt to address the above issues by pruning agents or discarding redundant messages. Nevertheless, such agent-level or message-level optimization results in insufficient evidence supporting for final decisions or still containing redundant message transmissions. To address these challenges, we propose BANDMAS, a multi-agent collaboration framework that models inter-agent communications as task-oriented traffic, which enables efficient transmission via causality-inspired replay valuation. Specifically, we decompose messages into several data packets by analyzing their semantic features such as evidence and requests. The system only transmits these packets if their predicted replay-derived contribution exceeds their resource cost. Consequently, BANDMAS is able to adaptively schedule communication packets while adhering to bandwidth, latency, deadline, and receiver context constraints. On frozen Qwen3-4B traffic across SciFact, HotpotQA, and FanOutQA, our framework reduces application-layer bytes by 53.2% to 77.3% at selected caps and attains the highest mean task metric among constrained methods on all three workloads.

Jiangwen Dong, Wanyu Lin

Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Collaboration Multi-Agent Communication

Jul 30, 2026cs.MA

Argonaut: Interactive Visual Exploration for Distributed Optimization

Distributed discrete-choice optimization in decentralized settings is often hard to explore and navigate: disentangling what other agents choose, how their choices are interdependent, and how they collectively reach a global objective quickly becomes intractable as the system scales. The major limitation is observability of the search process. Existing methods are largely centralized and offer limited support, visualizing only the final solution or providing algorithm backends over a fixed dataset, so how a solution is reached stays a black box. We present Argonaut, a lightweight, containerized optimization dashboard that enables interactive, visual exploration of the entire search process for multi-agent discrete-choice optimization in decentralized settings. Users upload datasets, construct agents and options, modify the decision space and its parameters on the fly, and run multiple algorithm backends to inspect how each configuration shapes local agent decisions and the resulting global objective. By uniting system construction, optimization, and analysis in one interactive loop, the first of its kind, Argonaut makes distributed discrete-choice optimization a human-in-the-loop process rather than a one-shot, black-box computation. We evaluate Argonaut on real-world household-electricity, shared-mobility, and sensor-data-exchange datasets scaling to 5600 agents and up to 1M solutions under brute force. Built on a Node.js interface with extensible Java and Python optimization backends, it maintains a typical runtime of 200 agents over 100 decision attributes in under 30 seconds.

Srijoni Majumdar, Chuhao Qin, Evangelos Pournaras

School of Computer Science, University of Leeds, Leeds LS2 9JT, UK. · School of Energy Systems, LUT University, 53850 Lappeenranta, Finland

Multi-Agent System Optimization Visual Analytics Decentralized Optimization

Jul 30, 2026cs.MA

Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis

LLM-based multi-agent systems have the potential to enable collective intelligence and scale toward solving highly complex tasks through coordinated ensembles of specialized agents. However, despite their theoretical potential, the architectural design space remains largely non-systematized and lacks broadly established design principles. Furthermore, the scalability characteristics of such systems are only partially understood so far. This paper makes two contributions. We first distill four design principles for scalable MAS architectures from a structured analysis of prior work: simplicity, elastic feedback, sequential workflows with optional loops, and summary-based communication. We operationalize these principles in a reference architecture whose topology is formalized as a constrained directed workflow graph, and we evaluate four configurations of increasing complexity on a standardized benchmark of terminal-based system engineering tasks using two LLMs of differing capability. Our findings show that scaling yields measurable accuracy improvements with approximately linear cost growth, but only when the underlying LLM exceeds a minimum capability threshold. Performance peaks at intermediate complexity, then degrades due to timeouts and evaluation limitations. In addition, persistent consistency issues emerge as a central challenge across all scaling levels. These results provide concrete design guidance for practitioners and highlight consistency and evaluation standardization as key targets for future research.

Linus Sander, Fengjunjie Pan, Vahid Zolfaghari +3

Robotics, Artificial Intelligence and Real-Time Systems, School of Computation, Information and Technology, Technical University of Munich, Munich, Germany

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Orchestration Multi-Agent Systems

Jul 26, 2026cs.AI

Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems

Large language models (LLMs) enable autonomous agents for reasoning, planning, and tool use. Recent systems increasingly organize these agents as graphs of specialized, interconnected nodes. Although graph-based orchestration supports flexible decomposition and coordination, it creates a key challenge: \textbf{attention allocation}. As workflows grow, existing approaches often execute graph components uniformly, wasting resources on irrelevant or low-impact tasks. We introduce \textbf{Attention Orchestration}, a paradigm that extends Transformer-style attention from token representations to workflow-level agent coordination. Our framework, \textbf{Adaptive Goal-aware Attention Orchestration (AGAO)}, dynamically estimates agent importance based on user objectives, graph dependencies, and computational constraints. AGAO combines three components: (1) goal-aware attention, measuring semantic relevance between user goals and agent capabilities; (2) topology-aware attention, modeling structural dependencies in agent graphs; and (3) resource-aware attention, allocating budgets and execution priorities across heterogeneous agents. Together, these mechanisms transform static agent graphs into adaptive systems that focus computation on goal-critical reasoning paths. Experiments across diverse multi-agent workloads show that AGAO improves task effectiveness while reducing unnecessary computation, latency, and token consumption compared with existing graph-based execution strategies. Our work establishes \textbf{Attention Engineering} as a direction for scalable, intelligent multi-agent systems. Code: https://github.com/MingzhouFan97/AGAO.

Mingzhou Fan, Siyuan Xu, Mingxuan Yuan

Multi-Agent System Optimization LLM Agent Orchestration LLM Agent Workflow Optimization Multi-Agent Systems Multi-Agent LLMs

Jul 24, 2026cs.AI

Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems

Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in advance or allow full broadcast. Both can be inefficient because token cost, latency, redundancy, and error propagation increase with the number of active agents and communication links. We model agent selection and communication as a cooperative game with task-conditioned net utility

U(C\mid x)=V(C\mid x)-\sum_{i\in C}c_i

, separating coalition-level costs from agent activation costs. We propose a marginal-value activation rule and greedy router, extend the model to optimize communication edges with per-edge costs, and use estimated Shapley values to predict which agents are worth contacting before and during execution. We connect the problem to submodular maximization and prove two limited guarantees: a curvature-refined bound for a monotone, cardinality-constrained special case, and a tight

1/2

-approximation, with a correction for signed objectives, for an unconstrained non-monotone case via double greedy. Neither guarantee applies directly to the main router, which remains a heuristic. We also prove a Shapley-submodularity sandwich bound linking the error of marginal-value routing to a per-agent diminishing-returns quantity. In synthetic experiments, greedy routing achieves

99.5%

of brute-force-optimal utility while activating

1.96

of

8

agents on average, compared with

38.8%

for full broadcast. Performance is robust to activation cost and redundancy weight but falls to

66%

under strong violations of submodularity or noisy value estimates. We distinguish the framework from Shapley pricing, hedonic coalition formation, and communication-graph pruning, and propose evaluation on real multi-agent LLM benchmarks.

Mojtaba Eslami

University of Calgary

Multi-Agent System Optimization Cooperative Game Theory Multi-Agent Communication LLM Agent Routing

Jul 15, 2026cs.MA

Learning Latency-Aware Orchestration for Multi-Agent Systems

Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from multi-step execution and repeated model invocations. Existing orchestration methods primarily optimize task performance and inference cost, leaving latency largely unaddressed. In MAS, end-to-end latency is governed by the critical execution path, so reducing total cost alone does not reliably reduce latency. Moreover, optimizing latency while preserving accuracy remains non-trivial: naive latency optimization can misassign operator-level credit and degrade task accuracy. To address this gap, we propose Latency-Aware Multi-agent System (LAMaS), a latency-aware orchestration framework for learning-based multi-agent systems. LAMaS addresses this challenge at two levels: at training time, it learns latency-aware execution graphs through constrained optimization with critical-path-aware credit assignment; at inference time, since a graph committed at training time cannot exploit runtime evidence, it complements graph construction with a lightweight controller that adaptively eliminates redundant future agent interactions as execution unfolds. Experiments on four benchmarks show that LAMaS achieves the best latency among evaluated learning-based MAS baselines, reducing end-to-end latency by over 50% while maintaining competitive or better accuracy. LAMaS is also modular and transfers to other MAS with minimal changes, consistently yielding latency reductions.

Xi Shi, Mengxin Zheng, Qian Lou

University of Central Florida

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Orchestration

Jul 7, 2026cs.AI

How Much Does Correctness Cost? Budgeted Placement of Strong Correctors in a Weak Multi-Agent Swarm

A cheap swarm of unreliable agents can be steered to a correct consensus by a few strong, expensive "oracle" correctors. We ask how much one must spend, and where to place the oracles. We model the swarm as a consensus on a graph in which each oracle pins one node toward the truth at a cost-coupled, concave strength, and measure quality by the coherence H(R)=tr M(R)^{-1}. Our first result is that H stays submodular (each added oracle helps less than the last) even when the oracles differ in strength, so a cost-benefit greedy comes within 1-1/e of the best placement at any budget. Inverting the budget gives the budget-correctness frontier B*(eps), the least spend that guarantees an eps-correct consensus: closed-form on the complete graph, and a minimal oracle count k* when oracles cost the same. Whether a budget then buys a few strong oracles or many medium onese curvature of the cost-quality law: diminishing returns favour spreadsharply increasion. Measured onthe Qwen3 ladder (0.6-32B), the law is concave for math verificatio convex foremergent code tracing, so the verdict is genuinely task-dependent.https://github.com/YehudaItkin/budgeted-oracle-placemen

Igor Itkin

Independent Researcher, Tel Aviv, Israel

Submodular Optimization Multi-Agent System Optimization Multi-Agent Coordination Cost-Aware Inference Multi-Agent Consensus

Jul 6, 2026cs.AI

OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement

We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-ready mathematical formulation as well as executable code. Our architecture prioritizes the mathematical modeling step, where dedicated agents extract structures, such as decision variables and constraints, enabling iterative self-correction. We introduce a novel multi-loop validation architecture with four specialized feedback mechanisms, each targeting a distinct failure mode such as misinterpretation, structural defects, mathematical inconsistencies, validation failures, and code errors. Alongside accuracy, our modular design improves the process of solving optimization problems by improving transparency, as each agent exposes its reasoning and feedback, making the full modeling process auditable. Our framework achieves state-of-the-art performance on 3 out of 4 benchmarks across LP, MILP, and Nonlinear Programming tasks, while remaining highly competitive on the remaining dataset.

Adriana Laurindo Monteiro, Nayse Fagundes, Gabriel Mattos Langeloh +4

Instituto de Ciência e Tecnologia do Itaú, Brasil

Multi-Agent System Optimization Large Language Model-Guided Optimization Multi-Agent Reasoning Natural Language to Optimization Modeling

Jul 6, 2026cs.LG

Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets

In liberalised railway systems, operators must set prices dynamically in an environment with partial observability, as they retain private information about their objectives and performance, where regulatory constraints prohibit communication or direct information exchange between competitors to prevent explicit collusion. Consequently, agents must learn to infer strategic interactions only from observable market data which presents a significant challenge for multi-agent reinforcement learning, where standard approaches typically treat observations as unstructured vectors, ignoring the underlying market topology that governs strategic interactions. To address this, an entity graph modelling approach is proposed, which represents the environment as a graph of operational units, rather than decision-making agents or static infrastructure, encoding competition, coordination, and connectivity relations between entities. Then, an extension of the multi-agent twin delayed deep deterministic policy gradient algorithm with graph-based representation learning processes the features of the entities through a multi-layer relational graph convolutional network and aggregates them via a learnt attention mechanism. Experimental results in a rail pricing reinforcement learning environment show that this novel framework achieves higher revenue and stability in two different settings of increasing market complexity compared to a representative selection of relational and non-relational baselines. The code is publicly available at: https://github.com/Kinrre/RelationalRailPricing-RL

Enrique Adrian Villarrubia-Martin, David Muñoz-Valero, Luis Rodriguez-Benitez +2

Department of Technologies and Information Systems, Universidad de Castilla-La Mancha, Paseo de la Universidad 4, Ciudad Real, 13071, Spain · Department of Technologies and Information Systems, Universidad de Castilla-La Mancha, Avenida Carlos III, s/n, Toledo, 45071, Spain · Warwick Manufacturing Group, University of Warwick, Gibbet Hill Road, Coventry, CV4 7AL, UK

Multi-Agent System Optimization Intelligent Transportation Systems Partially Observable RL Dynamic Pricing Multi-Agent Reinforcement Learning

Jul 3, 2026cs.MA

MUTE: Return-Preserving Communication Unlearning for Efficient Multi-Agent Coordination

Inter-agent communication is critical for coordinating Multi-Agent Reinforcement Learning (MARL) agents under partial observability to perform effectively in cooperative games; however, real-world bandwidth constraints demand sparse interactions. Prior approaches primarily address this trade-off by optimizing information-theoretic surrogates. We argue that these statistical proxies are fundamentally misaligned with the true objective: a message can be highly informative yet irrelevant to the joint return of the task. In this work, we propose Message Unlearning for Targeted Efficiency (MUTE), a framework that views communication reduction as a value-guided machine unlearning problem. MUTE rigorously quantifies the Counterfactual Message Value using an attention-based estimator, and systematically unlearns the transmission of low-value messages from a policy trained without any communication constraints. This is achieved through a dual-objective mechanism that enforces communication sparsity while preserving the return of the original joint policy. We derive a theoretical upper bound on the performance gap induced by this sparsification, guaranteeing controlled return degradation. We also empirically evaluate MUTE on various complex multi-agent environments, achieving 80% to 90% bandwidth reduction while maintaining performance comparable to state-of-the-art baselines.

Rui Zuo, Qinwei Huang, Mingyang Li +3

Syracuse University · Air Force Research Laboratory

Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Communication Machine Unlearning Cooperative MARL

Jul 2, 2026cs.NE

Mechanism and Stability Analysis of Metabolic Closed-Loop Metaheuristics

This paper studies the Metabolic Multi-Agent Optimizer (MMAO) at the framework level rather than at the implementation or benchmark level. The central question is whether the metabolic resource loop of private energy, communal budget, role drift, and lifecycle turnover has a framework-level interpretation beyond narrative metaphor. We introduce a generic MMAO state model that abstracts away domain-specific move operators while retaining the resource bookkeeping that defines the framework. Under mild bounded-gain and bounded-spending assumptions, we establish boundedness and nonnegativity properties for private energy, communal budget, role state, and active population size. We then characterize three endogenous behavioral regimes of the loop: contraction under sustained resource deficit, reinvestment under surplus communal accumulation, and search redistribution under heterogeneous marginal returns across agents or subgroups. The analysis is intentionally conservative. It does not claim global convergence of the full adaptive system, universal superiority over specialist optimizers, or a complete stationary characterization of the resulting process. Instead, it identifies which internal regulation properties are generic consequences of the loop and which remain implementation specific. A compact mechanism-validation package on representative continuous and discrete MMAO realizations provides supporting empirical evidence for this reading, but is not intended to replace a full benchmark study. The resulting contribution is therefore a bounded, regenerative, resource-regulated interpretation of MMAO, rather than a complete proof of all adaptive behaviors of the full algorithm family.

Jinliang Xu, Liping Ma

independent researcher in Beijing, China

Multi-Agent System Optimization Algorithmic Stability Metaheuristic Optimization Multi-Agent Systems

Jul 1, 2026cs.NE

MMAO-Cls: Metabolic Multi-Agent Optimization for Joint Feature Selection and Classifier Tuning

This paper studies whether the Metabolic Multi-Agent Optimizer (MMAO) can act as a credible outer-loop optimizer for classification model selection. We propose MMAO-Cls, a mixed-space realization in which each agent jointly encodes a binary feature mask and classifier hyperparameters, while private energy, communal budget, role drift, and lifecycle turnover are mapped to the accuracy-complexity tradeoff of wrapper learning. The implementation is strengthened by deriving feature-budget adaptation from feature-information priors and by regularizing validation reward with both subset compactness and train-validation overfitting gap. We evaluate MMAO-Cls on seven standard tabular benchmarks with three seeds each and compare it against RandomSearch, GA-lite, PSO-lite, and an endogenous no-sharing ablation. On the aggregate validation objective, MMAO-Cls ranks second (

0.9433

) behind GA-lite (

0.9446

). On held-out test performance, it reaches mean score

0.8882

, improving over RandomSearch (

0.8808

) and GA-lite (

0.8857

), remaining close to PSO-lite (

0.8874

) and the no-sharing ablation (

0.8900

), while using the most compact mean held-out feature subset among all compared methods (feature ratio

0.4881

). Pairwise tests show that these margins are not yet statistically significant. The resulting claim is therefore conservative: MMAO-Cls supports classification applicability and compact mixed-space search more clearly than it isolates communal sharing as a decisive standalone advantage.

Jinliang Xu, Liping Ma

independent researcher in Beijing, China · Department of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General Hospital, Beijing, China

Model Selection Multi-Agent System Optimization Classification Multi-Agent Systems Feature Selection Automated Machine Learning+1

Jul 1, 2026cs.NE

MMAO-Dyn: A Metabolic Multi-Agent Optimizer for Dynamic Optimization

This paper studies whether the Metabolic Multi-Agent Optimizer (MMAO) can be credibly derived into a dynamic-optimization method without replacing its core metabolic control loop by external adaptation modules. The proposed MMAO-Dyn maps private energy, communal budget, role drift, success feedback, and lifecycle turnover to a nonstationary setting in which environmental changes repeatedly invalidate previously useful local structure. We evaluate MMAO-Dyn on an 18-scenario synthetic dynamic continuous benchmark matrix covering shifted sphere, shifted Ackley, and shifted Rastrigin landscapes at

10D

,

20D

, and

30D

, with two change severities and 12 seeds per scenario. The comparison layer includes a generic MMAO variant without dynamic derivation, dynamic random search, dynamic PSO-lite, dynamic DE-lite, and three endogenous ablations. Across the full 216-run matrix, MMAO-Dyn attains mean offline error

28.07

, improving over Generic-MMAO (

29.36

), Dynamic-PSO-lite (

34.65

), Dynamic-DE-lite (

67.09

), and Dynamic-RandomSearch (

111.37

). The gains are clearest in aggregate robustness on sphere and Rastrigin families and in 10-step post-change recovery relative to the generic backbone, whereas the seed-aligned comparison with Dynamic-PSO-lite remains unfavorable in win-loss count and the \texttt{NoMemoryRefresh} ablation stays very close to the full method. We therefore position MMAO-Dyn as a credible family-expansion result for MMAO: the metabolic loop can generate meaningful dynamic behavior, but the strongest current value lies in recovery-oriented resource redistribution rather than in universal dominance or in a fully optimized submechanism design.

Jinliang Xu, Liping Ma

Jinliang Xu is an independent researcher in Beijing, China · Liping Ma is with the Department of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General Hospital, Beijing, China

Multi-Agent System Optimization Black-Box Optimization Metaheuristic Optimization Multi-Agent Systems

Jun 30, 2026cs.NE

A Large-Scale Empirical Evaluation of MMAO Under Fair-Budget Continuous and Discrete Benchmarks

This paper evaluates the Metabolic Multi-Agent Optimizer (MMAO) under a stricter empirical protocol rather than reintroducing the framework itself. The study asks whether MMAO's closed-loop resource-allocation principle remains credible under broader, more standard, and more explicitly budget-controlled continuous and discrete benchmarks. The main completed matrix covers eight CEC2017 functions at 10D and 30D with 20 seeds each, and five TSPLIB instances with 20 seeds each, together with stronger reproducible baselines including PSO-lite, ES-lite, and an iterated-greedy 2-opt route baseline. We further add trajectory-level diagnostics for communal budget, success rate, role evolution, and population turnover, plus an auxiliary OR-Library multiple-knapsack slice to extend the discrete evidence beyond routing. Under this protocol, MMAO clearly outperforms the external baseline set on the continuous side and on the TSPLIB side, while the ablation variants remain much closer to the full method than the external baselines are. We therefore position MMAO as a benchmark-backed cross-domain adaptive framework whose most clearly validated value is endogenous resource redistribution under evidence pressure, while also noting that the strongest remaining gap is not basic workability but sharper mechanism isolation and broader competition-grade comparison.

Jinliang Xu, Liping Ma

Jinliang Xu is with the current study team · Department of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General Hospital, Beijing, China

Multi-Agent System Optimization Metaheuristic Optimization Combinatorial Optimization Ising Optimization Multi-Agent Systems

Jun 29, 2026cs.NE

Minimal MMAO: A Resource-Closed-Loop Framework for Adaptive Metaheuristic Search

This paper presents the Metabolic Multi-Agent Optimizer (MMAO) as an adaptive metaheuristic built around endogenous resource circulation. The central premise is that search intensity, exploration--exploitation balance, and lifecycle turnover should be induced by a shared metabolic controller rather than by separately attached schedules. We formulate MMAO through bounded private energy, a communal budget, normalized reward, continuous role adaptation, and resource-financed branching and pruning. The method is then instantiated in both continuous and discrete domains and evaluated on a matched small-scale suite including Sphere, Rastrigin, a synthetic Euclidean TSP, and two TSPLIB instances. The results show a consistent pattern: the same metabolic loop remains workable across domains, the discrete realization remains relatively stable under a compact design, and continuous refinement quality is the main cost of keeping the method lean. Taken together, these findings position MMAO as a coherent framework for adaptive heuristic design rather than a loose collection of operators.

Jinliang Xu, Liping Ma

Department of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General Hospital, Beijing, China

Multi-Agent System Optimization Metaheuristic Optimization Ising Optimization Multi-Agent Systems

Jun 29, 2026cs.AI

ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning

Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training with Decentralized Execution (CTDE) paradigm, policy gradients have remained difficult to compute directly. Prior methods largely follow two approaches: independent factorized updates with centralized critics, which lack general joint-improvement guarantees without value decomposition assumptions, or alternating best-response updates, which can converge to suboptimal Nash Equilibria. In this paper, we show the joint policy gradient admits an exact decentralized decomposition of per-agent terms, each formed from per-agent score functions and decentralized critics. Based on this decomposition, we develop Agent-Chained Policy Optimization (ACPO), where actors are trained independently, with their updates together constituting a single step on the joint policy gradient. Central to this result is a serialized view of the simultaneous joint decision in which agents commit actions one at a time, each conditioning on a belief over preceding actions. The belief acts as the coordination mechanism which ties the independent per-agent updates into a joint gradient step. We evaluate ACPO on Multi-Robot Warehouse, SMACv2, and MA-MuJoCo, where it outperforms strong baselines, with the gap widening as the number of agents grows.

Daiki E. Matsunaga, Junho Na, Tri Wahyu Guntara +4

1KAIST · 2KRAFTON · University of Toronto +2

Multi-Agent System Optimization Multi-Agent Coordination Decentralized MARL Policy Learning Cooperative MARL Multi-Agent Reinforcement Learning

Jun 26, 2026cs.MA

GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems

Multi-agent systems (MAS) built on large language models (LLMs) provide a promising framework for solving complex tasks through role specialization and structured interaction. However, their performance is often limited by miscoordination and, more fundamentally, the lack of fine-grained credit assignment across agents. Existing approaches typically rely on coarse-grained feedback, making it difficult to identify which agents or interaction steps are responsible for errors. We propose Gradient-Based Connections (GBC), an approach for fine-grained attribution and optimization of multi-agent systems. GBC models a MAS as a computational graph and introduces gradient-based connection weights to quantify the influence of each agent's output on downstream agents at the token level. By constructing an attribution graph and propagating task-specific loss signals backward, our method enables precise identification of error sources and targeted prompt optimization. We further develop AgentChord, an efficient implementation that leverages prefix-based gradient computation. Experiments on MultiWOZ and τ-bench show that GBC improves multi-agent performance and outperforms strong single-agent and multi-agent baselines, and higher attribution quality is associated with greater optimization effectiveness. Code is available at: https://github.com/yxc-cyber/AgentChord.

Xiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür +1

University of Illinois Urbana-Champaign

Gradient-Based Attribution Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Systems Prompt Optimization

Jun 26, 2026cs.NE

MMAO: A Metabolic Multi-Agent Optimizer with Endogenous Resource Allocation for Continuous and Discrete Optimization

Traditional meta-heuristics often rely on fixed population sizes, manually chosen search scales, and externally attached parameter-control modules. This paper presents the \textit{Metabolic Multi-Agent Optimizer} (MMAO), a cross-domain optimization framework in which adaptation is derived endogenously from a private-public metabolic resource loop. Each agent carries internal energy, a continuous role state, motion or structural memory, and local search history, while the population shares a communal resource pool. Fitness improvements are converted into normalized metabolic gains through a robust progress scale and a recent success statistic; the same closed loop then regulates sensing intensity, search amplitude, role drift, branching, pruning, respawning, and elite reinvestment. In the continuous setting, MMAO uses energy-regulated symmetric zero-order probing and role-interpolated motion. In the discrete setting, the same control law is instantiated through structural sensing, local route improvement, guided perturbation, and energy-weighted edge reuse. The paper combines an implementation-faithful formulation with a reproducible experimental study on a CEC2017 subset (10D/30D, 20 seeds) and five TSPLIB instances (100 discrete runs in total). The current evidence supports MMAO primarily as a parameter-light, self-calibrating optimization framework whose main validated originality lies in metabolically endogenous resource allocation across heterogeneous search behaviors, rather than as a universally superior optimizer.

Jinliang Xu, Liping Ma

Department of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General Hospital, Beijing, China

Multi-Agent System Optimization Metaheuristic Optimization Combinatorial Optimization Ising Optimization Multi-Agent Systems

Jun 25, 2026cs.MA

QueenBee Planner: Skill-Evolving Communication Topologies for Token-Efficient LLM Multi-Agent Systems

Large language model (LLM) multi-agent systems increasingly depend not only on how individual agents reason, but also on how agents are connected. This paper introduces QueenBee Planner, a framework that treats inter-agent communication topology as a retrievable and self-improving design skill. A pool of worker agents, the task adapter, and the scoring function are frozen; only an outer LLM planner learns to generate temporal communication DAGs specifying who sends information to whom, in which round, who merges messages, and who emits the final answer. Execution traces are distilled into evidence-backed design rules with three actions: \emph{Preserve}, \emph{Modify}, and \emph{Avoid}. To prevent self-evolution from turning lucky runs or plausible but false explanations into policy, QueenBee uses held-out acceptance gates, variance-aware credit, motif-level attribution, transfer trust, insight falsification, and structural deduplication. We evaluate the method on Count-Frequency aggregation and Silo-Bench-style distributed coordination tasks. With fixed workers, self-evolved graph generation produces communication structures that improve over fixed topologies and cold generation. In the CF fulltest setting, the best generated graph reduces RMSE from 12.53 for the strongest fixed topology to 7.87 while also reducing messages, model calls, and token cost; Silo-style results show the same direction of improvement over cold and fixed-topology baselines. These results suggest that multi-agent systems can learn reusable architectural design knowledge rather than merely memorizing task answers.

Congjia Tian, Yuhang Yao, Jiaming Cui

Virginia Tech, Blacksburg, VA · Carnegie Mellon University, Pittsburgh, PA

Multi-Agent LLM Systems Multi-Agent System Optimization LLM Agent Skill Learning Multi-Agent Communication

Jun 24, 2026cs.NE

EvoFlock: evolved inverse design of multi-agent motion

This paper describes an automatic method for adjusting or tuning models of multi-agent motion. Simulating the motion of bird flocks, human crowds, vehicle traffic, and other multi-agent systems is a widely used technique. These simulations model the behavior of a single group member (bird, human, or vehicle). The group behaviors (flock, crowd, traffic) emerge from interactions between group members. These models typically have many numerical control parameters. Even if each parameter is intuitive in isolation, their interaction can be complex and nonlinear. It is challenging to determine which parameters to adjust for the desired change in group behavior. Changing one aspect of group behavior often causes other aspects to change, leading to a tedious process of incremental changes. This work takes an inverse design approach. The desired group behavior is measured with a user-defined objective(/fitness/loss) function and optimized with a genetic algorithm. The objective function used here for basic flocking rewards proper spacing with neighbors, flying near a desired speed, and avoiding obstacles. Interestingly, the vivid alignment seen in bird flocks appears to emerge from maintaining proper spacing between flockmates.

Craig Reynolds

unaffiliated researcher

Multi-Agent System Optimization Multi-Agent Systems Inverse Design Emergent Behavior in Multi-Agent Systems

Jun 23, 2026cs.AI

ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling

Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sustain gains as depth increases, exhibiting degradation, early plateauing, or saturation. We propose ReM-MoA, a memory-augmented MoA framework that sustains scaling through two mechanisms: (1) a Ranked Reasoning Memory that persistently stores and ranks reasoning traces from all layers using a comparative Reviewer Agent, and (2) a Curated Diversified Memory Routing scheme that exposes different agents to distinct combinations of successful and failed traces, preserving exploration diversity while propagating high-quality reasoning. We further introduce an optional multi-domain Reviewer distillation pipeline that improves ranking quality through frontier-model supervision. Across five reasoning benchmarks spanning math, formal logic, code, knowledge, and commonsense, ReM-MoA consistently outperforms prior MoA variants across both depth and width scaling, and its advantage widens with depth, establishing structured cross-layer reasoning memory as a key missing mechanism for scalable multi-agent inference.

Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +5

University of Southern California · Iowa State University · Cisco AI Research

Multi-Agent System Optimization LLM Agent Memory Multi-Agent Systems Multi-Agent Reasoning Memory-Augmented Language Model Agents

Jun 22, 2026cs.LG

MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?

Multi-agent systems (MAS) offer a scalable path forward for agentic AI, comprising multiple LLM-based agents, each assigned a system prompt and a position within a workflow that governs inter-agent coordination and output aggregation. System prompts thus form a critical and accessible optimization surface: they specify agents' roles and behaviors, enabling system-level improvements without model finetuning. Although prompt optimization has shown substantial potential for single LLMs, extending it to MAS poses distinct challenges, notably an exponentially growing search space. It remains unclear whether, when, and by how much prompt optimization improves MAS performance, and how sensitive such gains are to system configuration. In this work, we systematically study system-prompt optimization across a broad range of MAS setups varying in task, workflow, communication protocol, and team size, benchmarking two prompt optimizers that naturally extend state-of-the-art single-agent methods. The results reveal its potential to unlock significant gains while exposing open challenges, characterizing when and how much prompt optimization helps across diverse MAS settings.

Juyang Bai, Laixi Shi

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA.

Multi-Agent LLM Systems Multi-Agent System Optimization AI Agent Benchmarks Prompt Optimization

Jun 18, 2026q-fin.RM

Optimal Order of Multi-Agent and General Many-Body Systems

This paper develops a general framework for analyzing multi-agent systems with feedback loops between agents actions and collective observations. The framework is built on two fundamental agent-level variables: power, which measures agent influence on collective outcomes, and response functions, which determine how agents react to observations. We derive how macroscopic properties, including total power, useful power, entropy, order, fragility, and mobility, emerge from these two variables of heterogeneous agents. To study the trade off between growth and resilience, we introduce a system-level utility function parameterized by a risk-appetite coefficient and derive an optimal degree of order that balances productivity, stability, and adaptability. The analysis suggests that stronger synchronization can increase collective output but may also increase systemic fragility and reduce mobility. We further argue that order, entropy, information, and useful energy are task-dependent and system-relative concepts whose meanings depend on the objectives of the system. By measuring and designing agent power distributions and response functions, it may be possible to better understand, predict, and optimize collective behavior and identify the conditions under which collective intelligence and optimal order emerge.

Jake J. Xia

Harvard Management Company · Research Affiliate at Massachusetts Institute of Technology

Dynamical Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Systems Emergent Behavior in Multi-Agent Systems

Jun 18, 2026cs.AI

A Multi-Agent system for Multi-Objective constrained optimization

Many decision-making problems in computing and networking systems can be naturally formulated as cost-minimization problems under performance constraints. In dynamic environments, reinforcement learning (RL) is often used to solve such problems at runtime by embedding both costs and constraint violations into a single scalar reward through weighted penalty terms, following a Lagrangian-inspired formulation. However, in this context the behavior of the learned policy critically depends on the choice of these weights, which are typically selected manually. This makes it difficult to identify an appropriate trade-off between optimizing the primary objective and effectively avoiding constraint violations, particularly in non-stationary environments where their relative importance may change. This paper presents MAMO (Multi-Agent system for Multi-Objective constrained optimization), an approach to tackle this balancing problem through multi-agent RL. MAMO decouples task execution from objective design by formulating the selection of reward weights as a learning problem, providing a !rst step towards more autonomous and robust RL-based solutions for constrained optimization problems in dynamic environments.

Federica Filippini

University of Milano-Bicocca Milan, Italy

Multi-Objective Reinforcement Learning Multi-Agent System Optimization Reinforcement Learning Reward Shaping Constrained RL Multi-Agent Reinforcement Learning

Jun 18, 2026cs.RO

Deep-Unfolded Coordination

Distributed optimization is a highly scalable and structurally transparent technique to solve multi-agent robotics problems; however, such methods often suffer from the need for highly-specialized, problem-specific hyperparameter tunings. In this work, we propose Deep Coordinator, a deep-unfolding framework that learns to dynamically adjust the hyperparameters of ADMM-DDP, a popular distributed solver for robotics tasks, at solve-time in response to optimizer performance. Our architecture consists of unrolling a fixed number of ADMM-DDP iterations into a neural network with learnable functions between layers mapping the optimizer state to the next hyperparameters. To the best of our knowledge, Deep Coordinator is the first deep-unfolding framework to adapt the penalty parameters of a non-convex optimizer at solve-time; we show that the mainstream supervised approach can yield degenerate solutions when training such models, and propose an unsupervised learning scheme. On simulations with fleets of cars and quadrotors, Deep Coordinator produces trajectories of comparable quality 6.18-9.44x faster than conventional solvers. Furthermore, Deep Coordinator retains its performance benefits when deployed to systems up to 8x larger than trained on.

Hunter Kuperman, Minchan Jung, Rahul V. Ghosh +2

Autonomous Control and Decision Systems Laboratory Georgia Institute of Technology United States

Trajectory Optimization Multi-Agent System Optimization Distributed Optimization Alternating Direction Method of Multipliers Multi-Robot Coordination Deep Unfolding

Jun 18, 2026cs.MA

SIGMA: Skill-Incidence Graphs for Compositional Multi-Agent Design

Existing graph-based multi-agent system (MAS) designers mainly improve collaboration by optimizing communication topologies over predefined agents, roles, or groups. However, because each node remains a closed-set entity, these methods struggle to generalize to tasks that require unseen combinations of capabilities. We propose SIGMA, a skill-incidence graph framework that constructs agents as task-conditioned bundles of reusable skills. Given a task and a skill library, SIGMA predicts a skill-agent incidence matrix, composes agent node embeddings from selected skills, and decodes a communication topology over the constructed agents. During execution, skill-specific mailboxes route messages to the relevant assigned capabilities, making the incidence structure directly operational. Across six reasoning and coding benchmarks with three base LLMs, SIGMA achieves the best average performance and improves over CARD, the strongest non-compositional topology-based baseline, by 2.06, 2.36, and 1.75 points, respectively. It also shows stronger robustness to unseen skill libraries, with an average performance drop of only 0.96 points. These results suggest that compositional node construction is a complementary and important axis for multi-agent design beyond communication topology optimization. Code is available at https://anonymous.4open.science/r/SIGMA-2338/.

Kun Zeng, Yu Huo, Siyu Zhang +5

Sun Yat-sen University · School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen · Taiyuan University of Technology +1

Multi-Agent System Optimization Multi-Agent Systems Multi-Agent Reasoning Multi-Agent Communication

Jun 16, 2026cs.CL

Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications

Large language model (LLM)-based multi-agent systems demonstrate strong performance on complex reasoning and task execution, enabling broad enterprise applications. However, production deployment remains challenging due to domain-specific customization requirements and high latency and inference costs in agentic workflows. We propose a unified framework for customization and efficient deployment of multi-agent systems in real-world settings. The first stage, Agentic Model Customization, combines continual pretraining, supervised fine-tuning, and preference optimization to adapt a compact model to specialized domains while retaining strong agentic capabilities. The second stage, Inference Optimization, integrates speculative decoding and FP8 quantization with targeted calibration to enable cost-efficient serving with minimal quality loss. Across enterprise workloads, our framework enables rapid domain adaptation and achieves a 4.48x speedup in throughput while maintaining performance and improving robustness on long-tail scenarios.

Paresh Dashore, Shreyas Kulkarni, Uttam Gurram +5

AI Foundations, Capital One

Multi-Agent LLM Systems Multi-Agent System Optimization LLM Fine-Tuning LLM Inference Acceleration

Jun 12, 2026cs.MA

Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning

Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contributions. We propose Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents. Theoretically, we formulate cooperative MOMARL as a team-optimal equilibrium problem, and show that, under suitable conditions, preference diversity yields a first-order improvement in the team objective. Experiments on multiple cooperative MOMA environments and a practical traffic-control scenario show that PCMA improves both performance and trade-off coordination.

Pengxin Wang, Lihao Guo, Yi Xie +3

Department of Electrical and Computer Engineering, University of Arizona

Multi-Objective Reinforcement Learning Multi-Agent System Optimization Multi-Agent Coordination Cooperative MARL

Jun 10, 2026cs.AI

Arbor: Tree Search as a Cognition Layer for Autonomous Agents

Arbor is a multi-agent framework that introduces structured tree search as a cognition layer for autonomous agents operating in large, stateful action spaces. Prior autonomous optimization systems operate on isolated targets with stateless evaluation. Arbor instead maintains an explicit search tree of scored hypotheses that serves as the shared working memory across agents, evolving with every measurement, treating failures as diagnostic signal that reshapes subsequent exploration, and expanding as prior successes shift the bottleneck distribution. We validate Arbor on full-stack LLM inference optimization, a domain where achieving peak performance has historically required coordinated effort from engineering teams across the application, framework, compiler, kernel, and hardware stack. Arbor pairs an Orchestrator agent, which drives optimization by delegating to Domain Specialists across the inference stack, with a Critic agent that safeguards stability through root-cause analysis, introspection, and measurement validation -- a checks-and-balances architecture where neither agent can unilaterally drive the system. Agent capabilities are decomposed into hard skills (domain expertise) and soft skills (coordination protocols that determine how contributions compose), enabling fully autonomous multi-day campaigns. Arbor achieves up to 193% inference throughput-latency Pareto improvement over vendor-optimized baselines, while a single agent without the harness plateaus at +33% throughput improvement and crashes irrecoverably within hours. Arbor generalizes to multiple generations of hardware platform, and run-to-run variance is within 2 percentage points demonstrating that the method is hardware-agnostic and reproducible.

Neha Prakriya, Chaojun Hou, Zheng Gong +5

Training and Inference Optimization Team AMD

LLM Inference Efficiency Multi-Agent System Optimization Multi-Agent Orchestration Autonomous Experimentation Autonomous Research Agents

Jun 9, 2026cs.AI

INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration

Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and model features. However, these methods do not consider the runtime state of the serving infrastructure. On shared GPU clusters under concurrent load, this infrastructure blindness causes systematic resource underutilization: preferred models accumulate deep request queues while equally capable alternatives sit idle. In multi-agent pipelines, where each query triggers multiple sequential model calls, these delays then compound across every downstream step. Closing this gap is challenging because the relevant infrastructure signals (queue depths, KV-cache pressure, latencies) are dynamic and noisy, and they must drive three different decisions: planning, per-step routing, and scheduling. We introduce INFRAMIND, a framework that makes the entire multi-agent stack infrastructure-aware. An infra-aware planner conditions topology and role selection on real-time system load and remaining budget, biasing toward simpler graphs under congestion and richer ones at low load. An infra-aware executor then observes per-model queue depths, cache utilization, and response latencies at each agent step to decide which model to call and how deeply to reason; a budget-aware scheduler further reorders each model's queue so that urgent requests are served first. Cast as a hierarchical constrained MDP and solved end-to-end via reinforcement learning, the system learns to balance quality against latency automatically. Across five benchmarks, INFRAMIND delivers up to +7.6 pp accuracy over the prior baseline at low load with up to 7x lower latency, and sustains up to 99.9% SLO compliance under high load where every baseline drops below 50%.

Ahasan Kabir, Jiaqi Xue, Mengxin Zheng +1

University of Central Florida

Multi-Agent System Optimization Multi-Agent Orchestration LLM Inference Scheduling LLM Agent Workflow Optimization LLM Inference Serving RL for LLM Agents+1

Jun 9, 2026cs.LG

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet deploy only a single workflow, leaving complementary candidates unused, while query-level methods synthesize a new workflow per query at substantial inference cost. Our motivating analysis shows these paradigms are more complementary than competing: workflows discovered during offline search often solve different subsets of queries, and many queries handled by expensive query-level generation can already be solved by cheaper precomputed workflows. This suggests a different objective: rather than searching for one universally best workflow or regenerating one per instance, we should build a compact bank of reusable, complementary workflows and select among them adaptively at inference time. Doing so requires solving three coupled problems: generating complementary rather than redundant candidates, compressing them into a small deployable portfolio, and assigning each query to the right workflow under a performance-cost trade-off. To this end, we present FlowBank, a three-stage framework for portfolio-based agentic workflow optimization. Diversifying proposes DiverseFlow to steer search toward under-covered queries and produce a high-coverage candidate pool. Curating proposes CuraFlow to compress this pool into a compact portfolio with minimal redundancy. Matching casts deployment as edge-value prediction on a query-workflow bipartite graph and routes each incoming query to the portfolio member with the best predicted utility. Across five benchmarks, FlowBank achieves the highest average score among the evaluated methods while remaining cost-competitive, improving over the strongest automated and handcrafted baselines by 4.26% and 14.92% relative, respectively.

Lingzhi Yuan, Chenghao Deng, Fangxu Yu +3

University of Maryland, College Park · Amazon

Multi-Agent LLM Systems Multi-Agent System Optimization Large Language Model-Guided Optimization Agentic Workflows LLM Agent Workflow Optimization

Jun 9, 2026cs.MA

Decentralized Multi-Agent Systems with Shared Context

Multi-agent systems (MAS) can scale large language model agents on long-horizon tasks by running them in parallel, yet existing designs waste much of this parallelism in bubbles: agent time spent waiting on others or redoing a peer's work. These bubbles stem from how agents communicate. Independent agents share nothing and rediscover what their peers have already found; peer-communicating agents wait at synchronous rounds; and under centralized orchestration, the main agent blocks on its sub-agents while progress is relayed. We propose Decentralized Language Models (DeLM), a MAS framework on top of existing agent harnesses that squeezes out these bubbles by replacing the main agent with a shared context and a task queue. Agents asynchronously claim tasks, publish findings as soon as they are available, and build on or correct one another's progress, with every peer's status visible to all. On long-horizon tasks from Terminal-Bench 4.0 and DeepSWE v1.1, and on SWE-bench Verified, DeLM is both more accurate and faster than Codex, Claude Code, their native subagents, and AOrchestra in every setting, improving accuracy by up to 17.5 points over the strongest baseline and running up to 2.49x faster than the harness it builds on. On ProgramBench, where agents rebuild programs from scratch, DeLM makes faster progress than Claude Code and finishes a 120-minute budget up to 19.9 points higher in test pass rate. The code is available on our project website at https://yuzhenmao.github.io/DeLM/.

Yuzhen Mao, Jerry Gu, Aadi Chauhan +3

Stanford University

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Systems Multi-Agent Coding

Jun 7, 2026cs.RO

PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback

Achieving fully automated, physically plausible 3D motion synthesis is a core objective in graphics and generative AI. However, configuring complex environmental force fields still relies entirely on manual expert intervention, creating a severe bottleneck for large-scale simulation data generation. Existing automated methods primarily focus on material optimization and exhibit severe modality gaps and technical flaws when applied to the vastly more complex force field optimization space: naive Large Language Models (LLMs) lack underlying simulation feedback, causing severe physical inaccuracies, while traditional Score Distillation Sampling (SDS) suffers from sluggish gradients, local optima entrapment, and a mathematical inability to dynamically switch discrete force fields. To address this, we propose PhysAgent, the first simulator-in-the-loop multi-agent framework that leverages multimodal inputs for automated, physically grounded 4D synthesis. By decoupling intrinsic materials from extrinsic dynamics, PhysAgent utilizes a Semantic Agent equipped with an externalized Force Field Skill module to master simulation rules and generate valid initializations. Subsequently, the Refine Agents, driven by Trajectory-Grounded Multi-Agent Feedback, leverage vision foundation models to extract dense point trajectories from rendered frames. By converting these explicit motion trajectories into structured textual descriptors, the agent harnesses LLM commonsense reasoning to execute zero-shot macroscopic leaps, effectively escaping local optima and dynamically switching discrete force fields. Extensive experiments demonstrate that PhysAgent rapidly generates stable, diverse physical scenes from arbitrary multimodal prompts, significantly outperforming existing baselines in both generation diversity and physical accuracy.

Chunji Lv, Jiaxi Ye, Yuchen Jiang +2

Beijing Institute of Technology

Multi-Agent System Optimization 3D Scene Generation Multimodal Generation Multi-Agent Systems Physics-Based Simulation 4D Scene Generation

Jun 5, 2026cs.MA

GRPO Does Not Close the Multi-Agent Coordination Gap

We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a clean test bed. Across 630 episodes spanning seven models and three philosopher counts, four frontier closed-source systems reach mean reward 0.45 to 0.87 and Mistral-Small 24B reaches 0.83 to 0.99, while Qwen3-14B reaches 0.13 to 0.35. We then ask whether group relative policy optimization (GRPO) on rollouts from the task itself can close the gap and find that it cannot: a Welch's t-test on per-episode reward at five philosophers gives p = 0.66 and a Hedges' g of -0.11, with no statistically significant change at ten or fifteen philosophers either. Two further observations qualify the result. The training reward of both 8B and 14B runs peaked at step nine and then declined, so the default saved checkpoint at step 15 is strictly worse than several earlier ones. The four-term reward we use admits a degenerate maximum at zero actions, which DeepSeek-R1-Distill-Qwen-7B and Mistral-Small 24B at five philosophers both inhabit, with mean reward 1.0 and 0.83 respectively at zero meals. The bottleneck for an open-weight 14B model on multi-agent coordination is not training compute but training methodology: reward shaping that does not collapse to a no-action maximum, checkpoint discipline that does not depend on the final step, and curriculum across problem scales.

Najmul Hasan, Prashanth BusiReddyGari

Department of Mathematics and Computer Science, University of North Carolina at Pembroke, Pembroke, NC, USA

Multi-Agent System Optimization Multi-Agent Coordination Group Relative Policy Optimization Multi-Agent LLMs

Jun 3, 2026cs.AI

What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems

Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language. However, this free-form communication can rapidly inflate token usage, consume the shared context window, and ultimately affect both system performance and inference cost. We analyze five common inter-agent communication strategies across two MAS topologies, finding that no fixed strategy is universally optimal. Instead, effective inter-agent messages consistently preserve action-centered information needed by downstream agents. Building on this, we propose the PACT (Protocolized Action-state Communication and Transmission), which treats inter-agent communication as a public state-update problem and projects each raw agent output into a compact action-state record before it enters shared history. Across different MAS topologies, PACT consistently improves the performance-cost trade-off, achieving comparable or stronger task performance with substantially fewer tokens. The gains extend to production coding harnesses: PACT lifts OpenHands' resolve rate at -10% tokens-per-resolved, and is resolve-neutral on SWE-agent while halving input tokens. Our code is publicly available at https://github.com/iNLP-Lab/PACT.

Chen Huang, Yuhao Wu, Wenxuan Zhang

Singapore University of Technology and Design

Multi-Agent LLM Systems Multi-Agent System Optimization Agent Communication Protocols Multi-Agent Communication

Jun 3, 2026cs.CL

Streaming Communication in Multi-Agent Reasoning

Multi-agent reasoning systems adopt a "generate-then-transfer" paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA, a multi-agent reasoning system that streams each reasoning step to downstream agents as soon as it is generated, pipelining adjacent agents and thus reducing latency. Surprisingly, this pipelining also improves effectiveness: because multi-step reasoning quality is non-uniform and early steps are more reliable than later ones, working with these reliable early steps instead of the full chain prevents error-prone late steps from misleading downstream agents. We formalize both advantages with the first closed-form joint analysis of stream, serial, and single protocols, deriving the effectiveness ordering, speedup upper bound, and cost ratio. Across eight reasoning benchmarks spanning mathematics, science, and code, two frontier LLMs (Claude Opus 4.6 and GPT-5.4), and three topologies (Chain, Tree, Graph), StreamMA outperforms both baselines (avg. +7.3 pp, max +22.4 pp on HMMT 2026; Claude Opus 4.6-high). Beyond these contributions, we discover a "step-level scaling law": increasing per-agent steps consistently improves both effectiveness and efficiency, a new scaling dimension orthogonal to and composable with agent-count scaling.

Zhen Yang, Xiaogang Xu, Wen Wang +3

HKUST(GZ) · ZJU · Alibaba Group +1

Multi-Agent LLM Systems Multi-Agent System Optimization LLM Agent Workflow Optimization Scaling Laws Multi-Agent Reasoning Multi-Agent Communication

Jun 3, 2026cs.CL

GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation

LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual model capabilities, but also on the policies by which agents interact and adapt. Multi-agent reinforcement learning can optimise these interaction policies, but its reward design often remains task-specific and weakly grounded in interaction structure. To address this gap, we propose GARL, a GAme-theoretic Reinforcement Learning framework for multi-agent strategic prioritisation. GARL formalises strategic prioritisation as a two-stage game: competing agents first allocate strategic resources over a shared candidate set, and a higher-level arbiter then produces the final ranking. The resulting game-theoretic utilities are converted into role-specific reinforcement signals, allowing policy optimisation to be guided by structured interaction. We instantiate GARL on issues-in-dispute ranking, where the goal is to prioritise core issues in legal proceedings. Experiments show that GARL improves ranking performance, enables small open-source LLMs to become competitive with a strong closed-source LLM under the same candidate-ranking setting, and yields gains in legal-domain competence and broader strategic decision-making. Overall, GARL demonstrates how game-theoretic interaction structure can be turned into reinforcement-learning objectives, providing a principled approach to policy optimisation in multi-agent strategic prioritisation.

Yuxiao Ye, Yiwen Zhang, Huiyuan Xie +2

1Tsinghua University · 2The Hong Kong University of Science and Technology (Guangzhou)

Multi-Agent LLM Systems Multi-Agent System Optimization Reinforcement Learning Multi-Agent Reinforcement Learning

Jun 2, 2026cs.SE

SPOQ: Specialist Orchestrated Queuing for Multi-Agent Software Engineering

Multi-agent AI systems show promise for automating software engineering tasks, yet existing approaches suffer from coordination overhead, quality control gaps, and limited human oversight. We introduce SPOQ (Specialist Orchestrated Queuing), a methodology combining three innovations: (1) wave-based topological dispatch that computes parallel execution waves from task dependency graphs; (2) dual validation gates applying quality metrics before execution (planning validation) and after (code validation) to reduce rework cycles; and (3) Human-as-an-Agent (HaaA) integration, where a human specialist participates in decomposition and can be consulted during execution. SPOQ uses a three-tier agent hierarchy (Opus workers, Sonnet reviewers, Haiku investigators) to optimize cost-quality tradeoffs. We evaluate SPOQ through four experiments. Experiment 1: wave dispatch approaches the critical-path lower bound (ratio 1.03--1.11, speedup up to 14.3x); on a 2-slot local backend it delivers a stable 1.4x speedup. Experiment 2: SPOQ improves planning coverage from 93.0 to 99.75, eliminates cyclic plans, and lifts parallelism from 31.0 to 75.25. Experiment 3: dual validation reduces defects from 0.34 to 0.20 per task and lifts test pass rate from 91.25% to 99.75%. Experiment 4: human review reduces residual defects from 0.47 to 0.03 per task. Results are replicated on a locally hosted open-weights model (Qwen3.6-35B-A3B), verifying gains are attributable to orchestration rather than any specific model. A longitudinal study across 17 repositories, 8,589 commits, 1,822 tasks, and 13,866 tests (99.87% pass rate) provides ecological validation.

Royce Carbowitz, Dheeraj Kumar

Pinpoint Technologies LLC

Multi-Agent System Optimization Software Engineering Agents Multi-Agent Orchestration Human-in-the-Loop AI Multi-Agent Planning

Jun 2, 2026cs.LG

MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency

Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limited GPU resources has bottlenecks. Skill-based routing creates skewed expert demand, and combining instruction-tuned LLMs with long-reasoning models results in extreme variability in generation lengths. Consequently, traditional scheduling strategies suffer from significant GPU idling and throughput collapse due to load imbalances. We present MOSAIC, a scheduling framework to accelerate MoA workloads. First, we formulate an Integer Linear Program (ILP) based scheduler that jointly optimizes expert placement and per-worker prompt assignment from offline-profiled costs, replicating reasoning experts across workers while pinning lightweight ones. Second, MOSAIC uses confidence-aware adaptive aggregation, leveraging inter-expert agreement to bypass the heavy final aggregator LLM for consensus queries. In our 4-GPU system, MOSAIC achieves up to 2.5x expert-stage, 4.23x aggregator-stage and 1.7~2.3x end-to-end speedups over the baseline scheduler, while matching accuracy within 0.1pp.

Saptarshi Mitra, Yifan Zhang, Rachid Karami +5

University of California, Irvine, USA · University of Southern California, Los Angeles, USA · Intel, USA

LLM Inference Efficiency Multi-Agent System Optimization LLM Inference Scheduling LLM Agent Workflow Optimization LLM Inference Serving Multi-Agent LLMs

Jun 1, 2026cs.AI

MOC: Multi-Order Communication in LLM-based Multi-Agent Systems

Despite the remarkable progress of Large Language Model (LLM) based Multi-Agent Systems, most research focuses on optimizing coordination topology while largely underexploring the equally critical problem: how to transmit and optimize messages among agents effectively? Current communication schemes typically rely on the direct concatenation of first-order neighbor responses, which induces a restricted evidence receptive field and leads to the dilution of crucial insights over multi-hop paths. To address these limitations, we propose the Multi-Order Communication (MOC) scheme, which reconstructs the inter-agent communication to capture multi-hop dependencies and incorporates a structural message consolidation strategy to ensure efficiency. Specifically, we formalize the communication mechanism to construct a structured multi-order evidence stream, and subsequently design a Semantic-Topological Merging algorithm to optimize semantic fidelity within token constraints. Extensive experiments across six diverse datasets and LLM backbones of varying parameter scales demonstrate that MOC consistently improves task performance and reduces communication costs. The code is available at https://github.com/yao-guan/MOC.

Yao Guan, Lin Wang, Zhihu Lu +3

Fudan University · Nanjing Normal University · Pennsylvania State University

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Communication

Jun 1, 2026cs.AI

Coordination Graphs for Constrained Multi-Agent Reinforcement Learning

Constrained Multi-agent reinforcement learning (CMARL) faces two intertwined challenges: the joint action space grows exponentially with the number of agents, and additional requirements couple agents in ways that reward structure alone does not capture. We introduce Coordination Graphs for Constrained Multi-Agent Reinforcement Learning (CG-CMARL), a framework that addresses both challenges by combining coordination graphs with Lagrangian duality. The system decomposes the joint problem into pairwise regions, each served by a set of shared Q-functions, one for the primary objective and one for each of the constraints, so that the number of learned models is independent of the number of agents. At execution time, Max-Sum message passing coordinates actions across the factor graph, while a Lagrangian multiplier controls the objective--constraint tradeoff, allowing a single trained model to trace a Pareto front without retraining. We provide convergence guarantees under mild conditions, together with a compositional error bound that decomposes into separate interpretable sources, each traceable to a specific design choice and independently controllable. Experiments on cooperative navigation tasks (where teams of up to 10 agents must coordinate to reach target positions while satisfying pairwise constraints) show that our method produces Pareto fronts dominating established baselines trained at fixed reward-shaping ratios, while scaling to team sizes where centralized approaches become intractable.

Santiago Amaya-Corredor, Miguel Calvo-Fullana, Anders Jonsson

Department of Engineering, Universitat Pompeu Fabra, Barcelona, Spain

Multi-Objective Reinforcement Learning Multi-Agent System Optimization Constrained RL Constrained Optimization Cooperative MARL

Jun 1, 2026cs.MA

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation. However, existing multi-agent debate and collaboration frameworks typically adopt fully connected communication, causing the number of messages, token costs, and end-to-end latency to grow approximately quadratically with the number of agents; although fixed sparse topologies reduce overhead, they cannot adapt communication relationships to different task instances or intermediate reasoning states, making them prone either to preserving low-value interactions or to losing critical error-correction information. To address this problem, this paper proposes DySCo (Dynamic Sparse Consensus), a dynamic trust-aware sparse consensus mechanism. In each round of reasoning, DySCo estimates the value of communication edges based on agent reliability, answer divergence, and task relevance, and selects a small number of high-value edges for message exchange under budget constraints; it then aggregates the answers of different agents through dynamic trust weights and terminates the discussion early once consensus stabilizes. This mechanism replaces universal broadcasting with on-demand communication, thereby reducing communication overhead while preserving essential cross-validation information. We further present analyses of communication complexity and consensus stability, and evaluate the performance of DySCo on mathematical reasoning, logical reasoning, and factual question-answering tasks.

Wanshuang Gou, Zihan Liu

Chengdu University

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Debate Multi-Agent Consensus Communication Complexity+1

May 31, 2026cs.LG

When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding

Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks, such as coding, through parallelization and context isolation. However, adding agents in practice introduces inter-agent communication overhead, which incurs extra cost and can sometimes offset the efficiency gains. We formalize multi-agent orchestration as a graph partitioning problem that captures the communication-to-computation trade-off: task decomposition can shorten critical-path computation, but cross-agent dependencies require costly context transfer. We instantiate this view in repository-level software engineering and present Cohesion-aware Coder (Co-Coder), which builds dependency graphs from static analysis, isolates structural hub files, partitions the graph via community detection, and executes the partition with a dependency-aware scheduler. Across 28 real-world tasks on DevEval and CodeProjectEval, Co-Coder advances the Pareto-frontier over sequential and file-based parallel baselines as well as Claude Code with Agent Teams, lifting pass rate by up to 14.0%, achieving up to a 2.10x wall-clock speedup, and reducing API cost by up to 35%, with the largest gains on the most dependency-dense projects. Co-coder demonstrates how cohesion-aware orchestration can make parallel coding agents both theoretically grounded and practically efficient, suggesting a broader design principle for multi-agent systems.

Xu Yang, Lunyiu Nie, Ethan Chandra +3

1The University of Texas at Austin · University of Oxford

Multi-Agent System Optimization Software Engineering Agents Multi-Agent Orchestration Multi-Agent Systems Multi-Agent Coding

May 29, 2026math.OC

S $^3$ LDBO: A Snapshot Single-Loop Algorithm for Decentralized Bilevel Optimization

Networked AI systems increasingly rely on multiple agents that collaboratively learn and adapt models over communication networks. In such systems, bilevel formulations naturally arise in hyperparameter optimization, data cleaning, and meta-learning, but the repeated evaluation of gradients, Jacobians, and Hessians can impose a substantial computational burden on individual agents. To address this challenge, we propose Snapshot-SLDBO (S

^3

LDBO), an efficient single-loop decentralized bilevel optimization algorithm that enables agents to intermittently skip expensive derivative evaluations through a snapshot mechanism. This mechanism can be interpreted as an autonomous computation-adaptation strategy for networked AI, where agents selectively perform costly local updates while maintaining global collaborative learning. We establish the ergodic iteration complexity and the high probability nonergodic iteration complexity of the proposed algorithm within a deterministic setting. Experimental results on hyperparameter optimization with synthetic and MNIST datasets, data hyper-cleaning on Fashion-MNIST, and decentralized meta-learning on miniImageNet demonstrate that the proposed algorithm improves computational efficiency while maintaining competitive learning performance.

Chao Yin, Youran Dong, Shiqian Ma +2

School of Mathematics, Hohai University, Nanjing, P. R. China · School of Mathematics, Nanjing University, Nanjing, P. R. China · Department of Computational Applied Mathematics and Operations Research, Rice University, Houston, USA

Multi-Agent System Optimization Bilevel Optimization Decentralized Optimization

May 29, 2026cs.LG

Learning Multi-Agent Coordination via Sheaf-ADMM

We present a differentiable optimization framework for multi-agent coordination. An input is decomposed into overlapping local views, each processed by an agent that solves a convex subproblem parameterized by a neural encoder. Agents coordinate through the Alternating Direction Method of Multipliers (ADMM) with inter-agent constraints specified by a cellular sheaf. The sheaf specifies which aspects of neighboring solutions must agree, allowing for heterogeneous notions of global consensus. Backpropagating through the unrolled optimization jointly trains all components of the multi-agent system. We evaluate on maze pathfinding, image classification, and Sudoku, where agents with individually insufficient local views learn to coordinate to produce correct global outputs. On MNIST, the local-view decomposition yields improved robustness to distribution shifts relative to a standard CNN. On Sudoku, the optimization-derived structure yields markedly higher solve rates than parameter-matched MPNN baselines. Finally, the ADMM structure exposes distinct primal, consensus, and dual state variables, opening the coordination dynamics to direct analysis and intervention -- a property unavailable in standard message-passing architectures.

Jeffrey Seely, Bartłomiej Cupiał, Llion Jones

Sakana AI, Tokyo, Japan · University of Warsaw · AKCES NCBR

Multi-Agent System Optimization Multi-Agent Coordination Alternating Direction Method of Multipliers Multi-Agent Consensus Differentiable Optimization