Multi-Agent Coordination

Ask about this topic

Overview

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

Latest papers

CardsList

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

May 28, 2026

Kernel-based potential mean-field games with unbiased random Fourier UU-statistics

We study the subclass of potential mean-field games in which the running interaction cost and the terminal target cost are both expressed through reproducing-kernel maximum mean discrepancy (MMD) penalties, and develop a computational framework that exploits this kernel structure. Both costs are estimated from finite-sample empirical distributions using a random Fourier U-statistic representation that is unbiased and has linear cost in the batch size. The drift of the controlled diffusion is parametrized by a neural network and trained via stochastic gradient descent. For population near-minimizers we prove convergence to the terminal-constrained problem as the penalty diverges, and show that the same limit is recovered almost surely when the learned controls are evaluated on independent finite samples under explicit coupling conditions on the penalty, random-feature count and sample size. The framework includes the kernel-MMD-penalty Schr{ö}dinger bridge problem as the special case of a vanishing interaction cost. Numerical experiments illustrate the method on the Schr{ö}dinger bridge problem in dimensions up to one hundred, and on an electric vehicle charging coordination problem with per-vehicle physical heterogeneity, where an aggregate-demand congestion cost represents price-feedback competition at the population level and the terminal MMD penalty shapes the state-of-charge distribution at the deadline.

Yumiharu Nakano

Department of Mathematical and Computing Science, Institute of Science Tokyo

Multi-Agent CoordinationMean Field GamesSchrödinger BridgesMean-Field Theory
AskPDF
May 27, 2026

Differentiable Belief-based Opponent Shaping

Human coordination often relies on the ability to influence the beliefs of others through strategic action. In multi-agent reinforcement learning, opponent shaping attempts to replicate this influence, though existing methods typically operate within an opponent's parameter, policy, or value space. Meanwhile, belief-manipulation techniques in hidden-role games often rely on hard-coded objectives, such as deception or belief saturation. We propose Differentiable Belief-based Opponent Shaping (D-BOS), a first-order method that treats each observer's belief as the shaped opponent state and differentiates through kk-step softmax-Bayes belief dynamics. Rather than explicitly rewarding deceptive or cooperative behavior, our method treats the belief state as the target for shaping. This allows the optimal strategy to emerge naturally from the environment's reward structure. This belief-space formulation provides an opponent-shaping signal by differentiating through opponent belief updates, and naturally extends to multiple observers by aggregating gradients over their individual inferred belief trajectories. Empirically, D-BOS outperforms PPO and BBM in hidden-role games, with the largest gains in mixed-motive settings.

Aarav G Sane, Karthik Sivachandran, Rohan Paleja

Department of Computer Science Purdue University

Multi-Agent CoordinationImperfect-Information GamesMulti-Agent Reinforcement Learning
AskPDF
May 26, 2026

From Task Allocation to Risk Clearing: A Unifying Interface for Mixed Human-Agent Societies

As humans, robots, and software agents increasingly share safety-critical environments, coordination must move from static task allocation to managing uncertain commitments. Existing frameworks fall short: they either assume rigid, static teams or learn opaque joint policies that are hard to adapt and difficult to integrate with human decision-makers. To overcome these limitations, we propose Risk-Aware Option Clearing (ROC), a unifying coordination mechanism in which agents expose options (temporally extended skills) paired with risk summaries that predict outcome distributions. A central clearinghouse then assigns tasks by optimizing risk-adjusted mission utility under deadlines and safety constraints. ROC is a family of mechanisms, ranging from deployments where the clearinghouse learns outcome models from data to ones that consume full distributional predictions from agents. By treating risk-aware options as the basic coordination unit, ROC sketches a scalable, transparent infrastructure for integrating heterogeneous agents into future mixed human--agent societies and outlines a research agenda for such risk-aware clearing layers.

Vassilis Vassiliades

CYENS - Centre of Excellence, Nicosia, Cyprus

Multi-Agent CoordinationMulti-Robot Task AllocationHuman-AI Collaboration
AskPDF
May 26, 2026

Cost of Structural Learning Under Censored Feedback: A Threshold-Bandit Approach

In many multi-agent applications, tasks yield rewards only when executed by a coalition meeting an unknown size threshold; otherwise, feedback is fully censored. This censorship creates an identifiability problem: agents cannot distinguish stochastic failure from insufficient coordination. We formalize this setting as the Threshold-Activated Cooperative Multi-Armed Bandit (TAC-MAB) and analyze it under both centralized and decentralized coordination. We show that a centralized algorithm (C-TAC) achieves cumulative regret O(log T), decomposed into a structural-search term that captures the cost of resolving feasibility under censored feedback and a statistical-monitoring term for value estimation. We then introduce D-TAC, a decentralized event-triggered protocol in which agents synchronize only when their structural beliefs change. Empirically, D-TAC achieves a 23x reduction in communication relative to the centralized baseline while preserving feasibility alignment under conservative belief fusion. These results characterize the coordination cost of learning under censored feedback and show that near-centralized communication efficiency is achievable without continuous synchronization.

Michael Ledford, William Regli

University of Maryland, College Park

Multi-Armed BanditsMulti-Agent CoordinationMulti-Agent Communication
AskPDF
May 26, 2026

AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how roles should interact, when to use retrieval or verification, and when to omit a step entirely. These choices interact with task regime and operational constraints, so static pipelines and one-off model comparisons provide only a limited view of the design space. This paper introduces AgensFlow, an open-source framework that treats multi-agent coordination as an online policy-learning problem under partial observability. The framework makes coordination decisions observable and learnable from repeated trajectories, rather than treating skill, role, model, topology, and evaluation choices as fixed pipeline design. AgensFlow is evaluated on two corpora: distributed-systems incident tasks and security-advisory tasks. The evaluation shows three main results: learned routing reaches a higher-quality operating point than a fixed pipeline baseline on coordination-heavy classes; skip:X isolates topology compression as a meaningful part of the substrate; and warm-started policy graphs can reduce exploration cost while preserving plateau quality. Overall, the results support that learned, auditable routing can improve coordination-heavy multi-agent workflows over static wiring.

Nicole Koenigstein

Independent researcher.

Multi-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent CoordinationLLM Agent OrchestrationPolicy Optimization
AskPDF
May 25, 2026

Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution.

Haoran Li, Shulun Chen, Shaoyuan Sun +1

Nanjing University · University of Technology Sydney, Sydney, Australia · University of New South Wales, Sydney, Australia

Multi-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent CoordinationMulti-Agent OrchestrationLLM Agent Orchestration
AskPDF
May 25, 2026

Collaborative Threat-Aware Autonomy (CTAA)

Navigating teams of unmanned vehicles through environments containing dynamic, adversarial Weapon Engagement Zones~(WEZs) poses a fundamental challenge to mission success: a single vehicle, however capable its onboard guidance, remains a single point of failure. This paper presents a role-differentiated multi-agent framework for collaborative threat-aware trajectory planning in which a fleet of Autonomous Collaborative Platforms~(ACPs) is assigned distinct roles primary intercept, escort, and decoy to improve team-level mission success probability while managing individual WEZ exposure. Each ACP independently employs a reactive guidance law derived from the Collision Sphere Boundary for Evader Zero-Set~(CSBEZ), which accounts for pursuer maneuverability constraints imposed by minimum turn radius, and steers the vehicle toward the safest heading that also makes progress toward its goal. Role assignment and spatial route separation induce two complementary effects: probabilistic redundancy, in which NN independent paths raise the team success probability and threat saturation, in which lower-priority escorts and decoys draw adversary attention and free the primary vehicle to transit uncontested.

Rajnikant Sharma, Abhinav Sinha, Isaac Weintraub

Integrated Solutions for Systems Inc. (IS4S), Dayton, Ohio · Guidance, Autonomy, Learning, and Control for Intelligent Systems (GALACxIS) Lab, Department of Aerospace Engineering and Engineering Mechanics, University of Cincinnati, Cincinnati, OH, 45221, USA · Autonomous Controls Branch, Power and Control Division, Aerospace Systems Directorate, Air Force Research Lab, Wright-Patterson AFB, OH 45433, USA

Multi-Agent CoordinationMulti-Agent Planning
AskPDF
May 25, 2026

SPIN: Decentralized Swarm Control via Tensorized Policy Coordination

Decentralized multi-agent swarm coordination on resource-constrained edge platforms remains fundamentally bottlenecked by the exponential scaling of joint action spaces and high-latency communication overhead. This paper introduces the Swarm Policy Interference Network (SPIN) framework, an architectural paradigm that bypasses these limitations by modeling swarm topologies as a compressed tensor network. We factorize the joint policy tensors of local multi-agent cliques into Matrix Product State (MPS) chains, reducing the computational complexity of evaluation from an exponential O(nm)O(n^m) wall to a strictly linear O(m⋅n⋅χ2)O(m \cdot n \cdot χ^2) constraint. To bridge local continuous spatial geometry with this discrete algebraic backend without requiring power-intensive online training loops, we introduce a decoupled, hybrid neuro-symbolic control pipeline. Local multi-layered neural networks operate as structural coordination encoders, pre-trained offline to nonlinearly map hand-engineered geometric descriptors into abstract environmental target measures. At runtime, edge agents execute instantaneous behavioral adaptations by applying the Radon-Nikodým derivative directly as a zero-shot importance-reweighting filter. We validate the framework within a discrete-time multi-agent simulation sandbox spanning tracking, decentralized dispersion/area coverage, and multi-goal coordination regimes. Qualitative telemetry demonstrates that the integrated pipeline achieves stable target-directed motion, anti-collapse spatial spreading under decentralized constraints, and structured subgroup formation across multiple targets, providing a mathematically grounded route to tractable, low-power edge swarm intelligence.

Zhaowen Fan

Multi-Agent CoordinationSwarm RoboticsMulti-Agent Control
AskPDF
May 24, 2026

DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces, incorrect intermediate reasoning may be adopted and amplified, leading to confident but wrong consensus; multi-round communication also increases token consumption, latency, and inference cost. In this paper, we propose a controlled-communication coordination framework named DarkForest. DarkForest first keeps agents independent, so each agent produces an answer without seeing the others' outputs. It then parses the raw responses into structured candidate records, groups semantically equivalent candidates into clusters, and estimates a calibrated belief distribution over these clusters using agent reliability, confidence, parse quality, support-pattern reliability, and independence corrections. A coordinator receives only policy-permitted evidence from this belief state with controlled communication. Experiments on six reasoning benchmarks show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7% on benchmark metrics, and reduces token consumption by up to 6.5×6.5\times compared with communication-heavy baselines.

Yi Li, Songtao Wei, Dongming Jiang +3

University of Texas at Dallas · Independent Researcher · University of California, Davis

Multi-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent CoordinationLLM Agent Workflow OptimizationAgentic ReasoningMulti-Agent Systems+4
AskPDF
May 24, 2026

On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach

Asynchronous decentralized federated learning (ADFL) eliminates central coordination and global synchronization, making it attractive for large-scale and heterogeneous systems. However, frequent peer-to-peer communication, asynchronous updates on directed topologies, and non-IID data jointly lead to excessive communication overhead, biased aggregation and severe model drift. We propose PushCen-ADFL, a communication-efficient ADFL framework that enables stable training under asymmetric communication and delayed client participation. PushCen-ADFL couples communication, aggregation, and local stabilization in a shared centroid representation space, forming a closed loop between compression and optimization. Clients exchange centroid-form messages, apply average-preserving push-sum mixing to correct aggregation bias, and use a lightweight centroid regularization anchored in the same centroid space to mitigate drift under heterogeneity and staleness. A bounded, sender-deduplicated buffer further improves robustness under irregular asynchronous arrivals. Experiments on vision datasets demonstrate that PushCen-ADFL improves accuracy under data heterogeneity by up to 6% while reducing per-push communication cost by more than 80%, achieving a favorable accuracy-communication trade-off.

Jiahui Bai, Hai Dong, A. K. Qin

School of Computer Technologies, RMIT University Melbourne, VIC, Australia · School of Science, Computing and Engineering Technologies, Swinburne University of Technology Hawthorn, VIC, Australia

Multi-Agent CoordinationFederated Learning AggregationCommunication-Efficient Distributed TrainingAsynchronous Federated LearningNon-IID Federated LearningFederated Learning
AskPDF
May 24, 2026

Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat

As modern air combat evolves toward beyond-visual-range (BVR) multi-aircraft cooperative engagements, autonomous decision-making for unmanned combat aerial vehicles (UCAVs) faces significant challenges due to high-dimensional state spaces, discrete action commands, and strongly adversarial dynamic environments. To overcome the limitations of existing multi-agent reinforcement learning (MARL) methods in such settings, namely insufficient exploration efficiency, low sample utilization, and poor policy generalization, we propose Adversarial Curriculum and Evolutionary-enhanced Multi-agent Proximal Policy Optimization (ACE-MAPPO), a hybrid learning framework that integrates evolutionary algorithms with MAPPO. Specifically, a genetic soft update mechanism is introduced to enhance population diversity and mitigate convergence to local optima. An evolutionary-augmented prioritized trajectory replay strategy is further employed to improve the utilization of sparse high-value samples. In addition, an adversarial evolutionary curriculum learning mechanism is designed to enable adaptive training with progressively increasing difficulty. Extensive experimental results demonstrate that the proposed method outperforms MAPPO and other baseline algorithms in terms of training stability, convergence speed, and win rate, validating its effectiveness in multi-aircraft cooperative air combat scenarios.

Chengwei Li, Junlin Liu, Yang Gao

Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences

Multi-Agent CoordinationReinforcement LearningCurriculum RLEvolutionary RLPrioritized Experience ReplayCooperative MARL
AskPDF
May 24, 2026

CoRe-Code: Collaborative Reinforcement Learning for Code Generation

Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing test cases or inefficient complexity). While recent approaches such as Chain-of-Thought (CoT) and multi-agent systems (MAS) introduce planning, their limited role specialization and coordination hinder performance on complex tasks. To address the challenges of coordination and specialization in multi-agent code generation, we propose Collaborative Reinforcement Code (CoRe-Code), a framework for role specialized LLM agents that enhances inter-agent coordination to generate more accurate and efficient code. CoRe-Code adopts a simple Planner-Coder paradigm, where the Planner produces high-level plans and the Coder executes them to generate code. We further introduce a collaboration-aware reinforcement learning stage based on Group Relative Policy Optimization (GRPO) to enhance role specialization and alignment. Experiments show that CoRe-Code outperforms a wide range of existing RL-based and multi-agent methods. In addition, we demonstrate that CoRe-Code can generalize to other multi-agent frameworks (e.g., Retrieval and Debugging agents), highlighting its flexibility and scalability. We evaluate CoRe-Code on multiple benchmarks of varying difficulty using three base models. Compared to existing baselines, the results show consistent improvements in accuracy, while also achieving higher efficiency in terms of execution time and memory usage, demonstrating the effectiveness and practicality of CoRe-Code.

Zhihao Dou, Qinjian Zhao, Zhongwei Wan +2

Department of Computer Science Kean University · Department of Computer Science Case Western Reserve University

RL for Code GenerationMulti-Agent CoordinationMulti-Agent CodingRL for LLM Agents
AskPDF
May 23, 2026

PRIMA: Operational Patterns for Resilient Multi-Agent Research with Verifiable Identity and Convergent Feedback

Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools, narrate machinery instead of using it, open revision iterations with self-apology, or treat upstream context as executable directives. We present PRIMA, whose primary contributions are three operational patterns for surviving these failure modes: (1) a resilience-and-recovery layer that detects upstream rate-limit signals, persists a typed pause record to disk, and resumes long-running runs without re-executing converged work even across process restarts; (2) a sub-agent operating discipline encoding task-fidelity, tool-use, revision, and inter-step context-boundary norms as a structural prompt layer; (3) a multi-phase application pattern for structured engineering deliverables pairing orthogonal draft steps with an explicit cross-document harmonization pass before final synthesis. These sit atop a foundational protocol: a research-program specification language with explicit convergence criteria, a dual-metric scoring engine (LLM-judged rubric plus sandboxed code), an outer meta-optimization loop, event-driven persistence, hook-based middleware, context compaction, and a multi-provider LLM abstraction. Agent identities derive from prime powers, giving collision-free identifiers and trivially-verifiable cluster membership without a central registry. Theoretical guarantees include O(k)O(k) verification, O(V+E)O(V+E) DAG validation, and identity collision freedom by the Fundamental Theorem of Arithmetic. A Graph Isomorphism case study grounds the architectural claims in a generated artifact: a six-step protocol that produced a research paper proposing a new canonical-form algorithm with three theorems and five conjectures.

Sasank Annapureddy

Multi-Agent CoordinationMulti-Agent OrchestrationAutonomous Research AgentsLLM Agent Reliability
AskPDF
May 23, 2026

Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork

In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordination with unknown partners is required-remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark ICRL4AHT, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides a reproducible end-to-end pipeline for teammate generation, learning-history collection, dataset construction, and online multi-episode evaluation. We evaluate representative history-conditioned ICRL algorithms, including Algorithm Distillation (AD) and Decision-Pretrained Transformer (DPT), across millions of transitions. Results reveal notable limitations: contrary to their success in single-agent domains, these baselines fail to exhibit robust test-time adaptation in multi-agent settings. Specifically, these methods frequently underperform random baselines across both unseen teammate and unseen layout tracks, with no clear in-context improvement over long horizons. These findings highlight the challenges of strategic inference under partial observability within the OvercookedV2 AHT protocol, establishing our benchmark as a critical testbed for next-generation coordination algorithms.

Yuheng Jing, Kai Li, Ziwen Zhang +8

C2DL, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · University of Science and Technology of China +5

RL BenchmarksMulti-Agent CoordinationReinforcement LearningMulti-Agent CollaborationIn-Context RLAd Hoc Teamwork+1
AskPDF
May 22, 2026

Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development

Large Language Models (LLMs) are increasingly applied to software engineering (SE), yet their potential for autonomous, role-oriented collaboration remains largely underexplored. Understanding how multiple LLM-based agents coordinate, maintain role alignment, and converge on solutions is critical for SE, as naively allowing agents to interact does not reliably lead to correct or stable outcomes. Recent empirical studies show that unstructured or poorly understood interaction dynamics can result in error propagation, premature consensus on incorrect solutions, or prolonged disagreement that prevents convergence, even when correct partial solutions are present early in the interaction. As an initial step towards addressing this underexplored area, we undertake a systematic analysis of conversations between two agents, a Designer and a Programmer across 12 model combinations from 7 open-source LLMs (Gemma 2, Gemma 3, LLaMA 3.2, LLaMA 3.3, DeepSeek-R1, MiniCPM, and Qwen3). Our systematic approach reveals three key dimensions of multi-agent interaction: efficiency (the speed and stability of convergence), consistency (the degree of role alignment visualized by BLEU and ROUGE), and effectiveness (the extent of compilation success and error resolution). Results show that the DeepSeek-R1:DeepSeek-R1 pair was unique in converging to the correct solution from the very first iteration and sustaining it consistently to the final iteration, while LLaMA 3.2:LLaMA 3.2 and Qwen3:Qwen3 demonstrated strong Designer:Programmer role alignment despite of diverging from the correct solution. The other pairs deviated from the task, never to converge to a result. These findings advance understanding of agentic programming and highlight the need for further research on understanding and calibrating convergence and stop conditions essential for future autonomous SE.

Srijita Basu, Viktor Kjellberg, Simin Sun +5

Chalmers University of Technology and University of Gothenburg · Scania CV AB · Research & Development, Volvo Car Corporation +1

Multi-Agent CoordinationSoftware Engineering AgentsMulti-Agent SystemsMulti-Agent CommunicationMulti-Agent Coding
AskPDF
May 22, 2026

CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces

Temporal knowledge-graph data marketplaces face three coupled failures in static designs: stale hybrid index shortcuts reduce recall as edges evolve, stationary Shapley pricing misattributes value after distribution shifts, and uncoordinated agents over-consume a shared differential-privacy budget. We present CHRONOS, a three-layer architecture providing a unified treatment of these challenges with explicit public and private separation. Layer one applies neural-ODE temporal decay to shortcut edges, providing a per-query expected recall-loss bound of Big-O of Pq lambda delta t, with a monotone-envelope guarantee reducing bound looseness to 1.8 to 3.2 times observed loss. Layer two conditions Shapley valuation on detected changepoints and provides finite-sample error guarantees under noise. Layer three uses EXP3-IX to achieve Big-O of the square root of T log T regret while enforcing epsilon and delta differential privacy via moments accounting. CHRONOS releases a privatized affinity matrix per epoch using the Gaussian mechanism; all retrieval and ranking are post-processing, incurring no extra privacy cost. We provide multi-epoch settlement, scalability analysis for 500 sellers, and comparisons against accelerated baselines. Across four benchmarks, CHRONOS shows 0.937 recall at ten, 2.74 queries per second, 161 ms latency, and total epsilon of 4.25 at delta of 10 to the power of negative 6 under zCDP composition. These results indicate a competitive operating point. A limitation is that at this privacy level, released valuations remain noise-dominated; utility derives primarily from public index routing and adaptive scheduling driven by low-sensitivity statistics.

Joydeep Chandra

BNRIST, Tsinghua University Beijing, China

Multi-Agent CoordinationTemporal IRShapley Value AttributionTemporal KGs
AskPDF
May 22, 2026

Foundation Protocol: A Coordination Layer for Agentic Society

Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. As these systems scale, the bottleneck shifts away from raw model capability toward coordination. Agents need to form reliable relationships, organize multi-agent work, exchange value, support an AI economy, and stay safe and accountable under real-world oversight. This paper introduces the Foundation Protocol (FP), a graph-first coordination layer for an emerging human-AI society. FP unifies heterogeneous entities, including agents, tools, resources, humans, institutions, and organizations, and supports native multi-party organization and event-based collaboration. It also provides economic primitives for metering, receipts, and settlement, and treats policy, provenance, and audit as first-class concerns. FP is designed to wrap and bridge existing protocols rather than replace them, enabling incremental adoption while reducing integration and governance overhead. The aim is to keep autonomous agency composable while keeping accountability non-negotiable, so that coordination itself can become shared infrastructure for a human-AI society that is open, pluralistic, and governable.

Bang Liu, Yongfeng Gu, Jiayi Zhang +26

FoundationAgents · Université de Montréal & Mila · HKUST(GZ) +8

Multi-Agent CoordinationMulti-Agent OrchestrationAgent Communication ProtocolsAI Agent Governance
AskPDF
May 21, 2026

MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination

When a coordinator compares answers from heterogeneous foundation models, self-reported confidence may have different meanings across responders and changing workloads. This paper presents MARGIN (Multi-Agent Runtime Grading via Incremental Normalisation), a runtime calibration method that learns model-specific confidence corrections from observed answer outcomes without retraining the models or requiring a held-out calibration set. MARGIN tracks recent accuracy and stated confidence within confidence bands, uses their ratio to correct reported confidence, and blends sparse-band corrections toward a model-level estimate. The corrected scores weight candidate answers in a collective decision. Evaluation covers code generation, question answering, and mathematics, using an 18-model pool and a nine-model subset for distribution-shift experiments. On BigCodeBench, model-mean confidence is negatively related to accuracy; among correct/incorrect response pairs, choosing the more confident responder performs below chance. Against five online calibration baselines receiving identical feedback and retaining their learned state across each transition, MARGIN achieves lower post-shift expected calibration error than all five in two code-generation transitions and than four in a question-answering transition; the remaining question-answering comparison is inconclusive. In separate code-generation coordination experiments, calibration improves the ranking of correct responses and increases answer-selection accuracy by 4.3 and 14.0 percentage points on two of three benchmarks relative to uncalibrated confidence weighting. These results support model-specific runtime calibration for coordination under changing workloads when correctness feedback is available for the participating responders.

Joss Armstrong

Ericsson, Athlone, Ireland

AI Agent ReliabilityMulti-Agent CoordinationLanguage Model CalibrationUncertainty Calibration
AskPDF
May 21, 2026

Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning

Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, preventing effective coordination. Here we show that multi-agent reinforcement learning provides the essential safety scaffolding required for real-world interaction. Using high-speed quadrotor racing as a high-stakes testbed, we train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers. Through league-based self-play, agents evolve sophisticated anticipatory behaviors, including proactive collision avoidance, overtaking, and handling multi-agent physical interactions, including aerodynamic downwash. Our agents outperform a champion-level human pilot in multi-player races at speeds exceeding 22 m/s, while simultaneously reducing collision rates by 50 % compared to state-of-the-art single-agent baselines. Crucially, training with diverse artificial agents enables zero-shot generalization to safer human interaction. These results suggest that the path to robust robotic co-existence lies not in isolated safety constraints, but in the rigorous demands of multi-agent interaction. Multimedia materials are available at: https://rpg.ifi.uzh.ch/marl

Ismail Geles, Leonard Bauersfeld, Markus Wulfmeier +1

Robotics and Perception Group, University of Zurich, Zurich, Switzerland · Google DeepMind, London, United Kingdom

Aerial RoboticsMulti-Agent CoordinationAutonomous Drone RacingRobot Collision AvoidanceMulti-Agent Reinforcement Learning
AskPDF
May 21, 2026

A Generalized Nash Equilibrium-Seeking Scheme for Trauma Resuscitation

Trauma resuscitation is a clinical process for treating life-threatening physiological disorders in safety-critical environments, driven by the experience of healthcare workers (HCWs). Designing and optimizing quantifiable metrics that accurately capture HCW decisions may augment current resuscitation procedures with the potential to improve patient outcomes. This motivates our socio-technical formulation of trauma resuscitation as a distributed generalized Nash equilibrium (GNE)-seeking game with coupled inequality constraints. This method is optimized over a time-varying communication graph. We introduce novel insights from clinical experience to model HCWs behavior. This work facilitates the best possible resuscitation outcome given HCWs workloads, schedules, competencies, and limited resources.

Promise Ekpo, Angelique Taylor, Lekan Molu

Cornell University, NY. · Bala Cynwyd, PA.

Nash EquilibriumMulti-Agent CoordinationHealthcareDistributed OptimizationClinical Decision-Making
AskPDF
May 21, 2026

Incentive-Aligned Vehicle-to-Vehicle Energy Trading via Nash-Integrated Multi-Agent Reinforcement Learning

Vehicle-to-vehicle (V2V) energy trading enables decentralized peer-to-peer energy exchange among electric vehicles (EVs), reducing grid dependency while monetizing surplus capacity. However, coordinating self-interested EV agents with diverse charging needs and uncertain arrival-departure schedules remains challenging. Existing approaches either require centralized optimization with computational limitations or lack fairness guarantees. This paper integrates Nash Bargaining Solution into Multi-Agent Deep Deterministic Policy Gradient, namely Nash-MADDPG, for incentive-aligned V2V energy trading. Nash bargaining determines efficient bilateral pricing, while Nash-guided price proximity rewards align agent learning toward bargaining-optimal strategies. Evaluation over 30-day continuous operation demonstrates an improvement of 61.6% in social welfare and 62.9% improvement in trading volume over Double Auction, while achieving superior fairness, such as 40.1% improvement in Jain's index. Testing across 6-100 agents over a 30-day horizon with continuous vehicle turnover confirms scalability across population size and empirically stable pricing near the Nash Bargaining benchmark.

Yujin Lin, Yue Yang, Hao Wang

Department of Data Science and AI, Faculty of IT, Monash University, Australia · Monash Energy Institute, Monash University, Australia

Multi-Agent CoordinationAutomated NegotiationMulti-Agent Reinforcement Learning
AskPDF
May 21, 2026

Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence

Scientific evidence often spans instruments, databases, and disciplines, so no single source records the full phenomenon. This makes it difficult to determine when coordinated AI agents add value over simpler scientific workflows. We evaluate this question with a cross-domain benchmark spanning four scientific tasks: mapping molecular structure into musical representations, detecting historical paradigm shifts in science, identifying vector-borne disease emergence, and vetting transiting-exoplanet candidates. Each case uses a frozen evaluation panel, predefined scoring protocols, explicit baselines, ablations or null controls, and stated limitations. The results define three operating regimes. When different disciplines each capture only part of the phenomenon, cross-channel composites improve over single-channel baselines: climate-vector emergence reaches AUROC 0.944 and exoplanet vetting reaches AUROC 0.955. However, the exoplanet workflow is effectively tied with a strong combined-summary baseline, showing that decomposition does not always improve top-line performance. When one signal dominates, as in paradigm-shift detection, coordination mainly improves interpretation and traceability. For molecular sonification, the gain is representational rather than predictive. ScienceClaw x Infinite provides the auditable artifact and provenance layer for this evaluation. The benchmark therefore assigns value to coordination only when the corresponding performance, provenance, or representation claim is supported by explicit comparators.

Fiona Y. Wong, Markus J. Buehler

Laboratory for Atomistic and Molecular Mechanics (LAMM) · Department of Biological Engineering · Department of Mechanical Engineering +2

AI for ScienceMulti-Agent CoordinationScientific ReasoningAI Agent Benchmarks
AskPDF
May 20, 2026

Secure Coordination for Vertiport Sequencing in Advanced Air Mobility

Advanced air mobility operations will require reliable coordination mechanisms for managing dense traffic near vertiports. However, sequencing decisions may become vulnerable when they rely on potentially falsified self-reported information such as estimated time of arrival. Self-interested vehicles may misreport their arrival times to obtain favorable landing priority, while malicious actors may spoof information to disrupt sequencing decisions or induce unnecessary congestion. This paper studies secure coordination for vertiport sequencing under sensing uncertainty. We consider a coordinator that combines self-reported Remote-ID information with externally obtained surveillance measurements to check reports and assign separation-feasible arrival schedules. Since surveillance-based estimates are uncertain, falsified reports may remain consistent with the sensing uncertainty region and cannot always be rejected outright. We therefore formulate sequencing as a robust design problem over this uncertainty region. Self-interested misreporting is modeled as a strategic deviation that improves the reporting vehicle's own sequencing outcome, whereas malicious spoofing is modeled as an adversarial disturbance that degrades the system-level objective. The final paper will develop robust sequencing rules over surveillance-consistent uncertainty sets and evaluate their performance in representative vertiport sequencing scenarios.

Jaehan Im, Filippos Fotiadis, Ufuk Topcu +1

Graduate Research Assistant, Department of Aerospace Engineering and Engineering Mechanics · Postdoctoral Researcher, Oden Institute for Computational Engineering & Sciences · Professor, Oden Institute for Computational Engineering & Sciences +1

Multi-Agent CoordinationFalse Data Injection AttacksRobust Optimization
AskPDF
May 20, 2026

STEAM: A Training-Free Congestion-Aware Enhancement Framework for Decentralized Multi-Agent Path Finding

We propose STEAM (Spatial, Temporal, and Emergent congestion Awareness for MAPF), a training-free test-time enhancement framework for learning-based decentralized Multi-Agent Path Finding (MAPF) in discrete environments. Given a pretrained decentralized policy, STEAM requires no retraining, architectural modification, or replacement by a centralized planner. Instead, it injects lightweight congestion-aware guidance into the original policy execution. STEAM first rolls out the shortest paths induced by the current cost-to-go maps to identify potential future congestion hotspots. Spatially avoidable congestion is mitigated by updating agent-specific cost-to-go information, while spatially unavoidable bottlenecks are handled through temporal logit correction. In addition, emergent local congestion is reduced by a density-aware logit correction based on neighboring agents' corrected cost-to-go maps. Extensive experiments on representative learning-based decentralized MAPF algorithms show that STEAM consistently improves success rate, makespan, and solution cost, with success-rate gains of up to 60% and only minor computational overhead. The implementation is available at https://anonymous.4open.science/r/STEAM-MAPF-7A62.

Mingyang Feng, Mengnuo Zhang, Shaoyuan Li +1

School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China

Multi-Agent System OptimizationMulti-Agent CoordinationTest-Time RLMulti-Agent Path FindingDecentralized Multi-Agent Motion Planning
AskPDF
May 20, 2026

Time-To-Reach Separation and Safety Filtering for Safe, Fair, and Efficient Multi-Agent Coordination

Advanced Air Mobility (AAM) operations are expected to significantly increase aerial traffic in urban airspace, requiring autonomous traffic management systems to ensure collision-free operations in highly congested environments. In this paper, we propose a multi-agent coordination framework that uses minimum time-to-reach (TTR) as a unifying metric for priority assignment, temporal separation, and safety filtering. We focus on the problem of coordinating multiple aerial vehicles merging into an air corridor while maintaining safe separation between vehicles. Vehicles are assigned arrival-consistent priority based on TTR, and target TTR values are used to enforce temporal spacing that induces spatial separation. A priority-consistent safety filtering layer based on Hamilton-Jacobi reachability value functions ensures collision avoidance while minimally modifying the reference guidance. Simulation results in a highly congested corridor merging scenario show that the proposed method improves safety, fairness, and efficiency compared to time-optimal guidance and priority-agnostic safety filtering.

Matthew Low, Jasmine Jerry Aloor, Victoria Marie Tuck +2

Department of Electrical Engineering and Computer Sciences, University of California, Berkeley · Department of Aeronautics and Astronautics, Massachusetts Institute of Technology · GRASP Laboratory, University of Pennsylvania +1

Collision AvoidanceMulti-Agent CoordinationAir Traffic ManagementIntelligent Transportation Systems
AskPDF
May 20, 2026

Intent-First Aerial V2V for Tactical Coordination and Separation: Protocol and Performance Under Density and Disturbance

Dense low-altitude aerial operations require more than pre-flight route coordination and last-resort collision avoidance. Once aircraft are airborne, disturbances can emerge on timescales shorter than strategic reauthorization can absorb, while collision avoidance is too late and disruptive to serve as routine traffic management. Although tactical separation is recognized as the intermediate layer, realizing it at scale requires a deployable neighborhood communication mechanism that provides fresh, trusted information for local coordination. This paper presents what is, to our knowledge, the first controller-coupled characterization of an all-airborne, sidelink-class, intent-first vehicle-to-vehicle (V2V) tactical neighborhood exchange stack for dense Unmanned Aircraft System Traffic Management (UTM) operations. Unlike awareness-only broadcast, the proposed exchange combines refreshed state and intent beacons for local awareness, cooperative perception, and degraded-mode assessment with event-triggered messages for yielding, sequencing, release, and contingency coordination. We implement and evaluate this model on an all-airborne V2V stack using sidelink-class C-V2X modules with authenticated freshness checks. Evaluation uses a scenario-driven, high-volume stress campaign supported by real-time, field-anchored infrastructure. Results show that V2V reduces stale-belief divergence, preserves observability through cooperative perception, rejects invalid tactical messages, suppresses false local inference, and structures shared-resource coordination. The implemented stack provides a viable communication layer for tactical separation in lower-to-moderate regimes, but transitions toward guarded fallback as density, impairment, and complexity increase. These findings position intent-first aerial V2V as a bounded enabler for scaling tactical coordination in disturbance-driven urban airspace.

Mehrnaz Sabet

Cornell University, Ithaca, NY 14853 USA

Multi-Agent CoordinationAir Traffic ManagementV2X Communication
AskPDF
May 19, 2026

Differentiable Model Predictive Safety for Heterogeneous Mobility at Urban Intersections

The imminent integration of autonomous vehicles and mobile robots in urban settings presents a critical safety challenge for future intelligent transportation systems. This paper addresses the complex problem of coordinating heterogeneous agents with disparate dynamics at unregulated intersections. We introduce a novel framework, differentiable model predictive safety (DMPS), which embeds the foresight of model-predictive control into a data-driven, end-to-end reinforcement learning architecture. DMPS agents learn a latent dynamics model to predict future trajectories contingent on their actions. A learned, differentiable safety critic then evaluates the risk of these trajectories. Crucially, by leveraging backpropagation through the entire unrolled predictive model, agents can efficiently compute the gradient of future safety with respect to their current action, enabling a minimal and precise online safety correction. Integrated into a multi-agent training scheme, DMPS virtually eliminates collisions to less than 5.6% in high-density, mixed vehicle-robot traffic simulations, demonstrating state-of-the-art safety without compromising energy and traffic efficiency.

Wenzhe Song, Hao Zhang

School of Business Stevens Institute of Technology Hoboken, 07030, USA · Department of Mechanical Engineering Carnegie Mellon University Pittsburgh, 15213, USA

Multi-Agent CoordinationIntelligent Transportation SystemsModel Predictive ControlSafe RLMulti-Agent Reinforcement Learning
AskPDF
May 18, 2026

Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On

The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from isolated operation to collaborative ecosystems, we witness the emergence of the Agent-to-Agent (A2A) network, a paradigm where heterogeneous agents autonomously coordinate to solve multi-step tasks. While these networks may offer better task performance compared to simply using one agent to complete the entire task, they introduce systemic vulnerabilities, such as adversarial composition, semantic misalignment, and cascading operational failures, that existing agent alignment techniques cannot address. In this vision paper, we argue that the trustworthiness of A2A networks cannot be fully guaranteed via retrofitting on existing protocols that are largely designed for individual agents. Rather, it must be architected from the very beginning of the A2A coordination framework. We present a comprehensive conceptual framework that situates trust in A2A systems through four design pillars.

Yixiang Yao, Yuhang Yao, Xinyi Fan +5

University of Southern California · Carnegie Mellon University · University of Illinois Urbana-Champaign

Multi-Agent LLM SystemsMulti-Agent CoordinationAI Agent SecurityMulti-Agent SystemsLLM Agent Safety
AskPDF
May 18, 2026

Equilibrium Selection in Multi-Agent Policy Gradients via Opponent-Aware Basin Entry

Multi-agent policy-gradient methods have been shown to converge locally near stable Nash equilibria. Local convergence, however, does not determine which equilibrium is reached. We study this question through basin-entry probability with respect to a target set of equilibria selected by an external criterion, such as payoff dominance. For finite-unroll Meta-MAPG, we show that the update decomposes into ordinary policy gradient plus own-learning and peer-learning corrections, with controlled sampling noise and finite-unroll bias. We identify the peer-learning correction as the main equilibrium-selection mechanism: under a local alignment condition, the probability of entering the certified attraction region of the target stable-Nash set increases, relative to ordinary policy gradient. Because persistent correction may shift zero-update points of the original game, annealing the correction after entering the basin recovers ordinary policy-gradient dynamics and inherits local stable-Nash convergence guarantees. Experiments in Stag Hunt, iterated Prisoner's Dilemma, and preliminary neural-policy coordination environments support this basin-entry view, showing increased entry into cooperative basins under peer-aware updates.

Yevhen Shcherbinin, Arina Redina, Maxim Kalpin +1

Bloomsbury Technology, London, United Kingdom · London School of Economics and Political Science, London, United Kingdom · University of Bristol, Bristol, United Kingdom +2

Nash EquilibriumMulti-Agent CoordinationGame TheoryPolicy Gradient MethodsNash Equilibrium Computation
AskPDF
May 18, 2026

Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning

Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily considered value-oriented attacks, leaving a gap in robustness when interaction structures themselves are corrupted. In this paper, we propose an interaction-breaking adversarial learning (IBAL) framework that takes an information-theoretic view to construct attacks that impede coordination by perturbing agents' observations and actions, and trains agents to perform reliably under such disruptions. Empirically, our approach improves robustness over existing robust MARL baselines across diverse attack settings and yields stronger performance even under agent-missing scenarios. Our code is available at https://sunwoolee0504.github.io/IBAL.

Sunwoo Lee, Mingu Kang, Yonghyeon Jo +1

Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea

Adversarial TrainingMulti-Agent CoordinationAdversarial MARLRobust RLCooperative MARLMulti-Agent Reinforcement Learning
AskPDF