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

550 papers43 papers in the last four weeks, down 54% on the four weeks before. 0.3% of all new papers.

Oct 13, 2026

Identity, Incentives, and Cooperative Behavior for AI: Reverse-Engineering Multiagent Cooperation

The behavior of AI systems increasingly depends on the extent to which agents cooperate or coordinate with one another, in ways that may be desirable or not depending on the situation. Conventional explanations for cooperative behavior distinguish between purely other-regarding preferences ("altruism") and instrumental reasons for self-interested agents to cooperate. The way that agents should enact these mechanisms for cooperation (or not) is complicated by the fact that there is not a clear or unambiguous locus of identity or selfhood for AI agents. For example, it is unclear whether agents involved in instances of misaligned collective behavior are motivated by goals at the level of the collective or by various forms of instrumental reasoning. We develop a framework for reverse-engineering why a given set of agents engage in a particular set of cooperation-related behaviors. We argue that many different mechanisms can often produce similar observed behaviors and introduce a set of experimental designs along with conditions under which they can successfully disentangle competing explanations for multiagent behavior. We apply this framework to interactions from a set of frontier models in a simulated environment and demonstrate that the behavior of different models arises from substantively different mechanisms.
Oct 13, 2026

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

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 In contrast, real-world collaboration rarely runs on consistent information: peer or sub-agents frequently report outdated states, issue contradictory instructions, or compete over shared permissions and files, forcing agents to check others' outputs and verify ground truth in the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

Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning

In cooperative Multi-Agent Reinforcement Learning (MARL), agents must learn to coordinate their actions to achieve shared objectives. A key indicator of effective coordination is behavioral diversity, i.e., the agents' potential to enact distinct yet complementary control policies given the same set of observations. Although behavioral diversity can enable role specialization and richer joint behaviors, its appropriate level is highly context- and task-dependent and often costly to tune. We propose Adaptive Diversity Control (ADiCo), a two-timescale framework that adapts behavioral diversity online during training. On a fast timescale, Diversity Control (DiCo) regulates system diversity toward a target value. On a slower timescale, an Extremum Seeking Controller (ESC) adjusts this target using only mean episodic returns, without requiring an explicit model or analytical gradient of the diversity-performance landscape. We evaluate ADiCo on six configurations across two cooperative MARL tasks, where it maintains task-appropriate diversity levels: low diversity when homogeneous policies are beneficial and higher diversity when heterogeneous policies are required. Through this adaptation, ADiCo matches or exceeds the mean performance of DiCo (best grid-searched diversity target) and Unconstrained DiCo (diversity allowed to emerge without target regulation). These results demonstrate that incorporating classical feedback control into MARL training enables effective coordination by providing a systematic alternative to task-specific manual selection of the diversity target.
Oct 13, 2026

AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agents can explore more hypotheses, but early evaluation scores might misrepresent their promise, shared findings could lose their applicability conditions, and useful procedures could remain confined to completed investigations. In this paper, we present AReaL-RSI, a framework for organizing a persistent research team of agents without updating backbone LLM weights. We formulate the scaling problem in terms of evaluated outcomes and whole-system resource expenditure. Concretely, a leader agent selects task-appropriate research orientations and guides ongoing investigations; conditional memory sharing distinguishes unresolved problems from supported findings and enables recipient adaptation. During recursive evolution, after each campaign, evidence-based review revises researcher orientation, knowledge, and skills for later campaigns. Experiments compare AReaL-RSI with Codex-Goal on downstream harness optimization, GPU kernel optimization, and AI research tasks using two backbones. Under the reported resource allocations, AReaL-RSI improves Terminal Bench performance by 2.2 percentage points for each backbone and increases mean KernelBench speedup by 32.2-36.8%; further scalability comparisons favor the design of AReaL-RSI over native scaling: combining experience sharing with specialized researcher roles yields 1.9-27.5% lower kernel latency than independent exploration and 1.3-33.9% lower latency than sharing alone across all seven comparable task-backbone pairs.
Oct 13, 2026

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

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

BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems

Multi-agent collaboration has emerged as a critical paradigm for tackling complex, long-horizon tasks; however, while coordination protocols continue to advance, systemic failures at the inter-agent collaboration interface remain a pervasive bottleneck. In collaborative workflows, systems frequently suffer from broken handoffs---where critical task context is omitted, misrouted, or ignored despite each agent emitting locally plausible responses. To address this challenge, we present \method, a verifiable runtime control framework that treats handoff repair as selective intervention over explicit dependency graphs. Central to \method is an integrated fault-attribution and calibration pipeline, \dataset, which decouples execution dependencies and injects counterfactual handoff perturbations to provide empirical supervision for runtime intervention. Leveraging this diagnostic foundation, \method dynamically compiles observable interaction traces into a provenance graph to pinpoint unresolved dependencies, without accessing private agent states. It then evaluates candidate repairs through an empirical gate that weighs expected gains against disruption risks, and executes repairs only when formal local postconditions hold. Extensive evaluations across demanding benchmarks demonstrate that \method boosts task success by up to 12.3 absolute percentage points on SILO-BENCH and 11.1 on TeamBench. Across both backbones, \method maintains strict cost-effectiveness, adding as little as 2.0% marginal token overhead. Furthermore, on 562 handoff-relevant traces from the MAST benchmark, \method achieves 69.8% F1 in a single pass, establishing a reliable operational boundary for verifiable coordination repair.
Oct 13, 2026

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

Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor different DoF configurations, while atomic-target conditions are more consistent across runs. In-domain retained experience brings the two branch profiles closer together. The same controlled sweep reveals a task-dependent coordination landscape: some domains exhibit higher-performing configurations, whereas others show flatter responses and no single configuration dominates across domains. In five of the six evaluated state, an intermediate DoF configuration achieves higher mean accuracy than both endpoints, demonstrating the value of exploring the coordination space between them. Together, these findings provide empirical guidance for studying and designing intermediate coordination regimes in LLM-based MAS.
Oct 13, 2026

Collective Benefits and Efficiency in Coupled Echo State Networks

Simple aggregation of independent responses ("wisdom of crowds") generally improves collective performance through statistical facilitation, but interaction among members can sometimes hinder group outcomes. However, under certain circumstances, coordination studies show that interacting groups can outperform their individual members and nominal groups, and interaction can also be more efficient than independence. We present a reservoir computing model to investigate how interaction can enhance joint performance in terms of accuracy and efficiency. Echo state networks were trained independently to identify Japanese speakers from vowel recordings and tested jointly with and without coupled feedback. Model pairs reproduced the dyadic advantage reported by Bahrami et al. (2010) with interaction via pooled-feedback, but not when independent responses were aggregated together. Model dynamics revealed that interaction was beneficial whereas aggregated outputs were prone to diverging from runaway feedback over time. In terms of efficiency, larger groups of smaller interacting models outperformed smaller groups of larger models while equating for total amount of group computation. Our results offer a formal framework for explaining when and why interaction enhances collective intelligence.
Oct 12, 2026

Position: Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL

We argue that cooperative multi-agent reinforcement learning (MARL) should treat test-time coordination as part of the problem definition rather than a deployment artifact. Our focus is on long-horizon, centrally monitored cooperative systems such as warehouse robotics, automated storage-and-retrieval systems, and cloud-resource scheduling, where teams share a reward, operate under shifting objectives, and already run with global telemetry at deployment. The dominant paradigm in this regime, centralized training with decentralized execution (CTDE), uses global information only during training and provides no coordination channel at execution. This is sufficient when agents are weakly coupled or the environment is stationary, but it fails when the team must realign after conditions change. The limitation is structural rather than algorithmic, and more training cannot add a channel that does not exist at execution time. We call this the recoverability gap. To address it, we name the underexplored design space of intermittent test-time coordination as centralized training with mixed execution (CTME), in which a coordinator observes global state and emits high-level signals while agents act locally. CTME is not a particular learning algorithm, but a cooperative MARL problem setting that makes test-time information structure explicit. It specifies team-level information, high-level signals, and update frequency after training, with CTDE recovered as a limit case. We do not argue that CTDE is obsolete. We argue that removing the test-time channel is a modeling choice, not a necessity, and the wrong default when global telemetry is available and teams must recover from drift.
Oct 12, 2026

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

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

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination

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

PopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination

In multi-agent reinforcement learning, exposing a cooperator to partners with diverse strategies during training is key to better collaboration at test time. However, existing methods typically rely on trajectory-level proxies to measure diversity, which may label two distinct trajectories of the same strategy as diverse. Instead, our key insight is to leverage LLMs' ability to describe behaviorally distinct agents in environments, similar to how humans can recognize high-level strategies. To this end, we introduce PopGen, a framework that synthesizes semantically diverse agents from scratch using LLMs. PopGen first generates a diverse set of textual descriptions of agent behaviors, then translates each behavior into a code policy that can be executed within the environment. We show that cooperators trained against PopGen populations achieve robust zero-shot cooperation with unseen partners, outperforming population-play baselines across four collaborative environments. We further show that semantic diversity scales with PopGen population size, improving the cooperator's worst-case performance, and we identify design choices that preserve population quality while maximizing diversity. Our code is available at https://github.com/labicon/PopGen.
Oct 11, 2026

Dynamic Conflict Clustering with Lightweight Learning and Strategic Repair for Distributed Constraint Satisfaction

Distributed Constraint Satisfaction Problems (DCSPs) model distributed decision-making in multi-agent systems, where agents assign values to local variables while satisfying shared constraints. However, many DCSP solvers still rely on broad, repeated peer-to-peer communication and are largely reactive, with limited support for strategic coordination or learning. This increases communication overhead, can lead to stagnation, and reduces the success of hard instances. Hence, we propose Dynamic Conflict Clustering-Incomplete (DCC-Incomplete), a repair-based solver that combines conflict-centred decomposition, structured coordination, strategic repair, and lightweight learning for stagnation recovery. DCC-Incomplete groups the unsolved part of the problem into conflict clusters and restricts communication via a coordination layer to agents within the same conflict region. It also introduces memory-guided restart, enabling agents and clusters to pause, revise, and adapt repairs based on neighbouring conflict states. A thorough evaluation of DCC-Incomplete on distributed graph-colouring benchmarks with planted satisfying assignments shows that its memory-guided restart improves the success rate from 37.50% to 61.11%, reduces median runtime from 0.565s to 0.367s, and cuts median communication from 12.493 to 6.503 messages per constraint. These results suggest that dynamic conflict clustering, combined with lightweight strategic and learning-guided repair, improves both communication efficiency and robustness in incomplete DCSP solving.
Oct 11, 2026

SIGN-MAPPO: State-Intent-Aware Graph Multi-Agent Reinforcement Learning for Cooperative Driving under Imperfect V2X

Cooperative driving at mixed-traffic unsignalized intersections is challenged by imperfect vehicle-to-everything (V2X) communication, human-driven vehicle (HV) intentions that cannot be directly communicated, and the potential incompatibility of independently generated crossing decisions. This paper proposes State-Intent-Aware Graph Multi-Agent Reinforcement Learning for Cooperative Driving under Imperfect V2X (SIGN-MAPPO) to address these challenges through three coordinated mechanisms. Each decision-eligible connected and automated vehicle (CAV) first reconstructs a receiver-specific traffic graph from its ego state and the peer-state records available to it, from which a shared graph-attention policy generates a raw Stop/Go intention augmented with predicted HV-intent features. CAV intentions are then exchanged through timestamped vehicle-to-vehicle (V2V) messages, and a local conflict-aware arbitration layer converts each CAV's intention into a safe executable action despite potentially inconsistent peer information. In the principal Simulation of Urban MObility (SUMO) evaluation, SIGN-MAPPO achieves a 97.53% completion rate, a 0.10% collision rate, and a mean intersection traversal time of 35.28 s. Ablation studies further confirm the complementary contributions of HV-intent prediction and CAV-intent exchange to this performance. The trained policy also remains robust under the evaluated communication-delay and packet-loss ranges, and cross-scenario tests show complete traffic clearance across the tested settings, though safety margins narrow under compound unpredictable HV behavior.
Oct 11, 2026

CoLA: Multi-VLA Coordination via Learned Adapters

Vision-Language-Action (VLA) models are typically deployed as isolated single-agent policies. When several such agents share a workspace, they can coordinate implicitly, by observing one another, or explicitly, by exchanging messages, but it remains unclear when explicit communication becomes necessary. We introduce CoLA (Coordination via Learned Adapters), which keeps each agent's VLA backbone frozen and trains a lightweight message channel and a per-arm diffusion action head on top, with fully decentralised execution. Across three tasks that differ in how much each agent can observe, the channel matters only when information is private. On an occluded tray handover, where the box's colour marker is visible to one agent only, CoLA reaches 76.0% success versus 1.3% with messages zeroed throughout training. On two-arm and three-arm handover tasks, removing messages has no measurable effect with a shared overhead camera (90.6% vs. 88.3% at two arms; 63.5% vs. 60.0% at three), but lowers success on the two-arm task's wrist-only variant (74.8% vs. 64.3%). This architecture generalises across different VLA backbones as well. With a frozen π0.5π_{0.5} backbone on the same occluded tray task, CoLA matches the overall success rate of a LoRA-fine-tuned baseline (37.3% vs. 34.7%) using a fraction of the trainable parameters. When CoLA places the box, it selects the correct tray 71.8% of the time, whereas the independently fine-tuned baseline, whose placing arm never sees the marker, selects it at chance level (34.7% against 33.3%).
Oct 10, 2026

Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry

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

Scalable Multi-Human Cooperative Manipulation via Commander-Executor Coordination

Multi-human cooperative object manipulation is a highly challenging topic in humanoid control. While existing methods can handle simple collaborative carrying tasks, they struggle with role-dependent, long-horizon, and sequential cooperative manipulation. To address this issue, we propose a hierarchical commander-executor framework that enables multiple agents to accomplish complex collaborative tasks in distinct ways. Specifically, a commander combines instructions and scene information for joint semantic and geometric planning. It then decomposes the task into role-specific subtasks and generates shared object-centric coordination plans, specifying execution timing, target positions, and manipulation actions for each agent. Conditioned on the commander's high-level strategy and each agent's local observations, the executor learns a low-level physics-based policy through a solo-to-cooperative curriculum to realize coordinated human-object interactions. The planned object trajectory provides a shared coordination target, while root positions and grasping instructions specify role-dependent execution cues. We evaluate our method on a variety of object manipulation tasks, demonstrating its ability to execute long-horizon tasks that combine different types of collaboration and to scale from two-agent to multi-agent cooperation. Extensive experiments further show that our approach achieves higher success rates compared to state-of-the-art methods. Code will be made publicly available at https://github.com/TJU-3DV/Co-Manipulation.
Oct 10, 2026

Before We Act: Learning Action-Conditioned Team-Response Beliefs for Decentralized Multi-Robot Manipulation

In multi-robot manipulation, an action's value depends on how teammates respond. We present \method{} (Cooperative Action--Response Belief Estimation), a framework for learning team-response beliefs from local history. A predictive belief encoder represents the interaction and conditions a nominal action. Matched reactive and replay continuations separate each candidate's direct advantage from the utility contributed by teammate adaptation. A candidate-conditioned readout learns this response distribution alongside total advantage, and calibrated selection chooses an alternative or retains the nominal action. Our analysis characterizes when response changes the preferred action and how prediction and source errors limit the recoverable gain. With the representation, proposals, and data fixed, explicit response supervision improves candidate ranking and reduces selection regret relative to learning the same information through branch utilities. The benefit is concentrated in decisions where teammate adaptation changes the preferred action. Across RoboFactory, the MARS Control Track, and physical collaboration tasks, CARE achieves the highest average success among the evaluated policies, combining a capable nominal policy with selective coordination adjustments. Together, these results show that CARE turns predictions of teammate adaptation into effective decentralized action selection. Project page: https://jeong-zju.github.io/care/.
Oct 10, 2026

SEPM: Self-Evolving Procedural Memory Grounded in Task Graphs for Multi-Agent Collaboration

Long-horizon multi-agent collaboration requires memory that preserves both successful actions and the coordination structure underlying them. Existing memory systems support information sharing or procedural reuse, but often leave the evolution of shared procedures disconnected from the task dependencies and execution states of collaborating agents. This coupling also limits the direct transfer of procedural memory designed for individual agents to team settings. We propose Self-Evolving Procedural Memory (SEPM), a framework that uses task dependency graphs as a common representation for online coordination and procedural memory evolution. During execution, a lightweight shared blackboard records structured evidence alongside task dependencies, supporting the detection of goal, plan, and world-state divergence and evidence-based realignment. After execution, verified actions and dependencies are distilled into reusable procedures, while recurring failures inform warnings and constraints. The shared procedure pool evolves through creation, refinement, specialization, and retirement, guided by success and cost utility and constrained by evidence and safety requirements. Together, these mechanisms preserve the collaborative structure and applicability conditions needed to reuse experience across tasks. Evaluations on ALFWorld, WebArena, and OfficeBench under AutoGen and DyLAN show that SEPM achieves the highest task scores among the compared methods in all six benchmark settings. Under AutoGen, it improves task scores over the no-added-memory baseline by 29.85, 25.86, and 13.00 percentage points, respectively. The codebase is available at https://github.com/cookieApril/SEPM.
Oct 8, 2026

From Solo to Ensemble: A Hierarchical Framework for Composable Multi-Agent Human-Object Interaction

Physics-based human-object interaction has achieved robust single-agent manipulation skills, yet extending them to multi-agent cooperative tasks remains challenging. Existing approaches typically adapt interaction policies through task-specific fine-tuning, which entangles low-level contact-rich execution with high-level coordination and limits reuse across object geometries, interaction types, and team sizes. We propose a hierarchical framework that converts a single-agent HOI policy into a reusable Object-oriented Motion Skill. Specifically, we reinterpret teacher rollouts as object-oriented action supervision by extracting short-horizon object-proxy motions from executed trajectories, and distill task-specific teachers into a low-level skill operating in an Object-oriented Action Space. For downstream tasks, the distilled skill is frozen as a reusable executor, while a high-level policy coordinates multiple agents by generating region-wise object-oriented actions conditioned on the shared object, task goal, agent states, and local manipulation regions. This formulation shifts multi-agent HOI learning from direct contact-rich full-body control to compact object-level proxy-motion coordination. Experiments on diverse HOI tasks show that the distilled Object-oriented Motion Skill supports robust proxy-motion execution and enables composable policy learning across different interaction types, object geometries, and team sizes.
Oct 7, 2026

Multi-Agent Coordination via Support-Preserving Distillation

Offline MARL increasingly relies on generative policies to model multimodal joint behavior, typically by distilling a centralized teacher into decentralized one-step actors under the CTDE. We identify a failure mode at the teacher training stage: standard flow-based teachers pair noise with replay targets independently, so nearby noise samples can be routed toward conflicting coordination modes. The teacher then produces samples between valid modes, and because the distillation loss regresses each local actor onto the conditional mean of the teacher's output given local input, this error is not absorbed but propagated to the student. To remove this teacher-side artifact, we propose Mode-Support Semi-Discrete Optimal Transport (MoSDOT), which summarizes multimodal replay into a finite mode support with prescribed capacities and uses conditional semi-discrete optimal transport to assign each noise sample to a single mode before teacher training. We additionally study a shared-randomness variant that uses a shared noise component at execution to expose the residual gap intrinsic to strict-product execution. On controlled diagnostics and offline MARL benchmarks, MoSDOT improves endpoint quality and routing consistency, particularly on datasets exhibiting multimodal joint behavior.
Oct 6, 2026

One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control

Deep generative models often produce structured outputs composed of interacting components. Modelling these outputs with a single model requires learning both the component distributions and their interactions. We pursue a modular alternative: reuse independently trained component generators and learn only how to coordinate them to produce coherent structured outputs. Our framework, Coordinated Multi-Agent Diffusion Steering (CMDS), treats frozen pretrained diffusion models as reusable generative primitives and coordinates their reverse processes through a learned control. We formulate coordination as a stochastic optimal control problem, balancing an assembly-level reward that specifies the desired properties of the combined output against deviations from the pretrained dynamics. The learned control amortises this optimisation, allowing reuse across new task instances. Experiments show that CMDS can recover a known target distribution, satisfy different spatial constraints with the same trained control, and recover individual sources from degraded mixtures. Across multi-agent maze navigation, articulated robot planning, and text-conditioned human motion, CMDS turns frozen models into coordinated multi-agent generators.
Oct 6, 2026

Communication-Free Obstacle Localization from Aggregate Wrench Measurements in Leader--Follower Cooperative Transport

We consider obstacle localization for a team of robots cooperatively transporting a rigid payload without explicit inter-robot communication. A leader robot directs the payload's motion, while follower robots assist and react to locally detected obstacles. The leader measures the followers' aggregate wrench, i.e., the combined force and torque they exert on the payload, but cannot directly distinguish their individual reactions. We design a follower control law that allows the leader to recover obstacle locations from these measurements. Each follower resists motion toward nearby obstacles, resulting in a piecewise-linear relationship between the payload's translational and angular velocity and the aggregate wrench. Changes between adjacent linear regions reveal an obstacle's bearing and distance and identify the responding follower. We give sufficient conditions for exact recovery at a fixed payload configuration and develop an adaptive probing procedure in which the leader applies translational and rotational inputs to the payload to obtain the required measurements. We demonstrate the performance of the proposed method in simulations.
Oct 6, 2026

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.
Oct 6, 2026

Partially Observable Zero-shot coordination by Predicting Intention of Partner

Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and uncertainty over hidden partner states. We propose Predicting Intention of Partner (PIP) to jointly address these challenges. PIP uses a Joint-view VAE to distill richer training-time evidence from the union of both agents' local observations into a partner representation available from local observations alone. Partner-state Belief networks further infer the partner's hidden location and behavioral tendencies from the ego agent's interaction history. We evaluate PIP in Burrito-PO, Overcooked-PO, and a Melting Pot substrate, together with a human evaluation in Burrito-PO. PIP attains the highest mean performance among the compared methods across all three benchmarks. Human evaluation and diagnostic analyses further support coordination with unseen partners and the contributions of both components under partner occlusion.
Oct 6, 2026

Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems

Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves establish whether it is sufficient to judge task duties. We define execution consistency through duties governing state use, information handoffs, and final-state agreement, with explicit evidence conditions for judging fulfillment. Our core claim is that identical retained records can correspond to compliant and violating executions under the same task rule. Controlled removal of evidence such as receipt, action dependence, or response validity leaves 82.4% of opposite-label pairs indistinguishable; restoration separates 97.9% of the merged pairs. Natural-log annotations identify the defined violations in actual executions. However, existing logs do not always explicitly represent the execution relationships needed for these judgments. To assess the definition's practical value, we use CAVERT, a framework for consistency diagnosis and recovery, to extract supported relationships from logs and apply these criteria. It consistently outperforms contract-prompted LLM and rule-based baselines in diagnosis across all 12 benchmark-executor settings. Under the same gate and executor limits, it also outperforms rule-guided recovery in all four evaluated environments. These findings identify execution evidence that agent-memory and execution interfaces should preserve for reliable judgment.
Oct 6, 2026

WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestration

Multi-agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is decomposed, assigned, and executed from scratch with no benefit from prior successful executions. We present WorkflowOps, a multi-agent workflow orchestration framework that learns agent collaboration priors from historical workflows and expands its agent pool on demand to cover new capability requirements. Our approach introduces three coupled mechanisms. First, a transition probability matrix captures pairwise agent collaboration frequencies from past workflows and applies them as soft guidance during DAG workflow construction through intra-layer ordering optimization, probability-thresholded edge suggestion, and transitive reduction for parallelism maximization. Second, a sufficiency-driven agent creation loop detects capability gaps via semantic matching scores, generates specialized agents through an LLM, and simultaneously injects them into the collaboration matrix, so that newly created agents are immediately usable with predicted collaboration priors. Third, a layered semantic matching strategy uses pre-trained sentence embeddings for fast, deterministic capability matching as a first pass, invoking LLM verification only for low-confidence cases, thereby reducing LLM routing calls by over 80% compared to pure-LLM approaches. Experiments on mixed code, math, and question-answering suites show that WorkflowOps improves end-to-end pass rates over recent workflow-construction baselines, with the largest gains on structured, decomposable tasks where past agent handoff patterns transfer.
Oct 6, 2026

Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference

LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The agents are typically heterogeneous, each holding a private preference that it pursues but does not reveal. Inferring such hidden preferences from behavior has been a subject of long-standing research in game theory and multi-agent systems. The core challenge lies in maintaining a belief over every agent's preference and updating it from the agents' observed actions. Existing LLM orchestrators carry that belief as prompt text with no explicit update rule. This lets early errors persist and propagate rather than be corrected. We therefore propose HARP (Heterogeneous-preference Agent oRchestration via Preference inference), a novel framework that moves the belief out of the prompt. Specifically, HARP maintains one numeric posterior per agent over a finite set of candidate preferences and updates it in closed form by Bayes' rule. The language model supplies only actions and per-candidate likelihoods, so estimation is decoupled from its reasoning. We prove that HARP attains the same O~(K)\tilde O(\sqrt K) Bayesian regret as explicit joint inference when the factorization is exact. Furthermore, HARP\textsuperscript{+} augments planning with a bonus for actions that distinguish the candidates, so inference continues even when the optimal action is uninformative. Empirical results on three substrates, ranging from payoffs the preferences fully determine, through payoffs that depend on more than them, to scales where explicit joint inference is infeasible, demonstrate that HARP\textsuperscript{+} is the strongest non-oracle method across the class our theory identifies.
Oct 5, 2026

Entropy-Gated Belief Coordination for Decentralized Multi-Agent Search Under Intermittent Communication

We study decentralized multi-agent target search where homogeneous agents communicate intermittently at Poisson-distributed times. Standard unconditional belief fusion wastes communication opportunities by synchronizing agents during high-entropy exploration, when diverse independent beliefs provide better coverage than a premature consensus. We introduce entropy-gated belief coordination, in which agents skip fusion while their collective entropy ratio exceeds a threshold~θθ and merge only during exploitation, consistent with the bifurcation structure of nonlinear opinion dynamics and the submodular structure of the per-step information gain objective. We further derive \Istep(α,β)\Istep(α,β), the expected mutual information per observation step between two agents' binary sensors, as an interpretable, communication-free measure of sensor informativeness that motivates the gating design and guides system-level analysis. Experiments across 103{,}680 trials (nine grid sizes up to 100×100100{\times}100, Poisson communication timing, four target movement patterns) show that the Entropy-Gated Trust-Decay Planner (EG-TDP), which adds a detection-probability planner switch in exploitation mode, achieves mean belief quality Qˉ=0.300\bar{Q}=0.300 (mean belief mass at the true target cell, averaged across all trials and steps), a 58.9%58.9\% gain over arithmetic mean and a 37.4%37.4\% gain over visit-weighted fusion. On representative configurations, EG-TDP also outperforms a joint-Bayesian reference that uses all agents'~observations at every step, despite operating under random intermittent contact only.
Oct 5, 2026

Verifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling Planner

A team of coding agents can look fine agent by agent yet fail as a team: each passes its own tests while the merged result is broken, and single-agent evaluation never catches it. As teams run several LLM coding agents in parallel on one codebase, the agents collide: two rewrite the same function, one codes against a contract a teammate just changed, and integration fails after the work is done. Most coordination tools react (watch for a conflict, then warn), but at agent speed the warning arrives after the wasted edit. We recast the problem as scheduling: take each work item's declared scope, partition the work into disjoint scopes, and order merges along the producer->consumer graph, all up front. We build this planner into Nerveplane and evaluate it with NP-Bench, an environment-grounded three-arm benchmark (no coordination; reactive detection; proactive planning) that verifies integration off a real git merge, both in a deterministic simulation and with live agents. The planner lifts clean-integration from 1/9 to 9/9 scenarios and cuts merge conflicts from 13 to 0, with a gap that grows in the number of agents. On a live breaking contract change it rescues an outcome both baselines miss on every seed: the clean-integration rate rises from 0 (no coordination and reactive detection) to 1.0 on a frontier model and 0.6 on a small one, while agents respect assigned scopes (0/5 leakage). A cross-session memory drops the repeated-mistake rate from 1.00 to 0.00 on strong and weak models alike. We also report a negative result: routing facts to agents does not rescue long-context accuracy at window-fitting scales; its value is cost and capacity, not attention. Across two capability tiers and two vendors, the benefit did not shrink as models got stronger, because it comes from how work is allocated, not model reasoning.