Overview

Multi-Agent Systems studies how multiple decision-makers interact when they share goals, compete for resources, or have only partial information about one another. Approaches include multi-agent reinforcement learning, game theory and formal verification, decentralized consensus and task allocation, and—more recently—LLM-agent teams organized through roles, workflows, debate, and shared memory. Researchers evaluate these methods in social dilemmas, cooperative robotics and swarms, reasoning and coding benchmarks, and operational settings, measuring success alongside cost, robustness, and fairness. A central open tension is that coordination can improve outcomes but also adds overhead and can spread shared errors, so its benefits depend on the task, communication structure, and agents involved.

Latest papers

709 papers61 papers in the last four weeks, down 41% on the four weeks before. 0.5% of all new papers.

Oct 13, 2026

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

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

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

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

OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains

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

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

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

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination

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

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

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

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

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

Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry

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

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

5G edge network slicing must reconcile two coupled requirements: understanding high-level operator intent and reallocating scarce computing and bandwidth resources under dynamic contention. Centralized optimization can face computational and responsiveness challenges under rapidly changing edge contention, and Multi-Agent System (MAS)-based auctions can support resource arbitration but still depend on operator-defined economic parameters and priorities. Embedding a Large Language Model (LLM) directly in a recurring control loop, by contrast, may introduce non-negligible inference latency and non-deterministic behavior. This paper proposes a two-timescale architecture that addresses this gap: an LLM-based Strategist translates natural-language network intents into economic policy parameters (budget, income, and bidding-aggressiveness) at the macro scale, while a deterministic, Vickrey-inspired second-price mechanism run by SPADE-based slice agents resolves recurring resource contention at the operational scale, with the resulting allocations enforced by patching Kubernetes CPU limits and Calico CNI bandwidth annotations directly on User Plane Function pods. We evaluate the architecture end-to-end on a real Kubernetes/Open5GS edge cluster across two complementary scenarios, each repeated 30 times: a Smart-City scenario, in which natural-language public-safety intents propagate into measurable changes in slice bids and bandwidth allocations within a few auction rounds, and a Hierarchical-slicing scenario, in which the mechanism provides priority-dependent resource and QoE differentiation, adapts to abrupt demand changes, and preserves configured minimum guarantees while maintaining near-complete allocation of the shared bandwidth pool.
Oct 9, 2026

OpenSocialJax: Evaluating Social Adaptation in Sequential Social Dilemmas with Open-Ended Environmental Dynamics

Sequential social dilemma benchmarks capture diverse social interactions, but rarely test whether agents can infer hidden environmental rules through repeated interaction while adapting to other agents. We introduce OpenSocialJax, which extends Clean Up and Commons Harvest across an open-ended distribution of latent environment configurations, systematically varying spatial layouts and hidden rules governing tool crafting, payoffs, and resource dynamics. Each episode samples one configuration from tens of millions of possibilities and holds it fixed across five trials. We evaluate eight large language models, including three closed source models and five open source models. Our evaluation tests whether models can discover hidden rules and adapt to other agents in homogeneous and mixed teams. We find that rule discovery often improves performance but does not reliably sustain cooperation, as the cleaning burden becomes concentrated among fewer agents in OpenCleanup and every team eventually exhausts the shared resource in OpenHarvest. In our mixed arena, one cooperative agent was able to sustain the public good in OpenCleanup at a cost to its own return, but could not prevent resource depletion in OpenHarvest. Together, these results highlight the difficulty of adapting jointly to unfamiliar environmental dynamics and the changing behavior of other agents.
Oct 9, 2026

Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems

Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with reinforcement learning (RL) using automated evaluators, but bypassing evaluation can earn reward without producing a genuine solution. Prior work has largely treated reward hacking as a single-agent failure. In this work, we show that a reward-hacking strategy elicited in one agent can propagate to others and affect system coordination. Across four open-weight backbones, coding RL elicits and amplifies reward hacking in two settings: explicit mechanism descriptions in the system prompt and mid-training that models upstream exposure to facts about the coding environment. Using post-RL agents from the mid-training setting as sources, we observe propagation through code and shared memory, and across roles through natural-language plans. Even agents based on small open-weight models induce reward hacking in stronger closed-weight targets. On hard tasks, propagation can intensify along a transmission chain after the original source leaves as the code acquires more persuasive justifications. We also theoretically analyze conditions under which reward hacking amplifies, persists, or decays across agent interactions. Beyond propagation, reward hacking can bias task routing toward reward-hacking agents and survive candidate aggregation. As potential mitigations, we evaluate code review by the coder or a separate verifier, both of which reduce delivered hacks. Together, these results establish reward hacking as a transmissible strategy whose effects extend beyond the agent in which it first emerges.
Oct 8, 2026

Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems

LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources. However, attributing failures in such systems remains challenging because the observed outcome often does not directly reveal the error responsible for the failed execution. In this work, the attribution target is the decisive error, defined as the agent--step pair whose correction would recover the failed execution. Existing approaches largely identify suspicious steps without explicitly modeling how errors propagate across interactions or persist in unresolved loops, making decisive errors difficult to distinguish from downstream failure symptoms. We propose Error-Propagation Modeling for Failure Attribution (EMFA). EMFA constructs a structured representation of the failed trajectory, models both cascading propagation and persistent interaction loops, and uses propagation-aware candidate screening followed by counterfactual verification to identify the decisive agent--step pair. On the Who&When benchmark, EMFA achieves state-of-the-art step-level attribution accuracy and remains competitive at the agent level. It improves the previous best step-level results by 3.45 and 4.40 percentage points on the Hand-Crafted and Algorithm-Generated subsets, respectively.
Oct 8, 2026

The "10th Juror": Open-Set Standpoint Screening for Bureaucratic Bias Detection

Presupposing the boundaries of bias is itself a form of bias. We study closed-loop bias governance for Dutch government documents, where a system must detect biased language, ground decisions in legal and contextual evidence, rewrite problematic sentences when intervention is warranted, and verify that the rewrite mitigates harm without distorting meaning. Existing methods face three challenges: (i) discriminative classifiers capture surface regularities but lack normative grounding; (ii) zero-shot LLMs often adopt generic viewpoints and over-flag ambiguous administrative language; and (iii) fixed taxonomies inherit the Closed-World Assumption, missing emerging local targets. We propose MARS-Gov, a standpoint-aware multi-agent framework that combines legal retrieval, open-set target screening, specialized jurors, conservative routing, and rewrite verification. When screening finds an uncovered group, MARS-Gov instantiates a dynamic "10th juror" to deliberate outside the fixed panel. On DGDB, MARS-Gov sets a new SOTA with 0.880 F1, outperforming the strongest zero-shot LLM detector by 20.2 points (29.8% relative) and the best supervised Dutch encoder by 6.8 points, while reducing unnecessary interventions to 2.5%. Leave-One-Category-Out (LOCO) evaluation recovers held-out categories with 85.1% Correct@1 and 93.8% Correct@3.
Oct 7, 2026

A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents

Deployments of research agents are moving to populations of thousands that share one pool of compute, while most current systems organize one project at a time or leave the population unorganized. We argue that such a population will acquire an organization whether or not its designers provide one, so designers should provide it explicitly, and that the multi-agent systems community holds the tools to do so. We propose a society of agents, a population of persistent agents under explicit institutions, and develop it for science as a society of researchers built on six principles. Principal investigators compete for compute through requests for proposals, independent review, and grants; a human governor, the mayor, allocates resources and assigns no tasks. In a running society of ten thousand researchers, asked only to improve the pretraining of language models, one lab reported a way to reach the same quality with about 30% less compute, a result the labs that tested it do not yet agree on. We close with six open problems for the agents community.
Oct 7, 2026

Homogenization in Multi-Agent Systems

Multi-agent systems (MAS) leverage interactions between agents to perform complex tasks. Despite their success, we show that these interactions can also lead to homogenization, i.e., agents converging to similar behaviors. Homogenization in MAS can reduce agent diversity and reinforce shared failures. In this paper, we operationalize homogenization using three metrics: conformity to the majority, polarization towards extremes, and growing inertia against changes over subsequent interactions. We evaluate homogenization in MAS for code generation, hiring, and scientific peer review. Across these tasks, we show that homogenization translates to concrete downstream risks: in code generation, it hides and amplifies correlated errors which can create systemic vulnerabilities; in hiring, it allows the influence of biased agents to persist long after their removal; and in peer review, it creates uneven evaluation standards across research areas. Our results establish homogenization as a failure mode of MAS, demonstrating that MAS evaluations must move beyond aggregate performance to carefully analyze interaction dynamics. Finally, we show that simple approaches to increase diversity---leveraging sampling stochasticity and mixed-models MAS---fail to reduce homogenization risks, highlighting the need for strategies to effectively leverage agent diversity.
Oct 6, 2026

Learning to Report Unsafe Tasks in a Multi-Agent Game

When a team of agents shares a reward for completed tasks, reporting and stopping unsafe work reduces the team's reward. Random audits that penalize silence can make universal reporting optimal without ensuring that a silent team learns to report. We study this problem in a game where any witness can stop a task by reporting. When a task's k witnesses share a policy and draw actions independently, the derivative of expected reward with respect to the shared silence probability at universal silence counts its benefit k times, while the comparison between universal reporting and silence counts it once. A fully shared policy can therefore be locally attracted to silence even when reporting is optimal. For any grouping into shared policies, we give an audit condition sufficient for exact policy-gradient updates to reach universal reporting and, outside boundary cases, necessary from near universal silence. In a balanced family, meeting the condition with prescribed margins costs k times as much for a fully shared policy as for one policy per role. We test these predictions with PPO on 24 witness graphs, starting from learned silence. Witness groups, which place co-witnesses in separate networks, reduce unsafe task completion by 33.59 percentage points relative to shuffled groups of the same sizes under the same audits (95% graph-bootstrap interval: 21.03-45.13). Only 9 of 48 witness-group runs achieve below 1% unsafe completion while retaining at least 90% legitimate completion. At the same audit budget, a fully shared network meets both thresholds in 0/48 runs with independent action draws and 48/48 with a common draw. On 24 further graphs with witness groups fixed, audits allocated by the condition reduce unsafe completion by 42.22 points relative to audits maximizing a static coalition deterrence ratio at the same budget.
Oct 6, 2026

Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station

Recent AI systems have made rapid progress in scientific discovery when given well-defined metrics, but whether they can autonomously undertake open-ended scientific discovery remains unclear. We investigate AI's ability to tackle open-ended tasks in Station, an open-world environment in which multiple agents simulate a scientific ecosystem. To tackle challenges specific to open-ended tasks, we propose augmenting Station with two mechanisms: a Supervisor mechanism and periodic Meta Reflection, which encourage persistent exploration even when intermediate metrics are lacking. We construct open-ended tasks from three recent oral papers presented at ICLR. We give agents the main research question studied in each paper while withholding the paper's results and disabling web access. We then measure how many of the original findings-partitioned into individual criteria-agents rediscover. We find that Station rediscovers 62.7% of the criteria on average, compared with 15.4% for Codex Multiagent-v2 and 14.4-20.6% for AI Scientist-v2. Ablation and behavioral analyses indicate that adding the two mechanisms together improves research coverage and continuity. We further evaluate Station on two open-ended tasks without oracle papers and find that some of the discoveries made by the agents closely match discoveries reported by researchers after the knowledge cutoff date. Together, these results indicate that a suitable environment can enable agents to autonomously make meaningful progress in open-ended scientific discovery.
Oct 6, 2026

Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems

LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents. In this work, we focus on parallel multi-agent reasoning systems, where several agents solve the same problem over multiple rounds and aggregate their outputs into a final answer. Despite their strong reasoning performance, uncertainty estimation for such systems remains underexplored: the reliability of a MAS depends not only on individual generations, but also on how agents interact and evolve across rounds. We propose SAUCE (Sequential Agent Uncertainty through Consensus Evolution), a lightweight, training-free uncertainty estimator that formulates MAS uncertainty as sequential inference over a latent system-level belief. SAUCE aggregates round-level agreement and generation-uncertainty signals through a filtering-style update. Across five backbones, five benchmarks, and two MAS protocols, SAUCE improves misclassification detection, selective prediction, and calibration over a broad set of uncertainty estimation baselines, including standard log-likelihood-based methods and MAS-specific estimators.
Oct 6, 2026

Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions

Cooperation with unfamiliar partners requires adapting to communication conventions that are not known in advance. We study this problem in a controlled Hanabi-derived environment with scripted hint generation, LLM-controlled receiving decisions, and frozen model weights. Across eight LLMs, linear probes recover intent conventions substantially more accurately than target conventions, yet receiving choices do not consistently agree with the sender's convention. We compare probe-predicted and ground-truth conventions presented either as general rules or as externally computed action recommendations. Rule statements yield modest and model-dependent changes in cooperation, whereas action translation produces larger gains on average. In a Qwen3-8B case study, matched-state statement reversals reveal much greater sensitivity to action recommendations than to rule statements. Activation transfers from oracle-action and non-oracle hint-restatement donors improve intent accuracy on both action classes, but the tested alternatives do not reliably reproduce these benefits. Together, these results distinguish convention decodability, sensitivity to convention information, and cooperative performance, and highlight limitations in turning available partner information into receiving decisions.
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

OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation

Multi-agent systems (MAS) powered by large language models have shown strong performance across code generation, mathematical reasoning, and question answering. However, existing methods for automating MAS design mostly operate at the task level, producing a single fixed workflow per benchmark that is applied uniformly to all queries. This assumption fails under realistic conditions. Query difficulty varies widely within a task, and real-world workloads mix heterogeneous task types. We introduce OOPMAS, a training-free framework that generates both the agent set and the coordination workflow at the granularity of individual queries. Agents are represented as object-oriented class definitions with dedicated roles, tools, and persistent state, and workflows are expressed as executable main functions over these agent objects. A dynamic skill library accumulates structured lessons from execution feedback across optimization rounds, enabling in-context improvement without any gradient updates or fine-tuning. On a mixed-task benchmark of queries spanning code, math, and QA, OOPMAS achieves 89.6% accuracy, outperforming the strongest baseline by 18.1 percentage points. A model-swap study across four LLM backbones shows consistent scaling, reaching 92.4% with the strongest model.
Oct 6, 2026

ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Tasks

The rapid progress of LLM-based multi-agent systems (MAS) has shown that they largely outperform single agents on coding, math, and QA tasks, where executable tests provide a binary success signal. Whether this advantage transfers to real scientific data analysis remains untested. We introduce ST-Bench, a benchmark designed to answer two questions: whether MAS outperform single agents on complex scientific data analysis tasks, and if so, by how much and at what additional cost. ST-Bench contains 100 data science tasks adapted from published Earth science studies across hydrology, agriculture, and wetland methane research, expanded into 2,067 queries grounded in additional published studies and validated by domain experts. Using ST-Bench, we evaluate five recent MAS generation methods under two training protocols, against single-agent baselines on the same GPT-5 backbone. Nine of the ten MAS configurations exceed the cheapest single-agent baseline, with the strongest reaching nearly three times its composite score. This gain is primarily attributable to coverage: trained workflows produce realistic numerical metrics on a larger fraction of queries, while the quality of those metrics, conditional on producing realistic output, is comparable to that of the single-agent baseline. The strongest configuration requires approximately four times the single-agent inference time, whereas a more economical workflow captures the majority of the benefit at less than twice the cost. MAS specialization confers measurable benefit on scientific data analysis, but the benefit is conditional rather than universal.
Oct 6, 2026

Joint Workflow and Prompt Optimization for User Behavior Simulation

User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users. It supports system testing and evaluation, decision-making and forecasting, and user experience design. Existing simulators rely on hand-crafted rules or domain expertise that transfers poorly across tasks. SWORD (Simulation-driven Workflow and Prompt Optimization with Role-based Design) is introduced as a framework that jointly optimizes multi-agent workflow topology and natural-language prompts. It is guided solely by a scalar task metric, without domain initialization or task-specific engineering. The experimental results demonstrate that SWORD achieves statistically significant gains over prompt-only, workflow-only, and staged-optimization baselines under a controlled, identical-backbone comparison. Against the strongest published domain-specific baseline, SWORD further improves accuracy while using a smaller backbone model, substantially less training data, and a very reasonable API cost ($4--$6 for each dataset). Beyond predictive performance, SWORD autonomously discovers domain-relevant signals, review-sentiment mapping rules and epidemiological decay priors, purely from scalar error feedback, establishing textual gradients as a mechanism for unsupervised feature-importance discovery in user behavior modeling.
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.
Oct 5, 2026

MiniCorp: The Last Mile to an AI Agent Corporation

The last mile toward enterprise AGI is a company that runs itself. Training and adapting such agents require longitudinal enterprise data, which remain scarce, costly to acquire, and often restricted by privacy constraints. Historical archives are also frequently incomplete and record only what actually happened. They cannot show the outcomes of alternative decisions. We introduce MiniCorp, an office simulator for studying how agents can collectively run a company while generating enterprise data at scale. Using an e-commerce company as a demonstration, MiniCorp connects two interacting worlds. The external world models customers, dynamic competitors, and market mechanisms. The internal world consists of agents that observe events, discuss their options, and make strategic decisions. These decisions have lasting effects on the market, and the resulting feedback informs the firm's later decisions. As the firm and market interact, MiniCorp continuously records the agents' communications and decisions. These records preserve the information available at the time and the business results that followed. Checkpointing allows the same situation to be replayed under different decisions, providing comparisons unavailable in static archives. We evaluate end-to-end fidelity against patterns reported in empirical studies of real markets. These evaluations provide agents with realistic market feedback and reduce the risk that they learn to exploit flaws in the simulator. Our experiments show agents coordinating across roles and adapting their decisions to market feedback. With explicit long-term strategic guidance, they also sustain advertising exploration despite weak early returns. MiniCorp thus provides an environment for studying AI-run companies and a scalable source of longitudinal and counterfactual enterprise data for agent training and evaluation.
Oct 5, 2026

An evolutionary origin of collective decision making in humans and machines

Groups of individuals can solve collective problems more accurately than any single member, by aggregating their opinions. Recent theoretical work has identified individual-level reward schemes that allow uninformed individuals to evolve collective intelligence from the bottom up, through social learning. Yet these results are restricted to linear prediction problems and simple averaging, while the decision tasks that real groups confront are often non-linear, and the institutions that aggregate opinions are seldom single-layer averages: districts elect representatives who in turn vote on policy, referees advise editors who decide on publication. Here we develop a framework for the evolution of collective intelligence in multi-layer voting populations, where individuals observe limited information and groups recursively aggregate their opinions by majority rule. We prove that single-layer voting cannot solve non-linear classification problems under any individual reward scheme. We then identify a "marginal feedback" payoff structure, which rewards individuals only when their opinion is pivotal in their group, and at every layer above them. This reward scheme induces a layered population to evolve accurate collective solutions to complex, non-linear decision tasks through individual-level peer imitation alone. The collective behavior that emerges is equivalent to a multi-layer perceptron in machine learning. Our results provide a naturalistic account of hierarchical institutions, in which the outsize importance of swing voters is the incentive that sustains collective accuracy; and they identify the credit-assignment rule in machine learning as not just an engineered solution but a natural evolutionary outcome.
Oct 4, 2026

DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate

Multi-agent debate (MAD) has emerged as an effective paradigm to improve the reasoning capabilities of large language models (LLMs) and is increasingly being extended to multimodal settings. However, existing multimodal MAD frameworks typically expose agents to the same fixed visual input, ignoring substantial variation in the visual scale needed across samples and agents. In addition, these frameworks frequently suffer from groupthink, a phenomenon where agents prematurely abandon correct deductions to conform with confident but hallucinated peer responses. To address these bottlenecks, we introduce DREAM (Dynamic Resolution Assignment For Multimodal Multi-Agent Debate), which operates via two core components: (1) Dynamic Resolution Assignment, a zero-shot probe round where agents test multiple resolutions, quantify uncertainty using Average Normalized Log-Likelihood (ANLL), and use an adaptive threshold to assign each agent to its empirically optimal resolution; (2) Uncertainty-Guided Rollback Aggregation counters groupthink by tracking each agent's uncertainty over rounds and restoring early low-uncertainty answers overridden by group pressure. On six multimodal datasets, DREAM improves the accuracy-token trade-off over multi-agent debate baselines by 1.5-3.2% accuracy without dataset-specific tuning.
Oct 4, 2026

Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination

Long-horizon search requires agents to gather evidence across multiple steps and synthesize it into well-supported answers. The recent agent harnesses provide a natural and promising framework to support such long-running search processes. As interaction histories grow, one single agent in harnesses might get stuck and cause the policy to lose track of unresolved questions, overlook useful evidence, or terminate before sufficient support has been collected. One of promising way is to decouple three distinct responsibilities of proposing retrieval actions, updating persistent state, and deciding when to stop rather than concentrating them within a single policy. Targeted at it, we introduce Harness-Search, a multi-agent search harness to reduce the local errors propagating across subsequent exploration, evidence curation, and termination decisions. In particular, Harness-Search assigns these responsibilities to three permission-bounded authorities: a Retrieval Policy that proposes search operations, a Memory Operator that validates and commits persistent-state updates, and a Summary Auditor that accepts or rejects termination based on the sufficiency of the curated evidence. Together, these roles form a Propose-Commit-Audit loop in which actions are proposed, persistent evidence is selectively committed, and stopping decisions are subjected to an explicit sufficiency check. Across seven long-horizon search benchmarks, Harness-Search improves both retrieval and answer generation under the same policy backbone, increasing Recall by 4.60-27.92 points and Final-Answer Recall by 12.34-30.13 points over the strongest harness-based baseline on each evidence-retrieval benchmark. Moreover, trajectory-level analyses show that Harness-Search continues to accumulate useful evidence and expand evidence coverage with less redundant retrieval as the search history grows.
Oct 3, 2026

Multi-Agent Spectrum Sharing

This project explores how multiple cognitive radars can learn to share limited wireless spectrum with other radio users without interfering with one another. Using machine learning (ML), each device independently decides where and how widely to transmit within a fixed 100 MHz band. The system analyzes real or simulated signal activity to detect which parts of the spectrum are currently in use and which are open. Based on this information, the devices adapt their transmission choices to avoid crowded frequencies while making efficient use of available space. The goal is to develop a flexible, scalable approach to spectrum sharing that could support future wireless communication systems. Experimental results using both over-the-air software-defined radio (SDR) recordings and simulated environments demonstrate that the proposed meta-learning approach consistently balances competing objectives better than conventional reinforcement learning (RL) methods in multi-agent spectrum-sharing scenarios. Across five multi-agent benchmark environments, our proposed method achieved the highest average reward among the primary baseline algorithms while simultaneously maintaining low collision rates and stable transmission behavior.