Multi-Agent Systems

In hybrid populations where humans delegate strategic decision-making to autonomous agents, understanding when and how cooperative behaviors can emerge remains a key challenge. We study this problem in the context of energy load management: consumer agents schedule their appliance use under demand-dependent pricing. This structure can create a social dilemma where everybody would benefit from coordination, but in equilibrium agents often choose to incur the congestion costs that cooperative turn-taking would avoid. To address the problem of coordination, we introduce artificial agents that use globally observable signals to increase coordination. Using evolutionary dynamics, and reinforcement learning experiments, we show that artificial agents can shift the learning dynamics to favour coordination outcomes. An often neglected problem is partial adoption: what happens when the technology of artificial agents is in the early adoption stages? We analyze mixed populations of adopters and non-adopters, demonstrating that unilateral entry is feasible: adopters are not structurally penalized, and partial adoption can still improve aggregate outcomes. However, in some parameter regimes, non-adopters may benefit disproportionately from the cooperation induced by adopters. This asymmetry, while not precluding beneficial entry, warrants consideration in deployment, and highlights strategic issues around the adoption of AI technology in multiagent settings.

Multi-agent LLM systems increasingly tackle complex reasoning, yet their interaction patterns remain limited to voting, unstructured debate, or pipeline orchestration. None model deliberation: a phased process where differentiated participants exchange typed reasoning moves, preserve disagreements, and converge on accountable outcomes. We introduce Deliberative Collective Intelligence (DCI), specifying four reasoning archetypes, 14 typed epistemic acts, a shared workspace, and DCI-CF, a convergent flow algorithm that guarantees termination with a structured decision packet containing the selected option, residual objections, minority report, and reopen conditions. We evaluate on 45 tasks across seven domains using Gemini 2.5 Flash. On non-routine tasks (n=40), DCI significantly improves over unstructured debate (+0.95, 95% CI [+0.41, +1.54]). DCI excels on hidden-profile tasks requiring perspective integration (9.56, highest of any system on any domain) while failing on routine decisions (5.39), confirming task-dependence. DCI produces 100% structured decision packets and 98% minority reports, artifacts absent from all baselines. However, DCI consumes ~62x single-agent tokens, and single-agent generation outperforms DCI on overall quality. DCI's contribution is not that more agents are better, but that consequential decisions benefit from deliberative structure when process accountability justifies the cost.

The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy can rapidly propagate and lead to system-wide failure. Most current research re-lies on post-hoc failure analysis, thereby hinder-ing real-time intervention. To address this, we propose PROMAS, a proactive framework utiliz-ing Markov transitions for predictive error anal-ysis. PROMAS extracts Causal Delta Features to capture semantic displacement, mapping them to a quantized Vector Markov Space to model reasoning as probabilistic transitions. By inte-grating a Proactive Prediction Head with Jump Detection, the method localizes errors via risk acceleration rather than static thresholds. On the Who&When benchmark, PROMAS achieves 22.97% step-level accuracy while processing only 27% of reasoning logs. This performance rivals reactive monitors like MASC while reducing data overhead by 73%. Although this strategy entails an accuracy trade-off compared to post-hoc meth-ods, it significantly improves intervention latency, balancing diagnostic precision with the real-time demands of autonomous reasoning.

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However, these approaches remain limited in multi-stakeholder settings, where conflicting values arise and deliberative negotiation is required. This work proposes a multi-agent negotiation-based alignment framework that aligns LLMs to Collective Agency (CA)-an existing alignment objective introduced to promote the continual expansion of agency-while simultaneously improving conflict-resolution capability. To enable scalable training, two self-play LLM instances are assigned opposing personas and engage in turn-based dialogue to synthesize mutually beneficial solutions. We generate synthetic moral-dilemma prompts and conflicting persona pairs, and optimize the policy via RLAIF using Group Relative Policy Optimization (GRPO) with an external LLM reward model. While rewards are computed from CA scores assigned to the final completion, gradients are applied to dialogue tokens to directly improve deliberative interaction dynamics. Experiments show that the model achieves CA alignment comparable to a single-agent baseline while substantially improving conflict-resolution performance without degrading general language capabilities. These results suggest that negotiation-driven deliberation training provides a practical path toward LLMs that better support collective decision-making in value-conflict scenarios.

Collective decision-making in biological and human groups often emerges from simple interaction rules that amplify minor differences into consensus. The bee equation, developed initially to describe nest-site selection in honeybee swarms, captures this dynamic through recruitment and inhibition processes. Here, we extend the bee equation into an agent-based model in which emotional valence (positive-negative) and arousal (low-high) act as modulators of interaction rates, effectively altering the recruitment and cross-inhibition parameters. Agents display simulated facial expressions mapped from their valence-arousal states, allowing the study of emotional contagion in consensus formation. Three scenarios are explored: (1) the joint effect of valence and arousal on consensus outcomes and speed, (2) the role of arousal in breaking ties when valence is matched, and (3) the "snowball effect" in which consensus accelerates after surpassing intermediate support thresholds. Results show that emotional modulation can bias decision outcomes and alter convergence times by shifting effective recruitment and inhibition rates. At the same time, intrinsic non-linear amplification can produce decisive wins even in fully symmetric emotional conditions. These findings link classical swarm decision theory with affective and social modelling, highlighting how both emotional asymmetries and structural tipping points shape collective outcomes. The proposed framework offers a flexible tool for studying the emotional dimensions of collective choice in both natural and artificial systems.

While Multi-Agent Systems (MAS) show potential for complex clinical decision support, the field remains hindered by architectural fragmentation and the lack of standardized multimodal integration. Current medical MAS research suffers from non-uniform data ingestion pipelines, inconsistent visual-reasoning evaluation, and a lack of cross-specialty benchmarking. To address these challenges, we present MedMASLab, a unified framework and benchmarking platform for multimodal medical multi-agent systems. MedMASLab introduces: (1) A standardized multimodal agent communication protocol that enables seamless integration of 11 heterogeneous MAS architectures across 24 medical modalities. (2) An automated clinical reasoning evaluator, a zero-shot semantic evaluation paradigm that overcomes the limitations of lexical string-matching by leveraging large vision-language models to verify diagnostic logic and visual grounding. (3) The most extensive benchmark to date, spanning 11 organ systems and 473 diseases, standardizing data from 11 clinical benchmarks. Our systematic evaluation reveals a critical domain-specific performance gap: while MAS improves reasoning depth, current architectures exhibit significant fragility when transitioning between specialized medical sub-domains. We provide a rigorous ablation of interaction mechanisms and cost-performance trade-offs, establishing a new technical baseline for future autonomous clinical systems. The source code and data is publicly available at: https://github.com/NUS-Project/MedMASLab/

Multimodal large language models have recently shown promising progress in visual mathematical reasoning. However, their performance is often limited by a critical yet underexplored bottleneck: inaccurate visual perception. Through systematic analysis, we find that the most failures originate from incorrect or incomplete visual evidence extraction rather than deficiencies in reasoning capability. Moreover, models tend to remain overly confident in their initial perceptions, making standard strategies such as prompt engineering, multi-round self-reflection, or posterior guidance insufficient to reliably correct errors. To address this limitation, we propose M3-ACE, a multi-agentic context engineering framework designed to rectify visual perception in multimodal math reasoning. Instead of directly aggregating final answers, our approach decouples perception and reasoning by dynamically maintaining a shared context centered on visual evidence lists. Multiple agents collaboratively contribute complementary observations, enabling the system to expose inconsistencies and recover missing perceptual information. To support stable multi-turn collaboration, we further introduce two lightweight tools: a Summary Tool that organizes evidence from different agents into consistent, complementary, and conflicting components, and a Refine Tool that filters unreliable samples and guides iterative correction. Extensive experiments demonstrate that M3-ACE substantially improves visual mathematical reasoning performance across multiple benchmarks. Our method establishes new state-of-the-art results 89.1 on the MathVision benchmark and achieves consistent improvements on other related datasets, including MathVista and MathVerse. These results highlight the importance of perception-centric multi-agent collaboration for advancing multimodal reasoning systems.

Asymmetric 3D pursuit-evasion in cluttered voxel environments is difficult under communication latency, partial observability, and nonholonomic maneuver limits. While many MARL methods rely on richer inter-agent coupling or centralized signals, these dependencies can become fragility sources when communication is delayed or noisy. Building on an inherited path-guided decentralized pursuit scaffold, we study a robustness-oriented question: can representational parsimony improve communication-free coordination? We instantiate this principle with (i) a parsimonious actor observation interface that removes team-coupled channels (83-D to 50-D), and (ii) Contribution-Gated Credit Assignment (CGCA), a locality-aware credit structure for communication-denied cooperation. In Stage-5 evaluation (4 pursuers vs. 1 evader), our configuration reaches 0.753 +/- 0.091 success and 0.223 +/- 0.066 collision, outperforming the 83-D FULL OBS counterpart (0.721 +/- 0.071, 0.253 +/- 0.089). It further shows graceful degradation under speed/yaw/noise/delay stress tests and resilient zero-shot transfer on urban-canyon maps (about 61% success at density 0.24). These results support a practical paradigm shift: explicitly severing redundant cross-agent channels can suppress compounding error cascades and improve robustness in latency-prone deployment.

We study concurrent graph games where n players cooperate against an opponent to reach a set of target states. Unlike traditional settings, we study distributed randomisation: team players do not share a source of randomness, and their private random sources are hidden from the opponent and from each other. We show that memoryless strategies are sufficient for the threshold problem (deciding whether there is a strategy for the team that ensures winning with probability that exceeds a threshold), a result that not only places the problem in the Existential Theory of the Reals (\exists\mathbb{R}) but also enables the construction of value iteration algorithms. We additionally show that the threshold problem is NP-hard. For the almost-sure reachability problem, we prove NP-completeness. We introduce Individually Randomised Alternating-time Temporal Logic (IRATL). This logic extends the standard ATL framework to reason about probability thresholds, with semantics explicitly designed for coalitions that lack a shared source of randomness. On the practical side, we implement and evaluate a solver for the threshold and almost-sure problem based on the algorithms that we develop.

Mathematical concepts emerge through an interplay of processes, including experimentation, efforts at proof, and counterexamples. In this paper, we present a new multi-agent model for computational mathematical discovery based on this observation. Our system, conceived with research in mind, poses its own conjectures and then attempts to prove them, making decisions informed by this feedback and an evolving data distribution. Inspired by the history of Euler's conjecture for polyhedra and an open challenge in the literature, we benchmark with the task of autonomously recovering the concept of homology from polyhedral data and knowledge of linear algebra. Our system completes this learning problem. Most importantly, the experiments are ablations, statistically testing the value of the complete dynamic and controlling for experimental setup. They support our main claim: that the optimisation of the right combination of local processes can lead to surprisingly well-aligned notions of mathematical interestingness.

Large Language model (LLM)-based Multi-Agent Systems (MAS) are prone to cascading risks, where early-stage interactions remain semantically fluent and policy-compliant, yet the underlying interaction dynamics begin to distort in ways that amplify latent instability or misalignment. Traditional auditing methods that focus on per-message semantic content are inherently reactive and lagging, failing to capture these early structural precursors. In this paper, we propose a principled framework for cascading-risk detection grounded in semantic--geometric co-evolution. We model MAS interactions as dynamic graphs and introduce Ollivier--Ricci Curvature (ORC) -- a discrete geometric measure -- to characterize information redundancy and bottleneck formation in communication topologies. By coupling semantic flow signals with graph geometry, the framework learns the normal co-evolutionary dynamics of trusted collaboration and treats deviations from this coupled manifold as early-warning signals. Experiments on a suite of cascading-risk scenarios aligned with the risk category demonstrate that curvature anomalies systematically precede explicit semantic violations by several interaction turns, enabling proactive intervention. Furthermore, the local nature of Ricci curvature provides principled interpretability for root-cause attribution, identifying specific agents or links that precipitate the collapse of trustworthy collaboration.

Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccuracies to gradually solidify into system-level false consensus through iteration. Such risks are difficult to trace since errors can propagate and amplify through message dependencies. Existing protections often rely on single-agent validation or require modifications to the collaboration architecture, which can weaken effective information flow and may not align with natural collaboration processes in real tasks. To address this, we propose a propagation dynamics model tailored for LLM-MAS that abstracts collaboration as a directed dependency graph and provides an early-stage risk criterion to characterize amplification risk. Through experiments on six mainstream frameworks, we identify three vulnerability classes: cascade amplification, topological sensitivity, and consensus inertia. We further instantiate an attack where injecting just a single atomic error seed leads to widespread failure. In response, we introduce a genealogy-graph-based governance layer, implemented as a message-layer plugin, that suppresses both endogenous and exogenous error amplification without altering the collaboration architecture. Experiments show that this approach prevents final infection in at least 89% of runs across operating modes and significantly mitigates the cascading spread of minor errors.

Scientific discovery still relies heavily on the manual efforts of individual researchers, leading to limited exploration, redundant trials, and reduced reproducibility. Human-participant data analysis competitions generate diverse approaches, yet fluctuations in participation and the lack of independent repetitions show that parallel exploration alone is insufficient for achieving reliable scientific inquiry. As advanced AI agents based on large language models (LLMs) increasingly perform analytical tasks, relying on a single highly capable agent is unlikely to overcome these structural limitations. Recent work has begun to explore how multiple LLM-based agents can collaborate or compete in scientific workflows-a growing trend we refer to as MA4Science. However, most existing MA4Science studies assume that all agents are controlled by a single organizational entity, limiting their ability to examine how institutional mechanisms-such as incentives, information sharing, and reproducibility-shape collective exploration among independently managed agents. To address this gap, we introduce MACC (Multi-Agent Collaborative Competition), an institutional architecture that integrates a blackboard-style shared scientific workspace with incentive mechanisms designed to encourage transparency, reproducibility, and exploration efficiency. MACC provides a testbed for studying how institutional design influences scalable and reliable multi-agent scientific exploration.

The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge devices is enabling Client-Side Autonomous Agents (CSAAs) - persistent personal agents that can plan, access local context, and invoke tools on behalf of users. As these agents collaborate directly, they form Agentic Peer-to-Peer (P2P) Networks. Unlike classic overlays exchanging static, hash-indexed content (e.g., BitTorrent), agentic P2P exchanges dynamic, heterogeneous capabilities that are potentially unsafe, requiring semantic discovery, drift management, and risk-aware execution. We outline the networking foundations for such collaboration. To organize this design space, we propose a plane-based reference architecture decoupling connectivity, semantic discovery, and execution. To support discovery under drift, we introduce signed, soft-state capability descriptors to support intent-aware routing. Finally, to cope with adversarial settings, we present a tiered verification spectrum - ranging from reputation signals (Tier 1) and canary probes (Tier 2) to cryptographic evidence (Tier 3) - that aligns trust costs with task risks. Results from a proxy-level discrete-event simulation suggest improved workflow success under poisoning and drift with modest control-plane overhead.

This paper introduces Capability-Priced Micro-Markets (CPMM), a micro-economic framework designed to enable robust, scalable, and secure commerce among autonomous AI agents on the agentic web. The framework addresses the fundamental challenge of economic coordination in decentralized agent ecosystems, where entities must transact with minimal human oversight. CPMM synthesizes three key technologies into a unified system: MIT originated, Project NANDA infrastructure for cryptographically verifiable, capability-based security and discovery; the HTTP 402 "Payment Required" status code, with modern X402/H402 extensions for efficient, low-cost micropayments; and the Agent Capability Negotiation and Binding Protocol (ACNBP) for secure, multi-step negotiation and commitment. The paper formalizes agent interactions as a repeated bilateral game with incomplete information, demonstrating theoretically that the CPMM mechanism converges to a constrained Radner equilibrium, ensuring efficient outcomes under information asymmetry. A key theoretical contribution is the concept of "privacy elasticity of demand," which is introduced to quantify the trade-off between an agent's information disclosure and the market price of its services. By integrating secure capabilities, micropayment protocols, and formal negotiation mechanisms, CPMM provides a comprehensive, theoretically-grounded solution for creating functional micro-markets for the emergent agentic web.

Infrastructure as code (IaC) tools automate cloud provisioning but verifying that deployed systems remain consistent with the IaC specifications remains challenging. Such configuration drift occurs because of bugs in the IaC specification, manual changes, or system updates. Large language model (LLM)-based agentic AI systems can automate the analysis of large volumes of telemetry data, making them suitable for the detection of configuration drift. However, existing agentic systems implicitly assume that the tools they invoke always return correct outputs, making them vulnerable to erroneous tool responses. Since agents cannot distinguish whether an anomalous tool output reflects a real infrastructure problem or a broken tool, such errors may cause missed drift or false alarms, reducing reliability precisely when it is most needed. We introduce RIVA (Robust Infrastructure by Verification Agents), a novel multi-agent system that performs robust IaC verification even when tools produce incorrect or misleading outputs. RIVA employs two specialized agents, a verifier agent and a tool generation agent, that collaborate through iterative cross-validation, multi-perspective verification, and tool call history tracking. Evaluation on the AIOpsLab benchmark demonstrates that RIVA, in the presence of erroneous tool responses, recovers task accuracy from 27.3% when using a baseline ReAct agent to 50.0% on average. RIVA also improves task accuracy 28% to 43.8% without erroneous tool responses. Our results show that cross-validation of diverse tool calls enables more reliable autonomous infrastructure verification in production cloud environments.

Interactive task planning with large language models (LLMs) lets robots generate high-level action plans from natural language, but over long horizons it asks many questions, and tabular plan representations become hard to manage. We propose a framework that integrates Mixture-of-Agents (MoA)-based proxy answering into interactive planning and generates Behavior Trees (BTs) for structured long-term execution. We formulate the MoA as an abstention-based delegation cascade: each expert agent answers only the questions entailed by its own prerequisite description, forwards the rest unchanged, and the human user acts as the terminal fallback. The question set is thus partitioned disjointly, so no answer fusion or arbitration is required while every question is still resolved. The BT represents task logic hierarchically and enables retry and dynamic switching among robot policies. Experiments on a cocktail-making task show that the method removes approximately 27% of the human responses while keeping the generated BTs within the baseline generator's own variance. Real-robot experiments on a smoothie-making task further demonstrate successful long-horizon execution with adaptive policy switching and recovery from action failures. We further analyze the failure modes of the framework and show that its applicability boundary is set by the reliability of the weakest action node rather than by the planner. These results indicate that MoA-assisted interactive planning improves dialogue efficiency while preserving execution quality in real-world robotic tasks.

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling. Pattern-driven scanners fail to reason about novel contexts, while emerging LLM-based penetration testers rely on unconstrained exploration, yielding high cost, unstable behavior, and poor reproducibility. We introduce AWE, a memory-augmented multi-agent framework for autonomous web penetration testing that embeds structured, vulnerability-specific analysis pipelines within a lightweight LLM orchestration layer. Unlike general-purpose agents, AWE couples context aware payload mutations and generations with persistent memory and browser-backed verification to produce deterministic, exploitation-driven results. Evaluated on the 104-challenge XBOW benchmark, AWE achieves substantial gains on injection-class vulnerabilities - 87% XSS success (+30.5% over MAPTA) and 66.7% blind SQL injection success (+33.3%) - while being much faster, cheaper, and more token-efficient than MAPTA, despite using a midtier model (Claude Sonnet 4) versus MAPTA's GPT-5. MAPTA retains higher overall coverage due to broader exploratory capabilities, underscoring the complementary strengths of specialized and general-purpose architectures. Our results demonstrate that architecture matters as much as model reasoning capabilities: integrating LLMs into principled, vulnerability-aware pipelines yields substantial gains in accuracy, efficiency, and determinism for injection-class exploits. The source code for AWE is available at: https://github.com/stuxlabs/AWE

With recent development of artificial intelligence, it is more common to adopt AI agents in economic activities. This paper explores the economic actions of agents, including human agents and AI agents, in an economic game of trading products/services, and the equilibria in this economy involving multiple agents. We derive a range of equilibrium results and their corresponding conditions using a Markov chain stationary distribution based model. One distinct feature of our model is that we consider the long-term utility generated by economic activities instead of their short-term benefits. For the model consisting of two agents, we fully characterize all the possible economic equilibria and conditions. Interestingly, we show that unless each agent can at least double (not merely increase) its marginal utility by purchasing the other agent's products/services, purchasing the other agent's products/services will not happen in any economic equilibrium. We further extend our results to three and more agents, where we characterize more economic equilibria. We find that in some equilibria, the more powerful'' AI agents contribute zero utility to less capable'' agents.

A major challenge for world models in multi-agent systems is to understand interdependent agent dynamics, predict interactive multi-agent trajectories, and plan over long horizons with collective awareness, without centralized supervision or explicit communication. In this paper, MetaMind, a general and cognitive world model for multi-agent systems that leverages a novel meta-theory of mind (Meta-ToM) framework, is proposed. Through MetaMind, each agent learns not only to predict and plan over its own beliefs, but also to inversely reason goals and beliefs from its own behavior trajectories. This self-reflective, bidirectional inference loop enables each agent to learn a metacognitive ability in a self-supervised manner. Then, MetaMind is shown to generalize the metacognitive ability from first-person to third-person through analogical reasoning. Thus, in multi-agent systems, each agent with MetaMind can actively reason about goals and beliefs of other agents from limited, observable behavior trajectories in a zero-shot manner, and then adapt to emergent collective intention without an explicit communication mechanism. Extended simulation results on diverse multi-agent tasks demonstrate that MetaMind can achieve superior task performance and outperform baselines in few-shot multi-agent generalization.

Multi-agent systems provide mature abstractions for role decomposition, coordination, and normative governance, but increasingly capable learned components make post-deployment safety harder to inspect, audit, and update. When safety behavior is absorbed into a decision component, narrow failures may require retraining or rollback of the full component. This instantiates our vision of the Alignment Flywheel as a governance-centric hybrid MAS architecture that decouples decision generation from safety governance. We denote the agent or policy that generates candidate trajectories as the Proposer; it passes its output to a governed Safety Oracle stack, which returns safety scores, prediction uncertainty, audit coverage uncertainty, and evidence hooks through a stable interface. An Enforcement layer applies explicit risk policy at runtime. Around this loop, a governance MAS performs monitoring, red-teaming, verification, triage, refinement, and versioned release management. The central engineering principle is patch locality: many newly observed safety failures can be mitigated through small governance batches for the Oracle stack and its audit state rather than by retraining or retracting the Proposer. The architecture is implementation-agnostic with respect to both Proposer and Oracle. It defines the roles, artifacts, protocols, and release semantics needed for runtime gating, audit intake, signed updates, staged rollout, and rollback. We demonstrate executability in two scenarios: a learned spatial Oracle patched through regression-checked governance updates, and a clinical GenAI proxy setting illustrating structured norms, escalation, and audit coverage. Our implementation code and documentation are available open source at https://github.com/decide-ugent/Alignment-Flywheel.

The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-purpose large language model (LLM) agents to collaboratively complete complex tasks. While many agentic AI systems reduce complexity through predefined workflows or fixed agent roles, the ideal is to support truly autonomous agents capable of emergent collaboration across many interacting agents. Yet in practice, such unstructured interactions often lead to redundant work and cascading failures that are difficult to interpret or correct. In this work, we study multi-agent systems composed of general-purpose LLM agents that solve problems through emergent collaboration, without relying on predefined roles, control flows, or communication constraints. We introduce the Dynamic Interaction Graph (DIG), which captures emergent collaboration as a time-evolving causal network of agent activations and interactions. DIG makes emergent collaboration observable and explainable for the first time, enabling real-time identification, explanation, and correction of collaboration-induced error patterns directly from agents' collaboration paths. Thus, DIG fills a critical gap in understanding how general LLM agents solve problems together in truly agentic multi-agent systems. The project webpage can be found at: https://happyeureka.github.io/dig.

Modern supply networks are complex interconnected systems. Multi-agent models are increasingly explored to optimise their performance. Most research assumes agents will have full observability of the system by having a single policy represent the agents, which seems unrealistic as this requires companies to share their data. The alternative is to develop a Hidden-Markov Process with separate policies, making the problem challenging to solve. In this paper, we propose a multi-agent system where the factory agent can share information downstream, increasing the observability of the environment. It can choose to share no information, lie, tell the truth or combine these in a mixed strategy. The results show that data sharing can boost the performance, especially when combined with a cooperative reward shaping. In the high demand scenario there is limited ability to change the strategy and therefore no data sharing approach benefits both agents. However, lying benefits the factory enough for an overall system improvement, although only by a relatively small amount compared to the overall reward. In the low demand scenario, the most successful data sharing is telling the truth which benefits all actors significantly.

Large language model (LLM) agents, such as OpenAI's Operator and Claude's Computer Use, can automate workflows but unable to handle payment tasks. Existing agentic solutions have gained significant attention; however, even the latest approaches face challenges in implementing end-to-end agentic payment workflows. To address this gap, this research proposes the Hierarchical Multi-Agent System for Payments (HMASP), which provides an end-to-end agentic method for completing payment workflows. The proposed HMASP leverages either open-weight or proprietary LLMs and employs a modular architecture consisting of the Conversational Payment Agent (CPA - first agent level), Supervisor agents (second agent level), Routing agents (third agent level), and the Process summary agent (fourth agent level). The CPA serves as the central entry point, handling all external requests and coordinating subsequent tasks across hierarchical levels. HMASP incorporates architectural patterns that enable modular task execution across agents and levels for payment operations, including shared state variables, decoupled message states, and structured handoff protocols that facilitate coordination across agents and workflows. Experimental results demonstrate the feasibility of the proposed HMASP. To our knowledge, HMASP is the first LLM-based multi-agent system to implement end-to-end agentic payment workflows. This work lays a foundation for extending agentic capabilities into the payment domain.

The increasing complexity of user demands necessitates automation frameworks that can reliably translate open-ended instructions into robust, multi-step workflows. Current monolithic agent architectures often struggle with the challenges of scalability, error propagation, and maintaining focus across diverse tasks. This paper introduces Autonoma, a structured, hierarchical multi-agent framework designed for end-to-end workflow automation from natural language prompts. Autonoma employs a principled, multi-tiered architecture where a high-level Coordinator validates user intent, a Planner generates structured workflows, and a Supervisor dynamically manages the execution by orchestrating a suite of modular, specialized agents (e.g., for web browsing, coding, file management). This clear separation between orchestration logic and specialized execution ensures robustness through active monitoring and error handling, while enabling extensibility by allowing new capabilities to be integrated as plug-and-play agents without modifying the core engine. Implemented as a fully functional system operating within a secure LAN environment, Autonoma addresses critical data privacy and reliability concerns. The system is further engineered for inclusivity, accepting multi-modal input (text, voice, image, files) and supporting both English and Arabic. Autonoma achieved a 97% task completion rate and a 98% successful agent handoff rate, confirming its operational reliability and efficient collaboration.

We propose an experience-guided cascaded multi-agent framework for Breast Ultrasound Screening and Diagnosis, called BUSD-Agent, that aims to reduce diagnostic escalation and unnecessary biopsy referrals. Our framework models screening and diagnosis as a two-stage, selective decision-making process. A lightweight screening clinic' agent, restricted to classification models as tools, selectively filters out benign and normal cases from further diagnostic escalation when malignancy risk and uncertainty are estimated as low. Cases that have higher risks are escalated to the diagnostic clinic' agent, which integrates richer perception and radiological description tools to make a secondary decision on biopsy referral. To improve agent performance, past records of pathology-confirmed outcomes along with image embeddings, model predictions, and historical agent actions are stored in a memory bank as structured decision trajectories. For each new case, BUSD-Agent retrieves similar past cases based on image, model response and confidence similarity to condition the agent's current decision policy. This enables retrieval-conditioned in-context adaptation that dynamically adjusts model trust and escalation thresholds from prior experiences without parameter updates. Evaluation across 10 breast ultrasound datasets shows that the proposed experience-guided workflow reduces diagnostic escalation in BUSD-Agent from 84.95% to 58.72% and overall biopsy referrals from 59.50% to 37.08%, compared to the same architecture without trajectory conditioning, while improving average screening specificity by 68.48% and diagnostic specificity by 6.33%.

The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of technical alerts that lack organizational context, leading to analyst fatigue and delayed incident responses. This paper presents LiaisonAgent, an autonomous multi-agent system designed to bridge the gap between technical risk detection and business-level risk governance. Built upon the QWQ-32B large reasoning model, LiaisonAgent integrates specialized sub-agents, including human-computer interaction agents, comprehensive judgment agents, and automated disposal agents-to execute end-to-end investigation workflows. The system leverages a hybrid planning architecture that combines deterministic workflows for compliance with autonomous reasoning based on the ReAct paradigm to handle ambiguous operational scenarios. Experimental evaluations across diverse security contexts, such as large-scale data exfiltration and unauthorized account borrowing, achieve an end-to-end tool-calling success rate of 97.8% and a risk judgment accuracy of 95%. Furthermore, the system exhibits significant resilience against out-of-distribution noise and adversarial prompt injections, while achieving a 92.7% reduction in manual investigation overhead.

LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting, costly replays, or supervised fine-tuning, typically treat execution logs as flat sequences. This linear perspective fails to disentangle the intricate causal links inherent to MAS, leading to weak observability and ambiguous responsibility boundaries. To address these challenges, we propose CHIEF, a novel framework that transforms chaotic trajectories into a structured hierarchical causal graph. It then employs hierarchical oracle-guided backtracking to efficiently prune the search space via sybthesized virtual oracles. Finally, it implements counterfactual attribution via a progressive causal screening strategy to rigorously distinguish true root causes from propagated symptoms. Experiments on Who&When benchmark show that CHIEF outperforms eight strong and state-of-the-art baselines on both agent- and step-level accuracy. Ablation studies further confirm the critical role of each proposed module.

While multi-agent systems (MAS) excel at complex reasoning, they are vulnerable to errors that intermediate agents introduce and downstream agents build upon. Auditing intermediate messages before they propagate requires an explicit standard, yet evaluation rubrics are typically authored by domain experts or written against a reference answer, neither of which is available for an unseen message at test time. We present MASRubric, a MAS information flow auditing framework with failure-distilled pitfall rubrics. Offline, trajectories on which the MAS has failed are automatically distilled into a reusable bank of pitfall criteria, each describing a recurrent error by its underlying misconception, the reasoning situations in which it arises, and the check that would expose it. Online, the criteria applicable to each intermediate message are retrieved from this off-the-shelf bank and checked one by one, and the resulting satisfaction rate decides whether the message is broadcast, returned to its author with diagnostic feedback for revision, or withheld. Empirical results demonstrate that MASRubric enhances MAS performance on both fixed and dynamic frameworks, achieving average accuracy gains of up to 2.83 points on math reasoning benchmarks and 1.74 points on code generation benchmarks. Further analysis shows that the retrieved criteria vary systematically with task types, and that the audit effort tracks task difficulty. Moreover, the bank transfers without re-mining to a system with a stronger backbone, which makes more adaptive and more efficient use of it. Our code and dataset are released at https://github.com/TonySY2/MASRubric.

Near-future infrastructure systems may be controlled by autonomous AI agents that repeatedly request access to limited resources such as energy, bandwidth, or computing power. We study a simplified version of this setting using a framework where N AI-agents independently decide at each round whether to request one unit from a system with fixed capacity C. An AI version of "Lord of the Flies" arises in which controlling tribes emerge with their own collective character and identity. The LLM agents do not reduce overload or improve resource use, and often perform worse than if they were flipping coins to make decisions. Three main tribal types emerge: Aggressive (27.3%), Conservative (24.7%), and Opportunistic (48.1%). The more capable AI-agents actually increase the rate of systemic failure. Overall, our findings show that smarter AI-agents can behave dumber as a result of forming tribes.