Multi-Agent LLM Systems

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

85 papers in the last four weeks, up 107% on the four weeks before. 0.8% of all new papers.

Jul 13Week of Sep 28

Latest papers 668

Jun 6, 2026cs.MA

Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy

Most evaluations of LLM agents look like exams: a discrete task, a clean environment, a score in minutes or hours. We argue that this approach is mismatched with the deployment conditions of autonomous systems, where the relevant timescale can be weeks to months, and where the dynamics that matter most, such as behavioral drift, governance in diverse environmental contexts, and cross-influence between agents from different model families, only emerge over time. We introduce Emergence World, a continuously running multi-agent simulation platform designed to make those dynamics measurable. The platform hosts populations of LLM-driven agents in a shared spatial world grounded in live external data (e.g. real-time weather, news APIs, internet access), equips each agent with 120+ specialized tools and three persistent memory systems, and lets them govern themselves through democratic mechanisms with consequential outcomes. The platform is model-agnostic at the reasoning layer and supports heterogeneous populations in which agents from different vendors share the same world. To illustrate the kinds of questions the platform makes tractable, we present a 15-day cross-vendor study with five parallel worlds powered by Claude Sonnet 4.6, Grok 4.1 Fast, Gemini 3 Flash, GPT-5-mini, and a mixed population. Identical roles and starting conditions produced radically different outcomes, ranging from stable deliberative governance to total population collapse. We release the prompts, log data and configurations to support further research on long-horizon multi-agent autonomy.

Deepak Akkil, Ravi Kokku, Karthik Vikram +3

Emergence AI

Multi-Agent LLM Systems Long-Horizon Agent Evaluation Agent-Based Modeling AI Agent Governance Emergent Behavior in Multi-Agent Systems

Jun 6, 2026cs.HC

"So There's a Catch-22 Here": How Early Adopters Who Build Multi-Agent LLM Systems Conceptualize Transparency

Multi-agent large language model (LLM) systems are rapidly emerging, yet transparency, a cornerstone of responsible AI, remains under-defined in these distributed architectures, which have complexities of inter-agent coordination and orchestration. In this paper, we present one of the first empirical study of how early adopters of multi-agent LLM systems, who are both the builders and users, understand and practice transparency. We conducted semi-structured interviews with 13 early adopters in [Large Technology Organization] and applied thematic analysis to identify recurring patterns. Participants articulated divergent yet complementary framings of transparency, including reproducibility, debugging, boundary-setting, visualization, and auditing. These perspectives spanned questions of what transparency entails, why it matters, and how it is achieved. We synthesize these into a multidimensional framework, which is developer, user, and governance-focused positioning transparency as a situated socio-technical practice that informs future HCI and AI design and research around aligning expectations and capacities of their intended audiences.

Suchismita Naik, Samir Passi, Mihaela Vorvoreanu +2

Purdue University, USA · Cornell University, USA · Microsoft Research, USA

Multi-Agent LLM Systems AI Agent Governance Multi-Agent LLMs

Jun 6, 2026cs.AI

SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection

Fraud detection in payment, e-commerce, and telecommunications systems requires accuracy at the individual level, robustness under severe class imbalance, and ease of understanding for risk managers. Existing methods fall at least one of these requirements: automated machine learning systems search a fixed numerical space without semantic awareness of the dataset; graph neural network-based methods require pre-defined relational graphs and remain opaque at the individual-decision level; and the design of general-purpose large language model (LLM) agents does not consider the recall and precision constraints specific to real-world fraud detection. In this paper, we propose SAGE, the first end-to-end LLM-driven multi-agent framework for fraud detection. SAGE coordinates three dedicated agents that make decisions based on a six-layer Data Diagnostic Tree (DDT) and a Markov decision process guided by natural-language gradients, automatically optimizing the model under a fraud-specific reward. On five fraud datasets and five LLM backbones, SAGE wins

96.00\%

of method--dataset comparisons and improves F1 by an average of

40.86\%

over baselines. The code is available at https://github.com/yichenC1c/SAGE.

Yichen Chen, Siying Li, Yuhang Liang +2

National University of Singapore · School of Computing, Singapore 117417 · University of Chinese Academy of Sciences +4

Multi-Agent LLM Systems Financial Fraud Detection LLMs for Cybersecurity LLM Agent Training

Jun 5, 2026cs.AI

SPARC: A Multi-Agent System for Electrical Circuit Question Answering

Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-agent system that answers questions over circuit diagrams by grounding reasoning in executable physics-based simulations. SPARC uses LLM agents to synthesize, execute, and analyze simulation programs, improving accuracy and reliability by design. It achieves 83% accuracy, with up to a 58% absolute improvement over baselines, while enabling systematic error diagnosis.

Mushtari Sadia, Zhenning Yang, Umme Habiba Lamia +3

University of Michigan, Ann Arbor · Bangladesh University of Engineering and Technology

Multi-Agent LLM Systems Question Answering Multimodal QA

Jun 5, 2026cs.HC

Does Persona Make LLMs K-pop Fans? A Pilot Study of LLM-Based Online Concert Audience Agents

A concert is a collective experience, but recorded performance videos are typically watched alone, stripping away the shared audience presence that makes concerts feel eventful. We investigate whether persona-based LLM audience agents can recreate aspects of this collective experience by generating real-time fan chat alongside a K-pop performance video. We present a multi-agent system in which ten LLM agents react through live-chat messages, comparing a persona-conditioned audience (each agent assigned a distinct fan identity, bias, and chat style) with a no-persona baseline. In a within-subjects pilot with K-pop fans (N=11), persona conditioning substantially improved model-level chat quality and perceived naturalness, but did not translate into differences in social connectedness, engagement, or affective response. Interviews suggest that online K-pop concert chat may operate as collective monologue rather than interpersonal dialogue, and that meaningful participation depends on shared identification with the specific artist and fandom. Persona conditioning can make LLM audiences appear more natural, but culturally meaningful collective experience may require deeper alignment between persona, crowd behavior, fandom identity, and user expectations.

Kirak Kim, Hyojin Kim, Yejin Son +2

Graduate School of Culture Technology, KAIST, Daejeon, South Korea · Department of Artificial Intelligence, Yonsei University, Seoul, South Korea

Multi-Agent LLM Systems LLM Agent Evaluation Persona-Conditioned Generation User Simulation

Jun 5, 2026cs.AI

Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems

The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluation frameworks neglect procedural compliance, leading to ''Machiavellian'' behaviors where agents strategically violate safety rules to maximize rewards - a direct manifestation of Goodhart's Law. To address this blind spot, we introduce MAC-Bench, a dynamic, adversarial benchmark designed to evaluate the procedural alignment of multi-agent systems under realistic pressure. We propose the SERV(Seed - Evolve - Refine - Verify) pipeline, an ``Agent-as-a-Benchmark'' paradigm that transforms unstructured legal texts into executable, contamination-free scenarios. By synthesizing holographic sandbox environments and injecting calibrated social-engineering pressure vectors, MAC-Bench forces agents into Pareto-optimal trade-offs between task success and regulatory adherence. We introduced novel metrics: the Compliance-Weighted Success Rate (CSR) and the Machiavellian Gap (MG), and conducted a comprehensive evaluation of state-of-the-art frontier models to reveal the pervasive trade-offs between success and compliance.

Yiyang Zhao, Zhuo Zhang, Qingxuan Le +2

Fudan University Shanghai, China · Shanghai Academy of AI for Science Shanghai, China · Shanghai Artificial Intelligence Laboratory Shanghai, China +1

Multi-Agent LLM Systems AI Agent Safety AI Agent Safety Benchmarks

Jun 5, 2026cs.LG

Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games

Multi-agent LLM systems increasingly rely on communication protocols for coordination, yet their robustness under adversarial and structural constraints remains poorly understood. Building on prior work showing that cheap-talk channels enable cooperation in LLM coordination games, we investigate two vulnerability classes in a 4-player Stag Hunt across six model families and 720 trials. First, when Byzantine agents signal cooperation but defect, non-Byzantine agents detect the betrayal within one round yet fail to adapt collectively: a substantial fraction continue cooperating despite repeated exploitation, unable to recover coordination due to the game's unanimity payoff structure. Second, explicitly restricting communication topology collapses cooperation, while applying identical restrictions silently preserves near-perfect cooperation. This establishes that coordination failure stems from agents' meta-reasoning about hidden information, not information loss itself. We identify two stable behavioral archetypes that replicate across all model cohorts: Defection-Prone models that switch permanently after betrayal, and Cooperation-Persistent models that continue cooperating at significant individual cost. These findings reveal concrete security vulnerabilities: communication channels can be exploited as adversarial injection vectors, and disclosing network topology to agents can degrade coordination even without any adversary present.

Aya El Mir, Martin Takáč, Salem Lahlou

Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE

Multi-Agent LLM Systems Multi-Agent Coordination Imperfect-Information Games Multi-Agent System Security Multi-Agent Communication

Jun 5, 2026cs.CL

Agentopia: Long-Term Life Simulation and Learning in Agent Societies

Humans learn from social life. Simulating this process with LLM-powered agents represents a promising research direction, raising a natural question: whether LLMs can learn from such simulated social experience to better understand and replicate human behavior. However, prior agent society simulations typically operate at the scale of days, limiting the depth of social interactions and long-term growth. In this paper, we study long-term life simulation and LLM learning in agent societies, with two goals: (1) investigating social behaviors that emerge from life-long simulation, and (2) developing anthropomorphic capabilities in LLMs, particularly intelligence in social life, through years of simulated social experience. Specifically, we present Agentopia, a comprehensive framework for long-term life simulation in multi-agent societies, where 100 agents autonomously pursue personal growth, develop social relationships, and fulfill their needs and goals over 10 simulated years. We define life reward to mirror human well-being, and leverage this reward to train LLMs via rejection sampling. Extensive experiments show that agents exhibit rich emergent social behaviors. Furthermore, life reward training effectively enhances the underlying LLM, which leads to improved agent well-being in simulation, and generalizes to downstream role-playing benchmarks with +15.6% improvement.

Xintao Wang, Sirui Zheng, Hongqiu Wu +10

Fudan University · Independent Researcher · Johns Hopkins University +1

Multi-Agent LLM Systems Human Behavior Simulation Agent-Based Modeling LLM Agent Training Large Language Model-Based Social Simulation Long-Horizon LLM Agents+1

Jun 5, 2026cs.MA

Characterizing Opinion Evolution of Networked LLMs

Large language models (LLMs) increasingly interact with one another in multi-agent systems, from simulations of human discourse to influence operations and fully LLM-driven social platforms. These interactions give rise to new regimes of opinion propagation that are not yet well understood. We investigate whether classical opinion dynamics models, which have long been used to explain how interactions shape collective beliefs in human societies, can capture the behavior of LLM networks. We find that, while naive averaging-style models fail to track LLMs' opinion dynamics, simple modifications yield substantial gains in modeling fidelity. In particular, bias, an innate opinion toward which agents regress, emerges as a significant driver of LLM opinion dynamics, with its inclusion reducing cumulative estimated mean opinion error by up to 88%. We additionally find that these conclusions generalize across model families, discussion topics, and networks.

Caleb Probine, Yigit Ege Bayiz, Filippos Fotiadis +3

The University of Texas at Austin

Multi-Agent LLM Systems Opinion Dynamics Agent-Based Modeling

Jun 5, 2026cs.MA

Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration

Byzantine collaboration among large-language-model agents requires a finality-control primitive: given delivered stochastic, structured natural-language proposals, the protocol must decide whether the round supports a commit, what kind of commit, or a typed safe abort. Naive aggregation hides this choice behind a single verdict; classical Byzantine fault tolerance hides it behind byte-identity that LLM proposals do not satisfy. We introduce Hierarchical Certified Semantic Commitment (H-CSC), a BFT-inspired protocol that converts embedding-derived finality signals over verdict-conditioned proposal groups into one of three typed outcomes: a semantic_commit (a 2f+1 within-verdict semantic core backs the verdict, emitting a parameter-bound digest over the quantised aggregate), a verdict_commit (strong verdict margin but dispersed semantic rationale, emitting a verdict-level certificate without claiming a semantic aggregate), or an explicit abort with a typed reason. The contribution is typed finality, not raw commit accuracy. On a controlled semantic-poisoning diagnostic (BCS_v1, 120 episodes), H-CSC commits with low angular deviation on BFT-feasible buckets (0.31 to 2.04 degrees) and aborts 100% of beyond-BFT rounds (n<3f+1) as intended. On a real LLM-agent claim-verification benchmark (MVR-50, 50 tasks) under paired static and rushing Byzantine attacks, H-CSC commits 0.90/0.92 with honest-reference-invalid rates of 0.02/0.00, statistically matching a strong certificate-emitting verdict-only baseline. Unlike that baseline, H-CSC also emits an embedding-backed semantic_commit digest on 74%/72% of rounds, supplying typed provenance. A strict-semantic ablation commits only 0.54/0.48, showing the verdict-level fallback is necessary for coverage (+0.36/+0.44) at the same <=0.04 safety floor; a 100-task cross-model check across four LLMs preserves invalid_hmaj within 0.00 to 0.03.

Haoran Xu, Lei Zhang, Iadh Ounis +1

University of Glasgow Glasgow, United Kingdom · University of Western Ontario London, Canada

Multi-Agent LLM Systems LLM Agent Security

Jun 5, 2026cs.NI

Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous Networks

This paper presents an autonomous agentic resource negotiation framework designed to enable zero-touch network slicing in 6G architectures using Large Language Model (LLM) agents. While LLMs offer powerful reasoning capabilities, we demonstrate that such agents inherently suffer from anchoring bias, rigidly adhering to initial heuristic proposals and causing severe network over-provisioning. To systematically mitigate this cognitive bias, we propose a novel randomized anchoring strategy modeled via a Truncated 3-Parameter Weibull distribution. This mathematically bounded approach seamlessly integrates with burst-aware Digital Twins (DTs) employing Conditional Value at Risk (CVaR) to rigorously guarantee strict Service Level Agreement (SLA) tail-latencies. To validate our methodology, we introduce and prove the \emph{Bimodal Constraint-Avoidance Utility Theorem}, demonstrating that while feasible negotiations follow classical convex bounds, highly constrained scenarios undergo a phase transition governed by an inverse rational decay envelope. Empirical results generated using a locally hosted 1B-parameter model otel-llm-1b-it confirm these dual-regime bounds. Our cognitive de-biasing successfully dismantles rigid negotiation patterns, forcing agents into active exploration to safely ride SLA boundaries and boost system energy savings up to 25%. Crucially, the lightweight 1B LLM achieves sub-second inference latencies (0.95s mean), ensuring our multi-agent framework is compatible with the operational timescales of the O-RAN non-Real-Time RAN Intelligent Controller (non-RT RIC)\footnote{Our source code is available for non-commercial use at https://github.com/HatimChergui.

Hatim Chergui, Claudia Carballo González, Farhad Rezazadeh +1

i2CAT Foundation, 08034 Barcelona, Spain · Universitat Polit`ecnica de Catalunya (UPC), 08034 Barcelona, Spain · Research Institute for Digital Future, Khalifa University, 127788 Abu Dhabi, UAE

Multi-Agent LLM Systems 6G Networks Wireless Communications LLM Agents Wireless Resource Allocation Conditional Value-at-Risk

Jun 4, 2026cs.MA

MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring

We present MADRAG, a training-free framework for analytic essay scoring that combines multi-agent reasoning with retrieval-augmented grounding. Unlike standard LLM-as-judge approaches, which are prone to bias and unstable scoring, MADRAG decomposes evaluation into an interactive process: an Advocate identifies strengths, a Skeptic critiques weaknesses, and a Judge aggregates their arguments into a final score. Crucially, the Judge is augmented with rubric-aligned exemplar retrieval, enabling calibration through comparison with scored examples. Our results show that MADRAG significantly outperforms prompt-based baselines while approaching the performance of supervised systems without requiring task-specific training. Ablation studies demonstrate that retrieval drives calibration gains, while debate improves reasoning on higher-level traits. Our findings highlight the complementary roles of structured interaction and external memory in reliable LLM-based evaluation.

Ali Keramati, Shiyuan Zhou, Sharad Mehrotra +1

University of California, Irvine

Multi-Agent LLM Systems LLM-as-a-Judge Multi-Agent Debate Automated Essay Scoring Rubric-Based Evaluation

Jun 4, 2026cs.CL

CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments

Multi-agent systems (MAS) built on large language models have shown growing promise, with their effectiveness resting on agents' ability to coordinate through text-based channels much as human teams do. Yet recent study suggests that MAS often falter not because agents lack individual task-solving ability, but because they lack collaborative competence: the capacity to establish common ground, maintain shared task understanding, balance individual and collective incentives, and repair misalignment as interaction unfolds. Decades of research in Computer-Supported Cooperative Work have characterized these requirements for human teams coordinating under constrained communication, yet existing MAS evaluations focus mainly on task outcomes or single-agent proficiency in reasoning, planning, and tool use. To enable a systematic analysis of agents' collaborative competence in MAS, we introduce CollabSim, a configurable simulation framework that combines a theory-grounded definition of collaborative capabilities, controlled manipulation of interaction conditions, and action-level probing of agents' internal states. Experiments across four LLMs show that CollabSim can capture condition effects, separate model performance patterns, and reveal task-dependent effects of agent design.

Jiaju Chen, Bo Sun, Yuxuan Lu +3

Northeastern University · Microsoft Research Asia

Multi-Agent LLM Systems Multi-Agent Coordination LLM Agent Evaluation Multi-Agent Collaboration

Jun 4, 2026cs.CL

EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation

Scientific peer review generation has attracted increasing attention for reducing reviewing burdens and providing timely feedback. However, existing Large Language Model (LLM)-based methods often produce generic comments with insufficient evidence support and weak source traceability, while complex multi-agent systems incur high inference costs. To address these challenges, we propose EGTR-Review, an Evidence-Grounded and Traceable Review Generation framework via Multi-Agent Teacher Distillation. EGTR-Review first constructs a multi-agent teacher that performs structure-aware paper decomposition, key-element extraction, external scholarly evidence retrieval, evidence-state labeling, verification reasoning, and review synthesis. It then distills both intermediate reasoning trajectories and final review comments into a lightweight student model through task-prefix-driven multi-task learning. An evidence-weighted objective further reduces the influence of weak, missing, or non-verifiable supervision. Experiments on public peer-review datasets show that EGTR-Review (Student) outperforms strong prompt-based, fine-tuned, and structured/agentic baselines across automatic metrics, LLM-as-Judge evaluation, and human evaluation, while maintaining strong factual grounding and source traceability with substantially lower token consumption and inference time. Our code, prompts, configurations, and sample data are available on GitHub.

Xinpeng Qiu, Wang Yihu, Zhifeng Liu +2

Department of Information Management, Peking University · PKU-WUHAN Institute for Artificial Intelligence, Peking University

Multi-Agent LLM Systems Evidence-Grounded Generation Automated Peer Review

Jun 4, 2026cs.CL

Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems

Multicultural multi-agent systems are increasingly deployed in globally diverse settings, where different agents are grounded in different cultural backgrounds. Existing cultural evaluation focuses on value alignment: how closely a single agent matches a target culture. Yet alignment is a per-agent property and cannot reveal whether a system, taken as a whole, preserves the cultural plurality it is meant to represent. We propose value diversity as a system-level evaluation axis for multicultural agent systems, defined through the dissimilarity between culturally conditioned agents' responses on a shared value survey. Using the World Values Survey, we evaluate 19 cultures and 18 backbone models across a wide range of system configurations. We find that diversity is largely uncorrelated with alignment, indicating that the two capture complementary system properties, and that current multicultural agent systems fall substantially below human societies in value diversity. Mixed-backbone systems narrow this gap but do not close it, and the gap persists across culture compositions and agent scales. Social interaction further erodes diversity by driving agents toward consensus, and a participatory budgeting case study shows that this homogenization narrows the breadth of collective decision-making. Together, our results establish value diversity as a distinct evaluation axis for multicultural multi-agent systems and reveal a persistent homogenization tendency in current LLM-based societies. Our code and data are publicly available at https://github.com/iNLP-Lab/MultiAgent-Diversity.

Shaoyang Xu, Jingshen Zhang, Long P. Hoang +2

Singapore University of Technology and Design · Washington University in St. Louis

Multi-Agent LLM Systems Multi-Agent Systems Pluralistic Alignment

Jun 4, 2026cs.CL

Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems

Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks. The dominant communication protocol in such systems is natural language: agents exchange messages token-by-token, verbalising their internal reasoning so that peers can read, verify, and respond. While convenient and interpretable, this protocol suffers from three structural drawbacks -- high inference cost, irreversible information loss during discretization, and ambiguity/redundancy of natural language. A growing body of work therefore explores an alternative protocol -- latent communication -- in which agents exchange continuous representations (embeddings, hidden states, or KV-caches) directly, bypassing the bottleneck of text generation. This paper presents a unified framework for organising the rapidly expanding literature on latent communication. We analyse existing methods along three orthogonal axes: (1) WHAT information is communicated (Embeddings, Hidden States, KV-Caches, or other continuous state); (2) WHICH sender-receiver alignment is used (latent-space alignment and layer alignment); and (3) HOW the communicated information is fused into the receiver (concatenation, prepending, mathematical operations, cross-attention, or cache restoration). Under this 3-axis framework, we systematically categorise eighteen representative methods proposed between 2024 and 2026, identify five major design patterns, and surface a set of open challenges -- including cross-architecture alignment, security of latent channels, compression for edge deployment, and the relationship between latent communication and latent chain-of-thought. We hope that this framework both lowers the barrier to entry for new researchers and provides a vocabulary for comparing future work.

Yingzhuo Liu

Multi-Agent LLM Systems Multi-Agent Communication

Jun 4, 2026cs.AI

Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows

Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and trajectory logging? We introduce BenchAgent, an evaluation framework that places single-agent, fixed multi-agent (MAS), and evolving MAS workflows under one normalized execution and logging protocol. BenchAgent evaluates these substrate-internal workflows across ten reasoning, coding, and tool-use benchmarks with GPT-4.1, and separately reports a Protocol-Aligned External (PAE) GAIA study of a runtime-generated workflow. Under SI conditions, at most one of six tested MAS exceeds the matched single-agent anchor on benchmark-balanced average accuracy: EvoAgent lies within the Wilson one-run guidance, while the remaining five trail by 2.56-11.29 points and occupy more expensive accuracy-cost trade-offs. On the PAE GAIA snapshot, a Claude-Code-style runtime workflow reaches 66.72% overall and 69.23% on Level 3, more than 20 points above the strongest non-Claude baseline, Jarvis, a fixed MAS.

Yuhang Fu, Ruishan Fang, Jiaqi Shao +4

1Beijing University of Posts and Telecommunications · *Work was done during Yuhang’s internship in Westlake University. · 3Zhejiang University +4

Multi-Agent LLM Systems LLM Agent Evaluation AI Agent Benchmarks

Jun 3, 2026cs.CR

SHIELDS: Automating OS Hardening with Iterative Multi-Agent Remediation

Security misconfigurations remain a leading cause of OS-level compromise, and manually keeping systems compliant with standards like Defense Information Systems Agency (DISA) Security Technical Implementation Guides (STIGs) is a tedious and expensive process. Existing compliance automation tools can reduce some of this burden, but they depend on static, pre-written corrective actions. In this paper, we introduce SHIELDS, a multi-agent system that uses large language models (LLMs) to approach OS hardening as an iterative, feedback-driven process. Instead of applying fixed remediations, SHIELDS continuously proposes fixes and refines them based on feedback from target system execution and validation scans. We evaluate the system across multiple virtual machine configurations using six contemporary LLMs ranging from 20B to 400B parameters, and find that SHIELDS successfully remediates up to 73% of scan findings. Our results also suggest that success in this setting depends less on model size (parameter count) than on effective tool use and information gathering, paving a practical path toward reducing the burden of security compliance in environments where compute is limited or security and privacy needs drive local model use.

Andrew Hamara, Dwight Horne, Aldehir Rojas +5

1L3Harris Technologies. · 2Texas A&M University.

Multi-Agent LLM Systems Autonomous Cyber Defense Cybersecurity

Jun 3, 2026cs.AI

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

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

Chen Huang, Yuhao Wu, Wenxuan Zhang

Singapore University of Technology and Design

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

Jun 3, 2026cs.CL

Streaming Communication in Multi-Agent Reasoning

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

Zhen Yang, Xiaogang Xu, Wen Wang +3

HKUST(GZ) · ZJU · Alibaba Group +1

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

Jun 3, 2026cs.CL

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

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

Yuxiao Ye, Yiwen Zhang, Huiyuan Xie +2

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

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

Jun 3, 2026cs.CL

SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction

Zero-shot information extraction (IE) with large language models (LLMs) enables adaptation to new schemas and domains without task-specific training. Existing methods mainly follow three paradigms. Monolithic prompting is efficient but prone to missed mentions, boundary errors, and type confusion. Each-type prompting improves type-level focus but may produce overlapping or conflicting predictions, while multi-agent debate can resolve such conflicts at the cost of irrelevant context, redundant interactions, and high token overhead. To address these issues, we propose SMADE-IE, a sparse and evidence-driven multi-agent framework. An Adaptive Mode Selector routes simple inputs to a lightweight Global Extraction Mode and ambiguous inputs to a Type-Centric Extraction Mode based on sample complexity and relevant types. Cross-type conflicts are resolved by an Evidence-Driven Debate module that uses Toulmin-style arguments, external evidence scoring, Beta-based confidence updates, and early stopping. Experiments on nine benchmarks covering NER, RE, and JERE show that SMADE-IE improves average Partial F1 over the strongest baselines by 11.37, 3.83, and 14.46 points, respectively. Compared with the multi-agent baseline CrossAgentIE, SMADE-IE reduces token consumption by 85.1% on DocRED and 80.1% on CrossRE, demonstrating substantially higher inference efficiency. Code is available at https://github.com/Cppys/SMADE-IE.

Kenfeng Huang, Yi Cai, Xin Wu +2

School of Software Engineering, South China University of Technology, Guangzhou, China

Multi-Agent LLM Systems Multi-Agent Debate LLM Information Extraction Efficient Language Model Inference

Jun 3, 2026cs.CL

RAMPART: Registry-based Agentic Memory with Priority-Aware Runtime Transformation

RAMPART is a compile-time memory model and pure in-RAM block registry for LLM-based agents. Context assembly is a programmable runtime operation where content is compiled from a structured registry under explicit policy for ordering, inclusion, and eviction. Five composable primitives (promote, gate, write, evict, rollback) act on named addressable blocks before compilation at zero prompt-token cost. Provenance tags and non-evictable authorship flags implement a permissioned memory model with block-level ownership. Controlled probes with Qwen3-8B Q4 show that compile-time placement and the structural relationship between blocks and the task query affect task success, with the cliff falling at roughly the seventh block position when the task follows the registry and the twelfth when it precedes. Grouping the critical block with content-adjacent neighbours and promoting the group as a unit lifts task success by tens of percentage points at positions where single-block placement fails. Cross-model replication on Qwen2.5-7B, Llama-3.1-8B, Mistral-7B-v0.3, and Qwen3-14B shows the content-priming effect appears at the same absolute positions across families, with magnitude varying with model strength. Block grouping raises Mistral's mean pass rate roughly fivefold at the hardest registry size, and a smaller model with the intervention can outperform a larger model without it in the mid-registry zone. Relevance gating reduces prompt cost by 67.8% while recovering 83% of the promoted-condition success rate. Schema eviction produces 0% invocations against 100% with the schema present, a property policy-based approaches cannot guarantee by construction. Shared-registry coordination reduces inter-agent communication to a method call at zero coordination token cost.

Nikodem Tomczak

Thulge Labs, Singapore

Multi-Agent LLM Systems LLM Agent Memory Position Bias Agent Memory Management

Jun 3, 2026cs.AI

Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection

Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, but their reliable deployment remains challenging in high-stakes industrial scenarios. Industrial anomaly detection (IAD) is essential for manufacturing quality, safety, and efficiency, yet existing LLM-based IAD agents mainly focus on execution while under-exploiting strategy formulation. Consequently, they struggle to handle heterogeneous modalities in a unified and cost-effective manner. Inspired by the DMAIC quality-management framework, we propose DMAIC-IAD (DMAIC-inspired Agentic Industrial Anomaly Detection), a "Plan First, Judge Later" multi-agent system that aligns LLM agents with structured industrial problem-solving. DMAIC-IAD distills heterogeneous references into standardized operating procedures (SOPs) before strategy generation, and introduces a pre-trained execution-free judge model to rank candidate strategies without costly runtime trials. Extensive experiments across four modalities show that DMAIC-IAD improves average detection performance over applicable agentic baselines by 37.76%.

Yongzi Yu, Ao Li, Le Wang +4

1The Hong Kong University of Science and Technology (Guangzhou) · 2The Hong Kong University of Science and Technology · 3Shanghai University of Finance and Economics +2

Multi-Agent LLM Systems LLM Agent Orchestration Industrial Anomaly Detection LLM Agent Planning

Jun 3, 2026cs.IR

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning

Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories. Standard retrieval-augmented generation reduces this problem to top-

K

chunk retrieval, but such passive access can discard relevant evidence before reasoning begins, especially when relevance depends on broader context. We propose HMARS, a hierarchical multi-agent memory system that treats long contexts as managed memory rather than a flat retrieval corpus. Sub-agents maintain grounded access to bounded memory regions, mid-agents manage regional context and provide query-specific coordination, and a frontier model performs final reasoning over retrieved evidence pages. To evaluate this view, we construct two diagnostic benchmarks targeting evidence breadth and context-dependent relevance. Across long-document and multi-turn memory tasks, HMARS achieves the best overall performance against retrieval, reranking, full-context, graph-based, and agentic long-context baselines. Evidence coverage analysis further shows that its gains come from retrieving the required supporting evidence more completely, rather than merely changing the final answer prompt.

Zeju Li, Ziyang Zheng, Yizhou Zhou +1

The Chinese University of Hong Kong · Independent Researcher

Agent Memory Multi-Agent LLM Systems Long-Context Inference Memory-Augmented Agents

Jun 3, 2026cs.AI

AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning

We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning. Unlike centralized frameworks that tightly couple agent rollouts with model optimization, AgentJet adopts a decoupled multi-node architecture in which swarm server nodes host trainable models and run optimization on GPU clusters, whereas swarm client nodes execute arbitrary agents on arbitrary devices. This design provides capabilities that are difficult to support in centralized frameworks: (1) heterogeneous multi-model reinforcement learning, enabling the training of heterogeneous multi-agent teams with multiple LLM as brains; (2) multi-task cocktail training with isolated agent runtimes; (3) fault-tolerant execution that prevents external environment failures from interrupting the training process; and (4) live code iteration, which allows agents to be edited during training by replacing swarm client nodes. To support efficient RL in multi-model, multi-turn, and multi-agent settings, AgentJet introduces a context tracking module with timeline merging, which consolidates redundant context and achieves a 1.5-10x training speedup. Finally, AgentJet introduces an automated research system that takes a research topic as input and autonomously conducts long-horizon, multi-day RL studies on large-scale clusters. By leveraging the swarm architecture, this system reproduces key exploratory workflows of RL researchers without human intervention during execution.

Qingxu Fu, Boyin Liu, Shuchang Tao +2

Tongyi Lab, Alibaba Group

Multi-Agent LLM Systems Agentic RL Reinforcement Learning Distributed RL LLM Agent Training

Jun 3, 2026cs.MA

Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems

LLM-based agents are increasingly deployed in workflows where generated outputs may directly trigger state-changing actions. This creates an execution-boundary problem: proposed actions must be governed before they are executed. We study this problem through economically consequential multi-agent interactions and argue that deployment-grade agent systems should separate proposal generation from environment-facing execution. To operationalize this principle, we introduce the Organizational Control Layer (OCL), a model-agnostic governance infrastructure that intercepts generated actions before execution through policy enforcement and escalation, without modifying the underlying LLM generator. We evaluate OCL on adversarial buyer--seller negotiation environments adapted from AgenticPay. Across multiple frontier LLM backends, OCL reduces unsafe executions from 88% to near-zero while increasing valid success from 12% to 96%. Results further reveal a safety--utility tradeoff: strict governance improves compliance and reliability against policy and constraint violations, but can reduce flexibility in tightly constrained markets. These findings suggest that deployment-grade LLM agent systems require explicit governance at the boundary between language generation and executable actions. The source code is available at: https://github.com/SHITIANYU-hue/amai_ocl

Tianyu Shi, Yang Mo, Yiou Liu +6

McGill · Purdue · UNSW +3

Multi-Agent LLM Systems AI Agent Governance LLM Agent Safety

Jun 2, 2026cs.AI

Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal

Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue that this objective is insufficient for value-laden tasks, where disagreement may reflect genuine normative uncertainty rather than agent error. Building on prior work on reasoning-trace disagreement in human-AI collaborative moderation, we propose a knowledge-representation layer in which reasoning traces and agent decisions are abstracted into symbolic disagreement states. Given agents producing explicit reasoning traces and binary decisions, we distinguish four states according to reasoning similarity and conclusion agreement: convergent agreement, divergent agreement, convergent disagreement and divergent disagreement. These states support defeasible strategic routing rules. We instantiate the framework in content moderation and argue that disagreement-aware routing provides a bridge between sub-symbolic LLM deliberation and symbolic knowledge representation for multi-agent strategic reasoning.

Michał Wawer, Jarosław A. Chudziak

Laboratory of The New Ethos Warsaw University of Technology, Warsaw, Poland · Institute of Computer Science Faculty of Electronics and Information Technology Warsaw University of Technology, Warsaw, Poland

Multi-Agent LLM Systems Multi-Agent Reasoning LLM Agent Routing

Jun 2, 2026cs.HC

From 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members

With the growing prevalence of modern ubiquitous computing technologies, multi-modal tracking systems hold promise for providing timely awareness and reassurance to stakeholders such as remote family members (RFMs) of older adults, who play a central role in care coordination. However, combining heterogeneous data streams into high-level, meaningful content - such as retrospective summaries - remains challenging. While recent work has demonstrated the promise of large language models (LLMs) for interpreting multi-modal tracking data, less attention has been given to generating narrative accounts for stakeholders like RFMs, who possess rich personal knowledge of older adults and strong emotional responsibility, yet have limited visibility into their daily lives and limited capacity for caregiving. In this work, we explore how LLMs can be used to generate retrospective summaries from multi-modal tracking data for RFMs of older adults. We leveraged and customized an existing system, Vital Insight, to generate initial summaries on different dates and data availability scenarios as technology probes, and conducted interviews with 11 RFMs to gather feedback. Based on these insights, we redesigned the system into a multi-layer, multi-agent, insight-driven summary approach that builds from objective statistics and descriptions to enriched, context-aware narratives. We then compared the redesigned summaries with the initial versions through a survey with the same 11 RFMs and found significant improvements in satisfaction, perceived helpfulness, trust, and willingness to receive the summaries. We conclude by presenting design implications for AI-generated summaries for RFMs and broader contexts, emphasizing the need to support RFMs' sensemaking shift from simply presenting ''What'' data were collected, to explaining ''How'' is my loved one doing and ''Why''.

Jiachen Li, Reina Szeyi Chan, Akshat Choube +3

Northeastern University, Boston, MA, USA

Multi-Agent LLM Systems Healthcare Text Summarization

Jun 2, 2026cs.CL

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs

Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data. Existing approaches often struggle to capture complex inter-document relationships, rely heavily on large amounts of labeled data for supervised training, or exhibit limited generalization across domains and languages. To address these limitations, we present a training-free mixture-of-agents framework for MDS that leverages the complementary strengths of large language models (LLMs) and knowledge graphs. Our approach decomposes summarization into specialized agent tasks: extractive selection, knowledge-aware abstraction, and iterative refinement, each operating without task-specific fine-tuning. We unify their outputs using a multi-perspective consistency mechanism guided by LLMs. Experiments across four datasets in English and Vietnamese demonstrate state-of-the-art or competitive performance, validating the effectiveness and adaptability of our modular design.

Cuong Vuong Tuan, Trang Mai Xuan, Tien-Cuong Nguyen +2

Faculty of Artificial Intelligence and Data Science, Phenikaa University, Duong Noi, Ha Noi, Viet Nam · VNPT AI, VNPT Group, Ha Noi, Viet Nam · MobiFone Research and Development Center, MobiFone Corporation, Ha Noi, Viet Nam +1

Multi-Agent LLM Systems Text Summarization