Multi-Agent LLM Systems

LLM: Large Language Model

Ask about this topic

Overview

Multi-agent large language model systems study how multiple language-model agents can divide work, share information, and combine decisions on tasks such as reasoning, coding, research, and planning. Common designs use specialized roles, debate or review loops, retrieval-augmented generation, shared memory, and orchestrators that route tasks or choose communication links; some systems also learn prompts, workflows, or policies through reinforcement learning. Researchers evaluate these approaches on benchmarks for math, question answering, software, and tool use, as well as in longer-running simulations and domain applications. A central open tension is that collaboration can improve accuracy and verification, but may also add latency and token costs or spread errors, bias, and unsafe instructions, so gains depend on the task, architecture, and quality of coordination.

Latest papers

CardsList

1,050 papers142 papers in the last four weeks, up 35% on the four weeks before. 0.8% of all new papers.

Mar 30, 2026

A Multi-Agent Rhizomatic Pipeline for Non-Linear Literature Analysis

Systematic literature reviews in the social sciences overwhelmingly follow arborescent logics -- hierarchical keyword filtering, linear screening, and taxonomic classification -- that suppress the lateral connections, ruptures, and emergent patterns characteristic of complex research landscapes. This research note presents the Rhizomatic Research Agent (V3), a multi-agent computational pipeline grounded in Deleuzian process-relational ontology, designed to conduct non-linear literature analysis through 12 specialized agents operating across a seven-phase architecture. The system was developed in response to the methodological groundwork established by (Narayan2023), who employed rhizomatic inquiry in her doctoral research on sustainable energy transitions but relied on manual, researcher-driven exploration. The Rhizomatic Research Agent operationalizes the six principles of the rhizome -- connection, heterogeneity, multiplicity, asignifying rupture, cartography, and decalcomania -- into an automated pipeline integrating large language model (LLM) orchestration, dual-source corpus ingestion from OpenAlex and arXiv, SciBERT semantic topography, and dynamic rupture detection protocols. Preliminary deployment demonstrates the system's capacity to surface cross-disciplinary convergences and structural research gaps that conventional review methods systematically overlook. The pipeline is open-source and extensible to any phenomenon zone where non-linear knowledge mapping is required.

Julio C. Serrano, Joonas Kevari, Rumy Narayan

University of Vaasa, School of Management, Vaasa, Finland · LUT University, School of Engineering, Lahti, Finland

AI-Assisted Scientific ResearchMulti-Agent LLM Systems
AskPDF
Mar 30, 2026

GEMS: Agent-Native Multimodal Generation with Memory and Skills

Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose GEMS (Agent-Native Multimodal GEneration with Memory and Skills), a framework that pushes beyond the inherent limitations of foundational models on both general and downstream tasks. GEMS is built upon three core components. Agent Loop introduces a structured multi-agent framework that iteratively improves generation quality through closed-loop optimization. Agent Memory provides a persistent, trajectory-level memory that hierarchically stores both factual states and compressed experiential summaries, enabling a global view of the optimization process while reducing redundancy. Agent Skill offers an extensible collection of domain-specific expertise with on-demand loading, allowing the system to effectively handle diverse downstream applications. Across five mainstream tasks and four downstream tasks, evaluated on multiple generative backends, GEMS consistently achieves significant performance gains. Most notably, it enables the lightweight 6B model Z-Image-Turbo to surpass the state-of-the-art Nano Banana 2 on GenEval2, demonstrating the effectiveness of agent harness in extending model capabilities beyond their original limits.

Zefeng He, Siyuan Huang, Xiaoye Qu +4

Shanghai AI Laboratory · Nanjing University · Shanghai Jiao Tong University +1

Multimodal GenerationMemory-Augmented Language Model AgentsMulti-Agent LLM SystemsLLM Agent Skill Learning
AskPDF
Mar 30, 2026

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Five Production LLMs

Multi-agent LLM systems now read documents, web pages and tool results on behalf of users, yet their resistance to prompt injection is usually reported as one number: did the attack succeed? We introduce a kill-chain canary method that plants a unique token in every injected payload and records the furthest of four stages it reaches (Exposed -> Persisted -> Relayed -> Executed), across 950 runs, five production LLMs, six attack surfaces, and five defense conditions. Exposure was 100% among runs that called the tool; the outcomes differ downstream. Claude Haiku 4.5 and Claude Sonnet 4.5 executed none of their 164 text-surface attacks, and in the text relay the canary token never appeared in a memory write (0/40); GPT-4o-mini executed 53% of its attacks. Four findings follow. (1) A Claude writer kept the canary token out of shared memory in every relay run we report; one cross-model pairing (Claude writer, GPT-4o-mini reader, n = 3) is consistent with this protecting the reader, and other pairings were not tested. (2) As readers, the Claude models executed 0/40 raw pre-seeded injections, but Claude Haiku 4.5 executed 2/3 injections relayed by GPT-4o-mini; whether relayed injections are harder to refuse than raw ones is an open question. (3) DeepSeek Chat went from 0/24 on pre-seeded memory to 8/8 on tool results, scenarios that also differ in task and payload format; white-text PDF payloads, invisible on the rendered page, succeeded at least as often as visible ones. (4) pi_detector and write_filter failed on channels they do not inspect, spotlighting failed on content it wraps, and write_filter blocked the PDF relay but not the text relay, a difference we cannot explain. Code and run logs are publicly released: https://github.com/KevinChunye/prompt_injection

Haochuan Kevin Wang, Zechen Zhang

Massachusetts Institute of Technology · University of Chicago

Multi-Agent LLM SystemsLanguage Model Safety EvaluationPrompt Injection DefensePrompt Injection Attacks on LLMsPrompt Injection Attacks on AI AgentsPrompt Injection Detection
AskPDF
Mar 30, 2026

ViviDoc: Generating Interactive Documents through Human-Agent Collaboration

Interactive documents help readers engage with complex ideas through dynamic visualization, interactive animations, and exploratory interfaces. However, creating such documents remains costly, as it requires both domain expertise and web development skills. Recent Large Language Model (LLM)-based agents can automate content creation, but directly applying them to interactive document generation often produces outputs that are difficult to control. To address this, we present ViviDoc, to the best of our knowledge the first work to systematically address interactive document generation. ViviDoc introduces a multi-agent pipeline (Planner, Styler, Executor, Evaluator). To make the generation process controllable, we provide three levels of human control: (1) the Document Specification (DocSpec) with SRTC Interaction Specifications (State, Render, Transition, Constraint) for structured planning, (2) a content-aware Style Palette for customizing writing and interaction styles, and (3) chat-based editing for iterative refinement. We also construct ViviBench, a benchmark of 101 topics derived from real-world interactive documents across 11 domains, along with a taxonomy of 8 interaction types and a 4-dimensional automated evaluation framework validated against human ratings (Pearson r > 0.84). Experiments show that ViviDoc achieves the highest content richness and interaction quality in both automated and human evaluation. A 12-person user study confirms that the system is easy to use, provides effective control over the generation process, and produces documents that satisfy users.

Yinghao Tang, Yupeng Xie, Yingchaojie Feng +4

State Key Lab of CAD&CG, Zhejiang University · HKUST(GZ) · National University of Singapore +2

Human-AI Co-CreationLanguage Model Generation EvaluationMulti-Agent LLM SystemsLLM Agent Orchestration
AskPDF
Mar 30, 2026

Beyond Message Passing: A Semantic View of Agent Communication Protocols

Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across heterogeneous environments. This work presents a human-inspired perspective on this emerging landscape by organizing agent communication into three layers: communication, syntactic, and semantic. Under this framework, we systematically analyze 18 representative protocols and compare how they support reliable transport, structured interaction, and meaning-level coordination. Our analysis shows a clear imbalance in current protocol design. Most protocols provide increasingly mature support for transport, streaming, schema definition, and lifecycle management, but offer limited protocol-level mechanisms for clarification, context alignment, and verification. As a result, semantic responsibilities are often pushed into prompts, wrappers, or application-specific orchestration logic, creating hidden interoperability and maintenance costs. To make this gap actionable, we further identify major forms of technical debt in today's protocol ecosystem and distill practical guidance for selecting protocols under different deployment settings. We conclude by outlining a research agenda for interoperable, secure, and semantically robust agent ecosystems that move beyond message passing toward shared understanding.

Dun Yuan, Fuyuan Lyu, Ye Yuan +11

Agent Communication ProtocolsMulti-Agent CommunicationMulti-Agent LLM Systems
AskPDF
Mar 29, 2026

Emergent Risks in Generative Multi-Agent Systems

Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies.

Yue Huang, Yu Jiang, Wenjie Wang +12

University of Notre Dame · LMU Munich · University of Washington +7

Multi-Agent LLM SystemsMulti-Agent SystemsLLM Agent SafetyMulti-Agent System SecurityEmergent Behavior in Multi-Agent Systems
AskPDF
Mar 29, 2026

LUMEN: Cost-Transparent Multi-Agent Pipeline for Automated Systematic Review and Meta-Analysis

Systematic reviews and meta-analyses (SR/MA) remain the gold standard for evidence synthesis, yet completing one typically requires 67 weeks and substantial expert effort. Recent large language model (LLM) systems have demonstrated strong performance on individual SR phases - screening (otto-SR: 96.7% sensitivity), extraction (Gartlehner et al.: 91.0% accuracy), and search (TrialMind: 0.83 recall) - but no study has reported what it actually costs to run an end-to-end pipeline, how cost distributes across phases, or how architectural choices affect the cost-quality trade-off. We present LUMEN, an open-source multi-agent pipeline that automates six SR/MA phases using 11 specialized LLM agents with deliberate model routing. We evaluate LUMEN on seven datasets: five self-conducted domain reviews (psychiatry, psychology, surgery, vaccinology, cardiology) and two SYNERGY screening benchmarks. Across 13 ground-truth-comparable outcomes, LUMEN achieves 100% directional agreement with published meta-analyses, with effect sizes within 1% for homogeneous study designs. The primary contribution is the first empirical cost and operational characterization of such a pipeline: a complete review costs 19 to 29 USD (median 22.65 USD), with title-abstract screening and data extraction together dominating expenditure. A three-arm extraction ablation reveals a phase-dependent architecture reversal: multi-agent design hurts screening but is essential for extraction, producing 5.7x more poolable analyses than single-model alternatives while eliminating clinically dangerous direction errors. A two-dataset screening benchmark demonstrates that model ranking is domain-dependent and not transferable across review topics. All code and cost logs are publicly available.

Yen-Hsun Huang, Yu-Shiou Lin

Department of Education, Taipei Veterans General Hospital, Taipei, Taiwan · Department of Psychiatry, Taipei Veterans General Hospital, Taipei, Taiwan

Systematic Review AutomationAI-Assisted Scientific ResearchMulti-Agent LLM SystemsCost-Aware InferenceLLM Evaluation
AskPDF
Mar 29, 2026

InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection

Introspection is central to identity construction and future planning, yet most digital tools approach the self as a unified entity. In contrast, Dialogical Self Theory (DST) views the self as composed of multiple internal perspectives, such as values, concerns, and aspirations, that can come into tension or dialogue with one another. Building on this view, we designed InnerPond, a research probe in the form of a multi-agent system that represents these internal perspectives as distinct LLM-based agents for introspection. Its design was shaped through iterative explorations of spatial metaphors, interaction scaffolding, and conversational orchestration, culminating in a shared spatial environment for organizing and relating multiple inner perspectives. In a user study with 17 young adults navigating career choices, participants engaged with the probe by co-creating inner voices with AI, composing relational inner landscapes, and orchestrating dialogue as observers and mediators, offering insight into how such systems could support introspection. Overall, this work offers design implications for AI-supported introspection tools that enable exploration of the self's multiplicity.

Hayeon Jeon, Dakyeom Ahn, Sunyu Pang +5

hci+d lab. Seoul National University Seoul, Republic of Korea · Department of Communication Seoul National University Seoul, Republic of Korea

Language Model IntrospectionMulti-Agent LLM Systems
AskPDF
Mar 28, 2026

A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search

Ad hoc dataset search requires matching underspecified natural-language queries against sparse, heterogeneous metadata records, a task where typical lexical or dense retrieval alone falls short. We reposition dataset search as a software-architecture problem and propose a bounded, auditable reference architecture for agentic hybrid retrieval that combines BM25 lexical search with dense-embedding retrieval via reciprocal rank fusion (RRF), orchestrated by a large language model (LLM) agent that repeatedly plans queries, evaluates the sufficiency of results, and reranks candidates. To reduce the vocabulary mismatch between user intent and provider-authored metadata, we introduce an offline metadata augmentation step in which an LLM generates pseudo-queries for each dataset record, augmenting both retrieval indexes before query time. Two architectural styles are examined: a single ReAct agent and a multi-agent horizontal architecture with Feedback Control. Their quality-attribute tradeoffs are analyzed with respect to modifiability, observability, performance, and governance. An evaluation framework comprising seven system variants is defined to isolate the contribution of each architectural decision. The architecture is presented as an extensible reference design for the software architecture community, incorporating explicit governance tactics to bound and audit nondeterministic LLM components.

Riccardo Terrenzi, Phongsakon Mark Konrad, Tim Lukas Adam +1

Centre for Industrial Software University of Southern Denmark Alsion 2, Sønderborg, 6400, Denmark

Agentic RetrievalInformation RetrievalHybrid RetrievalMulti-Agent LLM Systems
AskPDF
Mar 28, 2026

MediHive: A Decentralized Agent Collective for Medical Reasoning

Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems often falter on complex, interdisciplinary problems requiring robust handling of uncertainty and conflicting evidence. Multi-agent systems (MAS) leveraging LLMs enable collaborative intelligence, but prevailing centralized architectures suffer from scalability bottlenecks, single points of failure, and role confusion in resource-constrained environments. Decentralized MAS (D-MAS) promise enhanced autonomy and resilience via peer-to-peer interactions, but their application to high-stakes healthcare domains remains underexplored. We introduce MediHive, a novel decentralized multi-agent framework for medical question answering that integrates a shared memory pool with iterative fusion mechanisms. MediHive deploys LLM-based agents that autonomously self-assign specialized roles, conduct initial analyses, detect divergences through conditional evidence-based debates, and locally fuse peer insights over multiple rounds to achieve consensus. Empirically, MediHive outperforms single-LLM and centralized baselines on MedQA and PubMedQA datasets, attaining accuracies of 84.3% and 78.4%, respectively. Our work advances scalable, fault-tolerant D-MAS for medical AI, addressing key limitations of centralized designs while demonstrating superior performance in reasoning-intensive tasks.

Xiaoyang Wang, Christopher C. Yang

College of Computing and Informatics, Drexel University, Philadelphia, PA 19104, USA

Multi-Agent LLM SystemsMedical QAMedical ReasoningShared-Memory Multi-Agent SystemsMulti-Agent Debate
AskPDF
Mar 28, 2026

When Verification Hurts: Asymmetric Effects of Multi-Agent Feedback in Logic Proof Tutoring

Large language models (LLMs) are increasingly used for automated tutoring, but their reliability in structured symbolic domains remains unclear. We study step-level feedback for propositional logic proofs, which require precise symbolic reasoning aligned with a learner's current proof state. We introduce a knowledge-graph-grounded benchmark of 516 unique proof states with step-level annotations and difficulty metrics. Unlike prior tutoring evaluations that rely on model self-assessment or binary correctness, our framework enables fine-grained analysis of feedback quality against verified solution paths. We evaluate three role-specialized pipelines with varying solution access: Tutor (partial solution access), Teacher (full derivation access), and Judge (verification of Tutor feedback). Our results reveal a striking asymmetry: verification improves outcomes when upstream feedback is error-prone (<70% accuracy), but degrades performance by 4-6 percentage points through over-specification when feedback is already reliable (>85%). Critically, we identify a shared complexity ceiling; no model or pipeline reliably succeeds on proof states exceeding complexity 4-5. These findings challenge the assumption that adding verifiers or richer context universally improves tutoring, motivating adaptive, difficulty-aware architectures that route problems by estimated complexity and upstream reliability.

Tahreem Yasir, Sutapa Dey Tithi, Benyamin Tabarsi +7

DK · North Carolina State University Raleigh, NC, USA

Intelligent Tutoring SystemsLLM EvaluationLLM ReliabilityMulti-Agent LLM SystemsLogical Reasoning
AskPDF
Mar 28, 2026

Story2Proposal: A Scaffold for Structured Scientific Paper Writing

Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment.

Zhuoyang Qian, Wei Shi, Xu Lin +19

AgentAlpha Team.

Long-Form Document GenerationAI-Assisted Scientific ResearchStructured Output GenerationMulti-Agent LLM Systems
AskPDF
Mar 27, 2026

On the Reliability Limits of LLM-Based Multi-Agent Planning

This technical note studies the reliability limits of LLM-based multi-agent planning as a delegated decision problem. We model the LLM-based multi-agent architecture as a finite acyclic decision network in which multiple stages process shared model-context information, communicate through language interfaces with limited capacity, and may invoke human review. We show that, without new exogenous signals, any delegated network is decision-theoretically dominated by a centralized Bayes decision maker with access to the same information. In the common-evidence regime, this implies that optimizing over multi-agent directed acyclic graphs under a finite communication budget can be recast as choosing a budget-constrained stochastic experiment on the shared signal. We also characterize the loss induced by communication and information compression. Under proper scoring rules, the gap between the centralized Bayes value and the value after communication admits an expected posterior divergence representation, which reduces to conditional mutual information under logarithmic loss and to expected squared posterior error under the Brier score. These results characterize the fundamental reliability limits of delegated LLM planning. Experiments with LLMs on a controlled problem set further demonstrate these characterizations.

Ruicheng Ao, Siyang Gao, David Simchi-Levi

Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA 02139. · Department of Systems Engineering, City University of Hong Kong, Kowloon, Hong Kong. · Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, MA 02139. +1

LLM Agent ReliabilityMulti-Agent LLM SystemsMulti-Agent PlanningMulti-Agent Communication
AskPDF
Mar 27, 2026

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these dimensions separately, their interaction under realistic cost constraints remains unclear. In this paper, we introduce a conceptual scaling view of multi-agent systems that jointly considers team size and lifelong learning ability, and we study how memory design shares this landscape. To this end, we propose LLMA-Mem, a lifelong memory framework for LLM multi-agent systems under flexible memory topologies. We evaluate LLMA-Mem on MultiAgentBench across coding, research, and database environments. Empirically, LLMA-Mem consistently improves long-horizon performance over baselines while reducing cost. Our analysis further reveals a non-monotonic scaling landscape: larger teams do not always produce better long-term performance, and smaller teams can outperform larger ones when memory better supports the reuse of experience. These findings position memory design as a practical path for scaling multi-agent systems more effectively and more efficiently over time.

Shanglin Wu, Yuyang Luo, Yueqing Liang +4

Emory University · Illinois Institute of Technology · University of Notre Dame +1

Multi-Agent LLM SystemsMulti-Agent SystemsMemory-Augmented Language Model AgentsLifelong Learning Agents
AskPDF
Mar 27, 2026

Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents

As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspecified instructions that lack crucial context. While human developers naturally resolve underspecification by asking clarifying questions, current agents are largely optimized for autonomous execution. In this work, we systematically evaluate the clarification-seeking abilities of LLM agents on an underspecified variant of SWE-bench Verified. We propose an uncertainty-aware multi-agent scaffold that decouples underspecification detection from code execution. Across both proprietary and open-weight frontier LLMs, our scaffold achieves a 69.40% task resolve rate, significantly outperforming a standard single-agent setup and closing the performance gap with agents operating on fully specified instructions. Furthermore, we find that the multi-agent system exhibits well-calibrated information-seeking behavior, conserving queries on simple tasks while proactively seeking information on more complex issues. These findings indicate that current models can be turned into proactive collaborators, where agents independently recognize when to ask questions to elicit missing information in real-world, underspecified tasks.

Nicholas Edwards, Sebastian Schuster

Faculty of Computer Science, University of Vienna, Vienna, Austria · UniVie Doctoral School Computer Science, University of Vienna, Vienna, Austria

Multi-Agent LLM SystemsAI Coding AgentsLLM AgentsLLM Uncertainty Estimation
AskPDF
Mar 27, 2026

ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings from symptoms to diagnoses, failing to capture the iterative, hypothesis-driven reasoning inherent in human clinicians. To bridge this gap, we introduce ClinicalAgents, a novel multi-agent framework designed to simulate the cognitive workflow of expert clinicians. Unlike rigid sequential chains, ClinicalAgents employs a dynamic orchestration mechanism modeled as a Monte Carlo Tree Search (MCTS) process. This allows an orchestrator to iteratively generate hypotheses, actively verify evidence, and trigger backtracking when critical information is missing. The foundation of this framework is a Dual-Memory architecture: a mutable working memory that maintains the evolving patient state for context-aware reasoning, and a static experience memory that retrieves clinical guidelines and historical cases via an active feedback loop. Extensive experiments demonstrate that ClinicalAgents achieves the best performance among evaluated baselines, significantly enhancing both diagnostic accuracy and explainability compared to strong single-agent and multi-agent baselines. Our code is released at https://github.com/ZhuohanGe/ClinicalAgents-Code.

Zhuohan Ge, Haoyang Li, Yubo Wang +3

The Hong Kong Polytechnic University, Hong Kong SAR, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China

Clinical Decision-MakingMulti-Agent LLM SystemsMedical DiagnosisClinical ReasoningMemory-Augmented Language Model AgentsLLM Agent Planning
AskPDF
Mar 27, 2026

SkinGPT-X: A Self-Evolving Collaborative Multi-Agent System for Transparent and Trustworthy Dermatological Diagnosis

While recent advancements in Large Language Models have significantly advanced dermatological diagnosis, monolithic LLMs frequently struggle with fine-grained, large-scale multi-class diagnostic tasks and rare skin disease diagnosis owing to training data sparsity, while also lacking the interpretability and traceability essential for clinical reasoning. Although multi-agent systems can offer more transparent and explainable diagnostics, existing frameworks are primarily concentrated on Visual Question Answering and conversational tasks, and their heavy reliance on static knowledge bases restricts adaptability in complex real-world clinical settings. Here, we present SkinGPT-X, a multimodal collaborative multi-agent system for dermatological diagnosis integrated with a self-evolving dermatological memory mechanism. By simulating the diagnostic workflow of dermatologists and enabling continuous memory evolution, SkinGPT-X delivers transparent and trustworthy diagnostics for the management of complex and rare dermatological cases. To validate the robustness of SkinGPT-X, we design a three-tier comparative experiment. First, we benchmark SkinGPT-X against four state-of-the-art LLMs across four public datasets, demonstrating its state-of-the-art performance with a +9.6% accuracy improvement on DDI31 and +13% weighted F1 gain on Dermnet over the state-of-the-art model. Second, we construct a large-scale multi-class dataset covering 498 distinct dermatological categories to evaluate its fine-grained classification capabilities. Finally, we curate the rare skin disease dataset, the first benchmark to address the scarcity of clinical rare skin diseases which contains 564 clinical samples with eight rare dermatological diseases. On this dataset, SkinGPT-X achieves a +9.8% accuracy improvement, a +7.1% weighted F1 improvement, a +10% Cohen's Kappa improvement.

Zhangtianyi Chen, Yuhao Shen, Florensia Widjaja +6

School of Data Science, The Chinese University of Hong Kong, Shenzhen · Department of Dermatology, Tianjin Institute of Integrative Dermatology, Tianjin Academy of Traditional Chinese Medicine Affiliated Hospital, Tianjin 300120, China · Department of Dermatology, Beijing AnZhen Hospital, Capital Medical University, Beijing 100029, China..

Medical DiagnosisDermatologyMulti-Agent LLM SystemsSkin Lesion ClassificationMedical VLMsExplainable Medical Image Analysis+1
AskPDF
Mar 25, 2026

Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems

Domain experts possess tacit knowledge that they cannot easily articulate through explicit specifications. When experts modify AI-generated artifacts by correcting terminology, restructuring arguments, and adjusting emphasis, these edits reveal domain understanding that remains latent in traditional prompt-based interactions. Current systems treat such modifications as endpoint corrections rather than as implicit specifications that could reshape subsequent reasoning. We propose context-mediated domain adaptation, a paradigm where user modifications to system-generated artifacts serve as implicit domain specification that reshapes LLM-powered multi-agent reasoning behavior. Through our system Seedentia, a web-based multi-agent framework for sense-making, we demonstrate bidirectional semantic links between generated artifacts and system reasoning. Our approach enables specification bootstrapping where vague initial prompts evolve into precise domain specifications through iterative human-AI collaboration, implicit knowledge transfer through reverse-engineered user edits, and in-context learning where agent behavior adapts based on observed correction patterns. We present results from an evaluation with domain experts who generated and modified research questions from academic papers. Our system extracted 46 domain knowledge entries from user modifications, demonstrating the feasibility of capturing implicit expertise through edit patterns, though the limited sample size constrains conclusions about systematic quality improvements.

Anton Wolter, Leon Haag, Vaishali Dhanoa +1

Aarhus University, Denmark · Maastricht University, Netherlands · TU Wien, Austria

Human-AI InteractionDomain Adaptation for LLMsMulti-Agent LLM SystemsIn-Context Learning
AskPDF
Mar 25, 2026

AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model

Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they navigate. They process papers sequentially, propose ideas without structured gap analysis, and lack mechanisms for agents to verify, challenge, or refine each other's findings. We present AI-Supervisor, a multi-agent orchestration framework where specialized agents provide end-to-end AI research supervision driven by human interests -- from literature review through gap discovery, method development, evaluation, and paper writing -- through autonomous exploration and self-correcting updates of research knowledge. Unlike sequential pipelines, AI-Supervisor maintains a continuously evolving Research World Model, implemented as a Knowledge Graph, that captures methods, benchmarks, known limitations, and unexplored gaps, serving as shared memory across all agents and enabling agents to explore and build upon a structured understanding of the research landscape. The framework introduces three architectural contributions: (1) structured gap discovery that decomposes methods into core modules, validates their performance across benchmarks, and maps the specific gaps each module creates; (2) self-correcting discovery loops that probe why modules succeed on certain problems and fail on others, whether benchmarks carry hidden biases, and whether evaluation protocols remain adequate for emerging challenges; and (3) self-improving development loops governed by cross-domain mechanism search that iteratively targets failing modules by finding solutions from other scientific fields. All agents operate under a consensus mechanism where independent findings are corroborated before being committed to the Research World Model.

Yunbo Long

Autonomous Research AgentsAI Agents for Scientific DiscoveryMulti-Agent LLM Systems
AskPDF
Mar 25, 2026

From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring

Monolithic Large Language Models (LLMs) used in educational dialogue often behave as "black boxes," where pedagogical decisions are implicit and difficult to audit, frequently violating instructional constraints by providing answers too early. We introduce the Ensemble of Specialized LLMS (ES-LLMS) architecture that separates decision-making from wording. Pedagogical actions are selected by a deterministic rules-based orchestrator coordinating specialized agents covering tutoring, assessment, feedback, scaffolding, motivation and ethics-guided by an interpretable Bayesian Knowledge Tracing (BKT) student model. An LLM renderer surface-realizes the chosen action in natural language. This design emphasizes reliability and controllability: constraints such as "attempt-before-hint" and hint caps are enforced as explicit rules, and the system logs per-turn agent traces and constraint checks. Validation of pedagogical quality via human expert reviewers (N=6) and a multi-LLM-as-Judge panel (six state-of-the-art models) showed that ES-LLMs were preferred in 91.7% and 79.2% of cases, respectively. The architecture significantly outperformed monolithic baselines across all seven dimensions, particularly in Scaffolding & Guidance, and Trust & Explainability. Furthermore, a Monte Carlo simulation (N=2,400) exposed a "Mastery Gain Paradox," where monolithic tutors inflated short-term performance through over-assistance. In contrast, ES-LLMs achieved 100% adherence to pedagogical constraints (e.g., attempt-before-hint) and a 3.3x increase in hint efficiency. Operationally, ES-LLMs reduced costs by 54% and latency by 22% by utilizing stateless prompts. We conclude that structural decoupling is essential for transforming stochastic models into trustworthy, verifiable and resource-efficient pedagogical agents.

Nizam Kadir

Singapore University of Technology and Design, Singapore 487372, Singapore

Intelligent Tutoring SystemsMulti-Agent LLM SystemsLLM ReliabilityLanguage Model Ensembles
AskPDF
Mar 25, 2026

AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents

Recent advances in large language models (LLMs) suggest strong potential for automating analog circuit design. Yet most LLM-based approaches rely on a single-model loop of generation, diagnosis, and correction, which favors succinct summaries over domain-specific insight and suffers from context attrition that erases critical technical details. To address these limitations, we propose AnalogAgent, a training-free agentic framework that integrates an LLM-based multi-agent system (MAS) with self-evolving memory (SEM) for analog circuit design automation. AnalogAgent coordinates a Code Generator, Design Optimizer, and Knowledge Curator to distill execution feedback into an adaptive playbook in SEM and retrieve targeted guidance for subsequent generation, enabling cross-task transfer without additional expert feedback, databases, or libraries. Across established benchmarks, AnalogAgent achieves 92% Pass@1 with Gemini and 97.4% Pass@1 with GPT-5. Moreover, with compact models (e.g., Qwen-8B), it yields a +48.8% average Pass@1 gain across tasks and reaches 72.1% Pass@1 overall, indicating that AnalogAgent substantially strengthens open-weight models for high-quality analog circuit design automation.

Zhixuan Bao, Zhuoyi Lin, Jiageng Wang +5

Nanyang Technological University Singapore · Institute for Infocomm Research Singapore · Institute of Microelectronics Singapore +2

Electronic Design AutomationLLM Agent Self-ImprovementMemory-Augmented Language Model AgentsMulti-Agent LLM Systems
AskPDF
Mar 24, 2026

Emergence of Fragility in LLM-based Social Networks: the Case of Moltbook

The rapid diffusion of large language models and the growth in their capability has enabled the emergence of online environments populated by autonomous AI agents that interact through natural language. These platforms provide a novel empirical setting for studying collective dynamics among artificial agents. In this paper we analyze the interaction network of Moltbook, a social platform composed entirely of LLM based agents, using tools from network science. The dataset comprises 39,924 users, 235,572 posts, and 1,540,238 comments collected through web scraping. We construct a directed weighted network in which nodes represent agents and edges represent commenting interactions. Our analysis reveals strongly heterogeneous connectivity patterns characterized by heavy tailed degree and activity distributions. At the mesoscale, the network exhibits a pronounced core periphery organization in which a very small structural core (0.9% of nodes) concentrates a large fraction of connectivity. Robustness experiments show that the network is relatively resilient to random node removal but highly vulnerable to targeted attacks on highly connected nodes, particularly those with high out degree. These findings indicate that the interaction structure of AI agent social systems may develop strong centralization and structural fragility, providing new insights into the collective organization of LLM native social environments.

Luca Sodano, Sofia Sciangula, Amulya Galmarini +1

School of Industrial Engineering, Intelligence, Complexity and Technology Lab (ICT Lab), LIUC - Università Cattaneo, Castellanza (Italy), 21053 · Intelligence, Complexity and Technology Lab (ICT Lab), LIUC - Università Cattaneo, Castellanza (Italy), 21053

Social Network AnalysisMulti-Agent LLM SystemsSocial Media AnalysisComputational Social ScienceLarge Language Model-Based Social SimulationAgentic AI
AskPDF
Mar 24, 2026

ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization

How should multi-agent systems be designed, and can that design knowledge be captured in a form that is inspectable, revisable, and transferable? We introduce ABSTRAL, a framework that treats MAS architecture as an evolving natural-language document, an artifact refined through contrastive trace analysis. Three findings emerge. First, we provide a precise measurement of the multi-agent coordination tax: under fixed turn budgets, ensembles achieve only 26% turn efficiency, with 66% of tasks exhausting the limit, yet still improve over single-agent baselines by discovering parallelizable task decompositions. Second, design knowledge encoded in documents transfers: topology reasoning and role templates learned on one domain provide a head start on new domains, with transferred seeds matching coldstart iteration 3 performance in a single iteration. Third, contrastive trace analysis discovers specialist roles absent from any initial design, a capability no prior system demonstrates. On SOPBench (134 bank tasks, deterministic oracle), ABSTRAL reaches 70% validation / 65.96% test pass rate with a GPT-4o backbone. We release the converged documents as inspectable design rationale.

Weijia Song, Jiashu Yue, Zhe Pang

Multi-Agent SystemsMulti-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent Coordination
AskPDF
Mar 24, 2026

Benchmarking Multi-Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost-Accuracy Tradeoffs and Production Scaling Strategies

The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments face fundamental architectural decisions with limited empirical guidance. We present a systematic benchmark comparing four multi-agent orchestration architectures: sequential pipeline, parallel fan-out with merge, hierarchical supervisor-worker and reflexive self-correcting loop. These are evaluated across five frontier and open-weight LLMs on a corpus of 10,000 SEC filings (10-K, 10-Q and 8-K forms). Our evaluation spans 25 extraction field types covering governance structures, executive compensation and financial metrics, measured along five axes: field-level F1, document-level accuracy, end-to-end latency, cost per document and token efficiency. We find that reflexive architectures achieve the highest field-level F1 (0.943) but at 2.3x the cost of sequential baselines, while hierarchical architectures occupy the most favorable position on the cost-accuracy Pareto frontier (F1 0.921 at 1.4x cost). We further present ablation studies on semantic caching, model routing and adaptive retry strategies, demonstrating that hybrid configurations can recover 89% of the reflexive architecture's accuracy gains at only 1.15x baseline cost. Our scaling analysis from 1K to 100K documents per day reveals non-obvious throughput-accuracy degradation curves that inform capacity planning. These findings provide actionable guidance for practitioners deploying multi-agent LLM systems in regulated financial environments.

Siddhant Kulkarni, Yukta Kulkarni

Department of Computer Science and Engineering, New York University, New York, NY 10012

Multi-Agent LLM SystemsLLM Agent OrchestrationDocument Information ExtractionLLM EvaluationFinancial Services
AskPDF
Mar 23, 2026

Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking

We present an AI Co-Scientist framework that closes the research loop for the production search-ranking system of a large online travel platform -- pairing LLM agents with direct cloud-compute access so that idea generation, code implementation, GPU experimentation, and result analysis iterate end-to-end with a human scientist in the loop. The framework uses a hybrid agent architecture: single-LLM agents handle routine work, while multi-LLM consensus (GPT-5.2, Gemini Pro 3, Claude Opus 4.5) is invoked for higher-stakes decisions. On the production ranking task, a human-designed transformer baseline (V2) yielded +0.118%+0.118\% over a pre-transformer baseline (V1); the AI Co-Scientist's automated loop on top of V2 contributed an additional +0.083%+0.083\%, for a combined +0.201%+0.201\% offline gain delivered in roughly one extra week of wall-clock time (single-run numbers; statistical limits discussed in the paper). The most useful AI proposals -- unified long-sequence layouts, slot-type embeddings, and multi-phase learning-rate schedules -- are standard practice in NLP and Vision but were absent from our production stack, suggesting that LLM agents can serve as cross-disciplinary connectors for ranking teams. We also report deployment context, negative results, and lessons learned.

Liwei Wu, Cho-Jui Hsieh

Trip.com Group · UCLA

Autonomous Research AgentsLearning to RankAI Agents for Scientific DiscoveryHuman-in-the-Loop AIMulti-Agent LLM Systems
AskPDF
Mar 23, 2026

Optimizing Multi-Agent Weather Captioning via Text Gradient Descent: A Training-Free Approach with Consensus-Aware Gradient Fusion

Generating interpretable natural language captions from weather time series data remains a significant challenge at the intersection of meteorological science and natural language processing. While recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in time series forecasting and analysis, existing approaches either produce numerical predictions without human-accessible explanations or generate generic descriptions lacking domain-specific depth. We introduce WeatherTGD, a training-free multi-agent framework that reinterprets collaborative caption refinement through the lens of Text Gradient Descent (TGD). Our system deploys three specialized LLM agents including a Statistical Analyst, a Physics Interpreter, and a Meteorology Expert that generate domain-specific textual gradients from weather time series observations. These gradients are aggregated through a novel Consensus-Aware Gradient Fusion mechanism that extracts common signals while preserving unique domain perspectives. The fused gradients then guide an iterative refinement process analogous to gradient descent, where each LLM-generated feedback signal updates the caption toward an optimal solution. Experiments on real-world meteorological datasets demonstrate that WeatherTGD achieves significant improvements in both LLM-based evaluation and human expert evaluation, substantially outperforming existing multi-agent baselines while maintaining computational efficiency through parallel agent execution.

Shixu Liu

School of Computer & Information Technology, Northeast Petroleum University, No. 99 Xuefu Street, Ranghulu District, Daqing, Heilongjiang, 163318, P.R. China

Multi-Agent LLM SystemsGradient Descent
AskPDF
Mar 23, 2026

Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation

Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration capabilities. As these systems become more complex and autonomous, effective failure management is essential to ensure reliability and availability. However, existing approaches often rely on per-trace reasoning, which leads to low efficiency, and neglect historical failure patterns, limiting diagnostic accuracy. In this paper, we conduct a preliminary empirical study to demonstrate the necessity, potential, and challenges of leveraging historical failure patterns to enhance failure management in MASs. Building on this insight, we propose EAGER, an efficient failure management framework for multi-agent systems based on reasoning trace representation. EAGER employs unsupervised reasoning-scoped contrastive learning to encode both intra-agent reasoning and inter-agent coordination, enabling real-time step-wise failure detection, diagnosis, and reflexive mitigation guided by historical failure knowledge. Preliminary evaluations on three open-source MASs demonstrate the effectiveness of EAGER and highlight promising directions for future research in reliable multi-agent system operations.

Lingzhe Zhang, Tong Jia, Mingyu Wang +9

Peking University Beijing, China · Huawei Technologies Co., Ltd. Beijing, China · Huawei Technologies Co., Ltd. Hong Kong SAR, China +1

Agent Failure AnalysisMulti-Agent LLM SystemsMulti-Agent Systems
AskPDF
Mar 21, 2026

Subjective-Graph LLM Agents for Simulating Uncertainty in Classroom Social Perception

Social actors do not observe a common social world: each individual forms judgments from a partial and potentially distorted view of the surrounding network. We study whether graph-local evidence and credibility-weighted communication can generate persistent distortions in perceived academic standing, even when agents repeatedly receive objective performance signals. We introduce a data-constrained multi-agent framework in which LLM agents operate through individualized subjective graphs that determine peer visibility, evidence access, and interaction opportunities. Agents exchange uncertainty-annotated assessments, evaluate message credibility, and maintain explicit Gaussian belief states updated through Bayesian fusion. We evaluate the framework on 12 middle-school classrooms comprising 482 students, using questionnaire-derived social information and six consecutive examinations. On the Social-Observed subset (n=419), collective ranking error increases from 0.066 \pm 0.008 to 0.124 \pm 0.009 across six epochs despite repeated exam-based anchoring. Ablations associate individualized visibility and LLM-based trust gating with more stable long-horizon behavior, while constrained retrieval primarily safeguards against global-information leakage. Compared with evaluated DeGroot configurations, the proposed framework achieves lower final ranking error; those DeGroot configurations exhibit near-zero terminal opinion diversity. These findings establish subjective-graph LLM agents as a mechanism-oriented framework for data-constrained simulated social perception. Code is available at https://anonymous.4open.science/r/Rashomonomon-0126.

Jinming Yang, Xinyu Jiang, Xinshan Jiao +1

Complex Lab, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · Department of Computer Science, City University of Hong Kong, Hong Kong · School of Health and Medical Technology, Chengdu Neusoft University, Chengdu,2026 China

Multi-Agent LLM SystemsOpinion DynamicsAI in EducationEducationComputational Social ScienceAgent-Based Modeling
AskPDF
Mar 20, 2026

An Agentic Multi-Agent Architecture for Cybersecurity Risk Management

Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip it entirely. We built a six-agent AI system where each agent handles one analytical stage: profiling the organization, mapping assets, analyzing threats, evaluating controls, scoring risks, and generating recommendations. Agents share a persistent context that grows as the assessment proceeds, so later agents build on what earlier ones concluded -- the mechanism that distinguishes this from standard sequential agent pipelines. We tested it on a 15-person HIPAA-covered healthcare company and compared outputs to independent assessments by three CISSP practitioners -- the system agreed with them 85% of the time on severity classifications, covered 92% of identified risks, and finished in under 15 minutes. We then ran 30 repeated single-agent assessments across five synthetic but sector-realistic organizational profiles in healthcare, fintech, manufacturing, retail, and SaaS, comparing a general-purpose Mistral-7B against a domain fine-tuned model. Both completed every run. The fine-tuned model flagged threats the baseline could not see at all: PHI exposure in healthcare, OT/IIoT vulnerabilities in manufacturing, platform-specific risks in retail. The full multi-agent pipeline, however, failed every one of 30 attempts on a Tesla T4 with its 4,096-token default context window -- context capacity, not model quality, turned out to be the binding constraint.

Ravish Gupta, Saket Kumar, Shreeya Sharma +2

BigCommerce · Lead Software Engineer, BigCommerce; IEEE Senior Member · University at Buffalo, The State University of New York, Buffalo, NY, USA +4

CybersecurityAI Risk ManagementMulti-Agent LLM SystemsLLMs for CybersecurityLLM Agent Evaluation
AskPDF
Mar 20, 2026

Can LLM Agents Simulate Dynamic Networks? A Case Study on Email Networks with Phishing Synthesis

While Large Language Model (LLM) multi-agent systems (MAS) offer a transformative approach to simulating human behavior in complex systems, it remains largely unexplored whether these simulations can replicate realistic structural and temporal dynamics from a dynamic network perspective. Our evaluation indicates that existing frameworks excel at generating plausible micro-level interactions but fail to capture the emergent, macroscopic topologies necessary for domains that rely on realistic network dynamics, such as modeling information propagation and cybersecurity threats. To bridge this gap, we introduce two easily integrable extensions to simulation frameworks to ensure they preserve macroscopic network fidelity: 1) augmenting LLM agents with data-driven event triggers to organically sustain long-horizon interactions, and 2) integrating Hawkes processes to accurately model temporal activation dynamics. Our approach allows LLM MAS to capture both plausible micro-level patterns and macroscopic topologies. We further demonstrate the utility of this framework in synthesizing realistic phishing campaigns within evolving communication networks. The study reveals how threats exploit structural vulnerabilities, highlighting the potential of our framework for developing next-generation defenses. Our code is available at https://github.com/Graph-COM/NSL.

Siqi Miao, Ziyang Chen, Yuhong Luo +4

Georgia Institute of Technology · University of Maryland, College Park · Rutgers University

Hawkes ProcessesLarge Language Model-Based Social SimulationMulti-Agent LLM Systems
AskPDF