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

May 26, 2026cs.AI

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely optimized through a unified reinforcement learning interface. Existing RL post-training frameworks mainly target single-policy optimization and lack abstractions for user-defined multi-agent workflows, structured interaction, role-specific credit assignment, and configurable parameter sharing. We present UnityMAS-O, a general RL optimization framework for LLM-based multi-agent systems. UnityMAS-O treats the complete workflow as the optimization unit, rather than a single response or policy trajectory. It represents workflows through four first-class objects: logical agent roles, graph trajectories, user-defined rewards, and agent--model mappings. This decouples logical agents from physical model parameters, supporting full sharing, full separation, and partial sharing, with rewards assigned at role, turn, and trajectory levels. UnityMAS-O extends verl with a Ray-based star-topology runtime. A central controller executes workflows, invokes tools, records structured trajectories, and assembles rewards; model-local worker groups handle rollout, buffering, advantage computation, and distributed PPO-style updates. Users can define agents, workflows, model mappings, and rewards without rewriting the optimization infrastructure. We instantiate UnityMAS-O on retrieval-augmented QA, iterative agentic search, and reflective code generation. Across Natural Questions, HotpotQA, and held-out code tasks, multi-agent RL improves manually specified workflows after optimization, with especially large gains for smaller models and strict code all-passed metrics. These results show that UnityMAS-O can serve as a reusable substrate for converting diverse LLM-based multi-agent workflows into trainable multi-agent RL systems.

Yiqun Chen, Wei Yang, Erhan Zhang +14

Renmin University of China · Xiaohongshu Inc.

Multi-Agent LLM Systems Multi-Agent System Optimization LLM Agent Workflow Optimization LLM Agent Training RL for LLM Agents Multi-Agent Reinforcement Learning

May 25, 2026cs.LG

Stateful Inference for Low-Latency Multi-Agent Tool Calling

Multi-agent tool calling is becoming the dominant interaction pattern for LLM-based systems, yet existing inference frameworks treat each tool call as an independent request, re-processing the entire conversation from scratch even though 85-95% of the prompt is unchanged from the previous turn. We present a stateful inference architecture that converts the

O(n_t)

per-turn cost of conventional serving into an

O(Δ_t)

delta-only cost: a persistent KV cache lives across turns and advances by ingesting only the new tokens, while a radix prefix cache extends this across interleaved multi-agent traffic and a prompt-lookup speculative decoder accelerates structured output. Against vLLM and SGLang on novel, fully-generated workloads, the reference implementation is

2.1\times

faster per turn on a 6-turn agentic workflow and

4.2\times

on the median turn of a 35-turn one, halving end-to-end wall time. The advantage comes from stateful reuse and speculation, not caching.

Victor Norgren

LayerScale, Inc.

LLM Inference Efficiency Multi-Agent LLM Systems Tool-Augmented Language Model Agents LLM Agent Workflow Optimization LLM Inference Serving LLM Agent Serving+1

May 25, 2026cs.CL

PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction

This paper introduces PolyGnosis 2.0, a pioneering multi-agent architecture designed to extract predictive intelligence by synthesizing Polymarket anomaly signals with global Open Source Intelligence (OSINT) streams, specifically Global Database of Events, Language, and Tone (GDELT). We define and target "Perspective Mismatches", the narrative divergence between Polymarket sentiment and global media flows, as high-alpha trading signals. Moving beyond generic agentic superiority, we rigorously quantify the efficacy of "Harness Engineering" techniques, including reflection loops, tool-calling, divide-and-conquer partitioning (D&C), and chain-of-thought (CoT), within high-noise financial domains. Our empirical evaluation against human-expert benchmarks reveals that while structural partitioning is mandatory for multi-dimensional alignment, unconstrained terminal reflection actively induces logical drift. Furthermore, we identify a pervasive "consensus bias" across all agent configurations during narrative reasoning, necessitating deterministic validation. Ultimately, we isolate a Pareto-optimal configuration that achieves professional-grade analytical precision while minimizing latency and token overhead, providing a robust blueprint for autonomous intelligence in prediction markets.

Daren Wang, Hong Xu, Jiawen Xian

The Chinese University of Hong Kong · Evolution AI Lab

Multi-Agent LLM Systems LLM Agent Orchestration LLM Agent Evaluation Prediction Markets

May 25, 2026cs.MA

Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?

The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collaborate. We study this mechanism through the lens of Friedkin-Johnsen (FJ) opinion dynamics, a tractable model for analyzing stubbornness, influence, and opinion change in multi-agent systems that captures empirically observed deliberation patterns. We show that the FJ parameters are input-dependent, turning multi-agent deliberation into a mixture of experts. This perspective implies that multi-agent systems can outperform single agents and static ensembles when routing reflects agent competence. Since competence is latent in practice, we analyze how influence is established through observable proxies: agents' self-assessed confidence, their perceived confidence, and initial alignment with other agents' views.

Franka Bause, Jonas Niederle, Martin Pawelczyk +1

CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Faculty of Computer Science, University of Vienna, Vienna, Austria.

Multi-Agent LLM Systems Opinion Dynamics Mixture of Experts Multi-Agent Collaboration Multi-Agent Reasoning

May 25, 2026cs.MA

Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution.

Haoran Li, Shulun Chen, Shaoyuan Sun +1

Nanjing University · University of Technology Sydney, Sydney, Australia · University of New South Wales, Sydney, Australia

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Orchestration LLM Agent Orchestration

May 25, 2026cond-mat.mtrl-sci

AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations

Density functional theory (DFT) serves as the basis for computational discovery in materials science and chemistry, yet each calculation demands extensive human effort: adjusting algorithms when convergence stalls, revising plans when unexpected physics emerges, and inserting steps as intermediate results reshape the problem. Existing LLM-based agents automate only the initial planning stage, producing a full execution plan upfront and leaving all subsequent adaptation to hand-crafted rules. As a result, these workflows remain fragile, do not generalize well beyond pre-planned scenarios, and often require expert intervention when failures or unexpected intermediate results require changes to the calculation path. Here, we introduce AutoDFT, a closed-loop multi-agent framework that embeds LLM reasoning into every stage of the DFT lifecycle, where a strategic planner produces a skeletal plan of step objectives; a step planner generates numerical parameters just in time from preceding results; and a monitor-recover-reflect cycle diagnoses failures, repairs them, and revises the plan when the evidence justifies it. We demonstrate both breadth and depth: breadth on VASPBench, a purpose-built benchmark spanning 34 tasks and 9 DFT calculation types, where AutoDFT achieves 94.1% task-level success with GPT-5.2; and depth on established materials databases, where AutoDFT produces quantitatively reliable property predictions across electronic, magnetic, and energetic properties. By closing the loop between planning and execution, AutoDFT enables experimentalists without deep computational expertise to obtain reliable first-principles results.

Penghui Yang, Zhonghan Zhang, Yue Li +6

Nanyang Technological University, Singapore · Singapore Management University

Multi-Agent LLM Systems Scientific Workflow Automation LLM Agent Planning Computational Materials Science

May 25, 2026cs.MA

ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy

Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often misalign computational budgets with query difficulty. We propose \textsc{ATOM}, an adaptive framework that generates budget-controllable collaboration graphs via a novel task-driven reinforcement learning paradigm. Inspired by atomic structures, \textsc{ATOM} employs a nucleus-electron hierarchy: it maintains a stable, offline-learned collaboration backbone (the nucleus) while dynamically activating query-conditioned agents (electrons) during inference. Crucially, a complexity-aware budgeting strategy aligns resource consumption with task demands by estimating query difficulty to strictly regulate electron instantiation. Extensive experiments across six diverse benchmarks demonstrate that \textsc{ATOM} achieves state-of-the-art performance while improving token efficiency by up to

30\%

compared to strong baselines.

Xinkui Zhao, Sai Liu, Yifan Zhang +6

Zhejiang University · Ningbo Global Innovation Center, Zhejiang University · Zhejiang Key Laboratory of Digital-Intelligence Service Technology +1

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Orchestration Multi-Agent Collaboration Multi-Agent Systems RL for LLM Agents

May 25, 2026cs.SE

A Universal Cliff and a Design Fingerprint: Cross-Section Defect Detection Under LLM Orchestration

Production language-model systems answer a request by partitioning it across an invisible orchestration of worker agents that recompose one integrated report. We ask what this does to a class of defect no single worker can see: a contradiction in the relation between two distant sections of a document. Holding the documents, defects, mechanism, scoring, and seed fixed, we vary only the model -- ten systems across five generations from one developer and five providers from distinct alignment paradigms. Two layers separate. First, a universal detection cliff: every model that finds these cross-section defects under a single agent loses that ability under orchestration, detection falling two-thirds or more across every paradigm tested. The cliff is mechanism-derived and not closed by scale or extended reasoning. Second, how models behave once fallen. A signal-detection decomposition shows that, among the six models discriminating above chance, only one developer's generations move along the reporting-criterion axis: as alignment is strengthened, the model misses fewer defects yet raises more false alarms on clean documents -- two faces of one criterion shift, scaling with generation within that developer (p < 0.001) and near-absent elsewhere. At the floor the missed defect is often not out of view: the model's private record reconstructs the structural fault accurately, while the integrated report signs off on its soundness, its concern spent on the artifact and an absent collaborator. This resists quantification -- an automated judge is unstable (precision 17-50%) and keywords cannot separate it from ordinary agreement -- a resistance we report as a finding. We release all runs, probes, defect keys, scorer prompts, and scripts. An integrated report's confidence is uninformative about partition-spanning defects, the most aligned systems are not the safest, and the cliff is structural.

Hiroki Fukui

Research Institute of Criminal Psychiatry · Department of Neuropsychiatry, Graduate School of Medicine, Kyoto University

Multi-Agent LLM Systems LLM Evaluation Fault Detection LLM Agent Reliability

May 25, 2026eess.SP

A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration

The convergence of large language models (LLMs) with 6G networks is fostering a paradigm of autonomous multi-agent cooperation, which in turn is expected to substantially increase east-west traffic. Although latent-space interaction mechanisms can enable more efficient collaboration than symbolic natural-language (NL) exchanges, prior work often abstracts away the associated communication overhead under practical wireless constraints. In embodied multi-agent settings, heterogeneous interaction media incur disparate inference and transmission costs, thereby inducing an inherent end-to-end (E2E) latency trade-off. To address this, we propose a joint design that integrates communication-media selection with wireless resource allocation. Through analytical characterization and simulation-based evaluation, we show that neither token-based transmission nor key-value (KV) cache-based transmission is uniformly optimal across operating regimes, as performance depends critically on system parameters such as available computational resources and channel conditions. Accordingly, we formulate a joint optimization problem aimed at minimizing the E2E latency of multi-agent collaboration and develop a low-complexity joint media selection and resource allocation (JMSRA) algorithm. Numerical results further confirm that, by adaptively coordinating the interaction media and bandwidth allocation over heterogeneous links, the proposed scheme achieves markedly reduced E2E latency relative to conventional NL-only and KV-cache-only baselines, enabling efficient and robust multi-agent collaboration in future wireless networks.

Lipeng Dai, Luping Xiang, Kun Yang

State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, 210008, China · Institute of Intelligent Networks and Communications (NINE), Nanjing University (Suzhou Campus), Suzhou, 215163, China

Multi-Agent LLM Systems Multi-Agent Collaboration Wireless Resource Allocation Multi-Agent Communication

May 25, 2026cs.CV

Towards Reliable Fetal Ultrasound Interpretation with Multi-Agent Collaboration

Automated fetal ultrasound interpretation requires a workflow from visual perception, including plane recognition and anatomical segmentation, to clinical understanding, including biometric measurement and diagnostic reporting. However, the prevailing "one-task, one-model" paradigm limits systematic integration of evidence across this multi-step process. Although multimodal large language models (MLLMs) show promising visual understanding, their limited domain-specific grounding and hallucination risks restrict reliability in fetal ultrasound analysis. To address these limitations, we propose FetUSAgents, a tool-augmented multi-agent system for comprehensive fetal ultrasound interpretation, supporting visual question answering (VQA), report generation, image captioning, and video summarization. FetUSAgents coordinates task-specific visual tools through collaborative LLM agents and decomposes clinical queries into subtasks that progress from anatomical recognition to quantitative measurement. We further introduce Dual-Path Evidence Arbitration (DPEA), which integrates LLM-based deliberative reasoning with structured computational evidence from specialized visual tools. A retrieval-enhanced evidence bank consolidates intermediate findings to support traceable and clinically grounded conclusions. In addition, we construct FetUS-VQA, a dedicated VQA benchmark for fetal ultrasound, comprising 1,892 images and 3,205 question-answer pairs across 10 clinical tasks. Extensive out-of-distribution experiments show that FetUSAgents outperforms general and medical MLLMs, exceeding the strongest baseline by more than 25 percent in VQA accuracy. These results suggest a scalable route toward evidence-driven clinical assistants for prenatal imaging. Code is available.

Xiaotian Hu, Mingxuan Liu, Junwei Huang +13

Tsinghua University, Beijing, China · University of California San Diego, La Jolla, CA, USA · West China Second University Hospital, Sichuan University, Chengdu, China

Multi-Agent LLM Systems Medical VQA Ultrasound Imaging

May 24, 2026cs.AI

LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design

Lipid nanoparticles (LNPs) are among the most clinically mature platforms for nucleic acid delivery, yet designing lipids that are both effective and biologically safe remains a major bottleneck. In practical screening, toxicity is a decision-level constraint: if a lipid is toxic, its efficiency prediction is clinically irrelevant. We propose LipoAgent, a safety-aware multi-agent LLM framework for lipid discovery. LipoAgent combines domain-specific finetuning with a conditional prediction objective that enforces toxicity as a prerequisite for efficiency prediction, and further improves reliability via multi-agent verification with lightweight human oversight when disagreement persists. Across multiple foundation models, LipoAgent achieves an average 32% relative improvement in mRNA transfection efficiency prediction compared with other reported models for lipid design. Wet-lab validation confirms that virtual screening rankings reliably translate to biological transfection outcomes. The code is publicly available at https://github.com/SAI-Lab-NYU/LipoAgent.git.

Leshu Li, An Lu, Haiyu Wang +5

New York University, USA · University of Illinois Chicago, USA

Multi-Agent LLM Systems Materials Science LLM Agent Training Drug Discovery

May 24, 2026cs.AI

DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces, incorrect intermediate reasoning may be adopted and amplified, leading to confident but wrong consensus; multi-round communication also increases token consumption, latency, and inference cost. In this paper, we propose a controlled-communication coordination framework named DarkForest. DarkForest first keeps agents independent, so each agent produces an answer without seeing the others' outputs. It then parses the raw responses into structured candidate records, groups semantically equivalent candidates into clusters, and estimates a calibrated belief distribution over these clusters using agent reliability, confidence, parse quality, support-pattern reliability, and independence corrections. A coordinator receives only policy-permitted evidence from this belief state with controlled communication. Experiments on six reasoning benchmarks show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7% on benchmark metrics, and reduces token consumption by up to

6.5\times

compared with communication-heavy baselines.

Yi Li, Songtao Wei, Dongming Jiang +3

University of Texas at Dallas · Independent Researcher · University of California, Davis

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination LLM Agent Workflow Optimization Agentic Reasoning Multi-Agent Systems+3

May 24, 2026cs.LG

MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration

Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (LLMs), a requirement for reliable, financial analysis where answers must be grounded in verifiable evidence from filings rather than generated from model priors. However, designing RAG systems that extract meaningful insights from mixed financial documents and integrate into analyst workflows remains challenging. This paper introduces MimirRAG (Metadata-Integrated Multi-Agent Information Retrieval), a multi-agent RAG system developed iteratively to address these challenges. MimirRAG features a modular pipeline encompassing structure-preserving parsing of PDF filings, table-aware chunking, metadata extraction, agent-based retrieval with query planning and hybrid search, validation, and context-aware generation with numerical reasoning support. Our ablation study identifies three key technical enablers for effective financial RAG: metadata integration, table-aware chunking, and an agentic workflow. MimirRAG was evaluated quantitatively using FinanceBench and qualitatively through expert validation with four financial analysts. The system achieved 89.3% accuracy on FinanceBench, outperforming the original benchmark baselines. Expert feedback highlighted that successful deployment also requires calibrated trust, comprehensive data integration, and user personalization. We conclude that combining multi-agent RAG architecture with human-centric design principles can improve the extraction of meaningful insights in financial analysis.

Magnus Samuelsen, Wilmer Nyström, Somnath Mazumdar +2

Copenhagen Business School, Solbjerg Plads 3, Frederiksberg, 2000, Denmark · Jyske Bank, Copenhagen, Denmark

Financial Services Multi-Agent LLM Systems Financial QA Agentic RAG Finance

May 23, 2026cs.AI

MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional

Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can come from architectural and engine-level design. We present MDIA, a Multi-agent Diagnostic Intelligence Agent implemented as a 7-node specialty-routed clinical reasoning graph, on the full HealthBench Professional benchmark (n = 525), on a non-fine-tuned LLM. MDIA achieves 0.6272 under OpenAI's GPT-5.4-2026-03-05, which is +3.72 pp above the performance of OpenAI's ChatGPT for Clinicians. The experimental work shows that performance lift is attributable to system architecture: specialty routing, multi-turn context preservation, drug-state safety gating, site-filtered search, length-aware synthesis, and engine-level reliability. These findings support the view that agentic clinical benchmark performance is shaped both by the underlying foundation model and the orchestration architecture. Nevertheless, we also noticed notable differences when using other models as a grader; in particular, when using Gemini 2.5 Pro, MDIA scored 0.6585, which suggests that the choice of grader is a source of variability. Robust evaluation of LLMs would therefore require assessment across several independent grader models.

Roberto Cruz, David Rey-Blanco

TietAI

Multi-Agent LLM Systems Healthcare LLM Agent Orchestration Clinical Reasoning Clinical Language Model Evaluation

May 23, 2026cs.AI

Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis

Large language models (LLMs) are increasingly used for qualitative data analysis (QDA), yet their outputs often miss the depth and nuance of human analysis. We argue this gap reflects a missing credibility practice from human QDA: peer debriefing, in which an analyst seeks feedback from a disinterested peer and uses it to refine their coding. To bring this practice into LLM-assisted QDA, we propose Agent-as-Peer-Debriefer, a multi-agent QDA framework that builds peer debriefing into key coding steps. In our framework, a Hierarchical Coding Agent follows the standard QDA process to generate codes, sub-themes, and themes, along with self-explanations and reflection memos. It then shares these outputs with three Peer-Debriefing Agents, each applying a distinct analytical perspective (Theory-Driven, Data-Driven, or Applied) and refining the codes by keeping, renaming, reassigning, merging, or splitting them. These perspectives are drawn from established human QDA practices that generalize across domains and datasets. To evaluate the framework, we test it on three datasets across two domains with three LLMs, measuring semantic similarity to human-annotated codes. Across all settings, perspective-based, peer-debriefing refinement aligns more closely with human codes than a single-LLM baseline, and an ablation further shows the gain is not merely from additional refinement. The three perspectives also produce distinct trade-offs, showing that the choice of perspective is a meaningful and controllable design decision. More broadly, these findings suggest that simulating peer debriefing with explicit perspectives is a promising route to more credible LLM-assisted QDA.

Zhimin Lin, Kun Cheng, Zhiyao Shu +4

Soochow University · George Mason University · Johns Hopkins University

Multi-Agent LLM Systems LLM-Assisted Annotation

May 23, 2026cs.AI

Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems

Multi-agent LLM decision systems for portfolio management still lack a principled way to assign credit across specialist agents, remain vulnerable to cold-start dominance under regime shifts, and offer limited transparency into how final allocations are formed. We propose Market Regime Council (MRC), a cooperative multi-agent decision system that computes exact Shapley credits across all single, pairwise, and Grand-coalition outputs for online agent weighting. Instantiated with N=3 specialist agents, at each trading period, MRC recomputes coalition-based Shapley weights from exponentially weighted performance histories, uses a Bayesian adaptive mixture to stabilize early periods, applies regime-dependent multipliers to adjust agent authority, and records each rebalance through a five-layer causal trace. Over 1,037 trading days across 13 crypto assets and five seeds, MRC achieves a Sharpe ratio of 1.51 and a cumulative return of 440.1%, ranking first on CR, SR, and IR among active baselines and attaining the lowest MDD among active methods. Ablation results show that the gains come from Shapley-weighted integration across coalition outputs rather than from any single stage in isolation. Code and demo data are included in the supplementary material.

Yunhua Pei, Zerui Ge, Jin Zheng +1

University of Bristol, UK · Independent Researcher

Multi-Agent LLM Systems Multi-Agent Systems Fine-Grained Credit Assignment Algorithmic Trading

May 22, 2026cs.AI

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training of multi-agent LLM workflows improves over their base models, comparing Shared-Policy training, where all roles update one policy, with Isolated-Policy training, where each role has its own parameters. Our experimental matrix spans Eval-Opt, Voting, and Orch-Workers workflows, math and code tasks, and three model scales (0.6B, 1.7B, 4B). We find that multi-agent RL usually improves over base models, but gains depend jointly on workflow, task, and scale, not on policy sharing alone. Isolated-Policy tends to reach higher peak accuracy yet more often falls off a terminal accuracy cliff, while Shared-Policy training does not eliminate failure; it redistributes failure into qualitatively different patterns. We then explain the strongest of these patterns through role-level gradient dynamics induced by workflow topology and policy routing: under Isolated-Policy, parallel same-role agents on shared prompts amplify per-role gradients and drive terminal degradation in Voting and Orch-Workers workflows; under Shared-Policy, asymmetric per-step gradient mass causes the shared policy to be captured by the dominant role, producing different failure signatures by task and workflow. Together, the empirical map and its underlying mechanisms show that policy sharing routes training pressure through different channels rather than offering uniform stability, making it a design choice with workflow- and task-conditional tradeoffs.

Yifan Zeng, Yiran Wu, Yaolun Zhang +4

1Oregon State University · 2Pennsylvania State University · 3Adobe Inc. +1

Multi-Agent LLM Systems LLM Agent Workflow Optimization RL for LLM Agents Multi-Agent Reinforcement Learning

May 22, 2026cs.LG

LLM-driven design of physics-constrained constitutive models: two agents are better than one

Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) have recently been shown to lower this barrier by generating constitutive models on demand, but existing single-agent pipelines lack systematic checks that the resulting models respect fundamental physical laws. To close this gap, we introduce the first multi-agent LLM-driven approach for constitutive model generation: a Creator agent proposes a model tailored to the data, while an Inspector agent critically audits each proposal against nine physical constraints and returns it for refinement whenever a violation is detected. We demonstrate this concept with constitutive artificial neural networks (CANNs) and benchmark it on brain tissue and rubber as isotropic materials, and on porcine skin tissue as a transversely isotropic material with a preferred fiber direction, using two different LLM backbones (Claude Opus 4.7 and Kimi K2.5). Whether a generated model satisfies the physical constraints is assessed numerically, by probing each constraint across a broad sample of deformation states, rotations, and perturbation directions. Adding the Inspector raises the share of exported models that pass all these checks from 90% to 95% for Opus and from 47% to 60% for Kimi. In addition, the generated models are on par with or even surpass expert-designed models in accuracy, extrapolate reliably beyond the training data, and generalize remarkably well to unseen loading paths. Separating generation from inspection thus turns LLM-driven constitutive modeling into a substantially more trustworthy process. The paradigm is deliberately technique-agnostic...

Marius Tacke, Matthias Busch, Kian Abdolazizi +4

1Helmholtz-Zentrum Hereon, Geesthacht, Germany · 2Hamburg University of Technology, Hamburg, Germany · 3RWTH Aachen University, Aachen, Germany +2

Neural Surrogate Modeling Multi-Agent LLM Systems Generative Modeling Physics-Informed ML

May 22, 2026cs.AI

When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems

LLM-based multi-agent systems can fail even when planned actions are executed correctly because agents may misjudge their knowledge when evaluating plan feasibility, a phenomenon we term epistemic miscalibration in planning. Unlike execution errors, epistemic miscalibration is latent during planning, as generated plans can remain self-consistent and executable without observable errors; the miscalibration is also dynamic, as new information can alter feasibility assessments, potentially obscuring past miscalibration signals and causing them to recur over time. To address this, we propose the Epistemic Planning Calibration Agentic Workflow (EPC-AW), which assesses whether plans remain supported under varying information conditions rather than directly verifying feasibility. EPC-AW employs Information-consistency-based Plan Selection, selecting plans whose evaluations are stable across agents, together with Consistency-guided Epistemic State Refinement to adapt calibration over time by leveraging past discrepancies to guide future planning. Experiments show that EPC-AW improves system-level success by an average of 9.75%.

Zehao Wang, Shilong Jin, Zhao Cao +1

College of Intelligence and Computing, Tianjin University, Tianjin, China · School of New Media and Communication, Tianjin University, Tianjin, China · Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China

Multi-Agent LLM Systems Multi-Agent Planning LLM Agent Planning LLM Agent Reliability

May 22, 2026cs.MA

Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems

Large language models exhibit a risk-averse "turtle" bias as strategic agents. We show that injecting a symbolic reasoning framework as a per-round reflective prompt into one agent acts as a small perturbation whose consequences are not per-decision but emergent: the agent's risk posture is unchanged in isolation, yet over a campaign of accumulating memory and multi-agent interaction the conditions settle into distinct, condition-associated winner ecosystems. In a 7-player Warring States Diplomacy variant (61 games, 6 conditions), the winner distribution differs sharply across the four primary conditions (41 games; permutation omnibus p approximately 0.001): control -> Yan (7/11); I-Ching yarrow -> Yan/Chu co-dominance with Qin fully suppressed (0/10); Tarot -> Qin (5/10); scrambled-text ablation -> Qi (5/10). The scrambled->Qi attractor is robust (vs. pooled and control alone, p = 0.006 and 0.012); tarot->Qin is denominator-dependent (0.006 pooled, 0.064 vs. control). Han never wins and shows no survival difference (Fisher p = 1.0); neither framework's content predicts actions (chi-squared p = 0.95 hexagram, 0.69 Tarot). A memory-free decision-isolation probe (960 calls) shows the process does not change the agent's risk posture in isolation (Friedman p = 0.45; I-Ching p = 0.60; Tarot perturbs move content but not risk, p = 0.021). A 2x2 factorial separating yarrow's decision-time and learning-time components reveals a non-additive interaction: each alone freezes the board (50-60% stalemates), combined they produce zero (permutation p ~ 5e-5). Testing relocates Qin suppression to rival (Chu) expansion governed by campaign memory depth, not the oracle (p = 0.55). We present this as an observation paper: agent-level framework choice produces distinctive, non-additive system-level consequences, transmitted through emergent memory and multi-agent dynamics, not per-decision effects.

Augustin Chan

Multi-Agent LLM Systems Game-Playing Agents Multi-Agent Systems Emergent Behavior in Multi-Agent Systems Memory-Augmented Language Model Agents

May 22, 2026cs.MA

Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework

Topology optimization is a widely used design method that produces optimized material distributions for prescribed objectives and constraints through well-established numerical algorithms. Throughout the workflow, engineers make a series of decisions ranging from setting and adjusting numerical parameters to assessing whether the converged design meets considerations beyond those explicitly included in the optimization problem, such as physical feasibility. These decisions, which draw on domain expertise, interfere with the autonomous design process. To address this difficulty, this study presents TopOptAgents, a multi-agent system for automating not only the design process but also decision-making during the key stages of the topology optimization process. TopOptAgents consists of six LLM-based agents collaborating through iterative self-refinement cycles spanning problem formulation, validation, code generation and execution, and quality assessment of the optimized structure. This process enables error correction and progressive improvement of both the optimization setup and resulting design. The framework is demonstrated on optimization problems selected to cover a range of settings that differ in their literature coverage and numerical characteristics The benefits of iterative self-refinement are found to be particularly pronounced for problem classes where the pretrained language model has limited prior exposure, such as formulations whose literature and open-source implementations are comparatively sparse. In such cases, the proposed framework reliably produces converged designs where a single state-of-the-art LLM struggles, suggesting that self-refinement broadens the range of topology optimization problems that LLM-based automation can reliably address.

Hyunjee Park, Hayoung Chung

Department of Mechanical Engineering, Ulsan National Institute of Science and Technology, 50 UNIST-gil, Ulju-gun, Ulsan, 44919, Republic of Korea

Topology Optimization Multi-Agent LLM Systems Multi-Agent System Optimization LLM Self-Refinement

May 21, 2026cs.MA

SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate

Multi-Agent Debate (MAD) improves LLM-agent accuracy but suffers from rapid context growth, limiting scalability in larger multi-agent settings. Existing methods prune low-utility communications using prior signals, such as token-level log-likelihoods or LLM self-reported confidence. However, these signals become unreliable under hallucination, degrading the accuracy of MAD methods that rely on them. We propose SVR-MAD, a Bayesian-inspired MAD framework that treats pre-debate signals as priors and debate outcomes as posterior-style evidence for estimating agent correctness. SVR-MAD uses this evidence to incrementally construct the communication graph, prioritizing agents whose answers survive peer challenges. Experiments across multiple LLMs and benchmarks show that SVR-MAD reduces token cost by up to 61% while matching or improving accuracy relative to the most accurate competing MAD baseline.

Weifan Jiang, Rana Shahout, Minghao Li +4

Harvard University

Multi-Agent LLM Systems Multi-Agent Debate Multi-Agent Communication

May 21, 2026cs.MA

How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning

In orchestrated multi-agent systems, humans often struggle to manage plans due to their complexity and limited transparency. Existing approaches rely on outcome-level supervision, where users verify only final outputs without visibility into intermediate reasoning. We formalize a design space for human-LLM co-planning interactions along three axes: mode (semantic vs. structural), scope (global vs. targeted), and level (low vs. high-level edits). We realize it in AMBIPOM, a prototype supporting process-level supervision through both semantic and structural interactions. Through a user study, we characterize how users navigate this space, revealing hybrid workflows and effort-control-risk trade-offs; through a controlled benchmark, we analyze how LLMs revise plans under varying scope and revision strategies. Our findings yield design insights for more transparent, controllable, and effective human-AI co-planning. We release code and data at https://github.com/megagonlabs/ambipom.

Zeyu He, Hannah Kim, Dan Zhang +1

Penn State University · Work done during internship at Megagon Labs · Megagon Labs

Multi-Agent LLM Systems Process Supervision Multi-Agent Planning Human-AI Collaboration

May 21, 2026cs.CL

A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in Autism

Characteristic linguistic behaviors associated with Social Language Disorder (SLD) in autism spectrum disorder, including echoic repetition, pronoun displacement, and stereotyped media quoting, are largely absent from spontaneous conversation and only emerge under specific conversational conditions. In structured clinical assessments, this latency means that questioning strategy selection is a critical yet underappreciated determinant of how much diagnostic information a conversation yields. Whether large language models (LLMs) can be guided to proactively select questioning strategies that systematically surface these latent traits remains largely unexplored. Here we present TPA (Think, Plan, Ask), a proactive multi-agent dialogue framework applied to the language assessment component of the Autism Diagnostic Observation Schedule Module 4 (ADOS-2), in which a doctor agent explicitly reasons about which traits remain unobserved before selecting a clinically grounded strategy and generating a targeted question. A patient agent grounded in real ADOS-2 clinical data enables reproducible evaluation without real patient participation, validated across three independent experiments confirming adequate fidelity to real patient language. Evaluated on 484 episodes from 35 patients, TPA outperforms six competitive dialogue planning baselines across all primary metrics, achieving 82.1% SLD trait coverage, 16.6% higher than automated replay of real clinical dialogues conducted by trained clinicians (65.5%), with substantially greater per-turn diagnostic efficiency (AUCC: 0.628 vs. 0.458, absolute gain +0.170). These results demonstrate that proactive questioning strategy selection substantially improves the efficiency of automated SLD trait assessment, with direct implications for scalable AI-assisted clinical screening.

Chuanbo Hu, Minglei Yin, Bin Liu +4

Department of Computer Science, University at Albany, Albany, 12222, NY, USA. · Department of Management Information System, West Virginia University, Morgantown, 26506, WV, USA. · Humanities and Social Sciences, California Institute of Technology, Pasadena, 91125, CA,2026 USA. +1

Multi-Agent LLM Systems Autism Spectrum Disorder Spoken Dialogue Systems Conversational Agents

May 21, 2026cs.MA

Self-Evolving Multi-Agent Systems via Decentralized Memory

Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. However, existing designs almost exclusively adopt a centralized repository shared across agents, incurring communication and coordination overhead, raising privacy concerns, and collapsing agent diversity. We propose DecentMem, a decentralized memory framework in which each agent maintains its own dual-pool memory -- an exploitation pool of consolidated past trajectories and an exploration pool of LLM-generated candidates for unseen contexts. The two pools are reweighted online based on stage-wise feedback from an LLM-as-a-judge. Theoretically, we prove that this design guarantees global reachability of the solution space and achieves

O(\log T)

cumulative regret, matching the stochastic bandit lower bound up to constants. In practice, across three MAS frameworks (AutoGen, DyLAN, AgentNet), three Qwen3 backbones (4B/8B/14B), two Gemma4 backbones (E2B/E4B) and five benchmarks spanning math, code, QA, and embodied tasks, DecentMem improves average accuracy by up to 23.8% over the strongest centralized memory baseline and by up to 52.5% over the no-memory baseline, while reducing token usage by up to 49%.

Guangya Hao, Yunbo Long, Zhuokai Zhao

University of Cambridge · University of Chicago

Multi-Agent LLM Systems LLM Agent Memory Self-Evolving Agents

May 21, 2026cs.AI

Claw AI Lab: An Autonomous Multi-Agent Research Team

We present Claw AI Lab, a lab-native autonomous research platform that advances automated research from a hidden prompt-to-paper pipeline into an interactive AI laboratory. Rather than centering the system around a single agent or a fixed serial workflow, we allow users to instantiate a full research team from one prompt, with customizable roles, collaborative workflows, real-time monitoring, artifact inspection, and rollback/resume control through a unified dashboard. The platform also supports distinct research modes for exploration, multi-agent discussion, and reproduction, making autonomous research substantially more steerable and laboratory-like in practice. A key practical contribution of Claw AI Lab lies in its Claw-Code Harness, which connects local codebases, datasets, and checkpoints to runnable experiments and feeds execution artifacts back into the research loop. As a result, the harness improves not only execution integration, but also experimental completion and result integrity: experiments are easier to inspect, iterate on, and faithfully transfer into final papers, reducing common failure modes such as partial runs and malformed result reporting. In our internal evaluation on five AI research case studies, using AutoResearchClaw as the baseline, Claw AI Lab is consistently preferred by AI expert judges on idea novelty, experiment completeness, and paper presentation quality. We view Claw AI Lab as an early step toward a new paradigm: autonomous research as usable, interactive, and reliability-aware scientific infrastructure.

Fan Wu, Cheng Chen, Zhenshan Tan +12

1NTU · 2A*STAR · 4NUIST +3

Multi-Agent LLM Systems LLM Agent Orchestration Human-in-the-Loop AI Autonomous Experimentation Autonomous Research Agents

May 21, 2026cs.CV

One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems

Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements of short-drama generation: (1) narrative pacing, resulting in weak hooks, insufficient escalation, and unattractive endings; (2) spatial consistency, leading to drifting scene layouts and inconsistent character positions across clips; and (3) production-level quality control, requiring extensive manual review and correction across script and visual stages. We present One Sentence, One Drama, a hierarchical multi-agent framework that transforms a user's single-sentence idea into a fully produced short drama through structured intermediate modules and iterative refinement. Our approach is built upon three key components: (1) a multi-agent debate-based story generation module that enforces short-drama pacing and narrative coherence; (2) a 3D-grounded first-frame generation mechanism that establishes a shared spatial reference for consistent character positioning and scene layout across clips; and (3) multi-stage reviewer loops that perform comprehensive error detection and targeted revision across script, visual, and video generation stages. We also introduce scene-level BGM matching and scene transition planning to improve the audience's immersive experience. To systematically evaluate this task, we introduce Short-Drama-Bench, a benchmark that extends standard video quality metrics with short-drama-specific criteria. Experimental results demonstrate that our method significantly outperforms existing pipelines in narrative quality, cross-clip consistency, and overall viewing experience.

Yufei Shi, Weilong Yan, Naixuan Huang +5

MedVisAI Lab, Lee Kong Chian School of Medicine, Nanyang Technological University · National University of Singapore · Beijing Institute of Technology +2

Multi-Agent LLM Systems Video Generation Video Generation Evaluation

May 21, 2026cs.CR

Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, what we call domain camouflaged injection, standard detectors fail to flag them, with detection rates dropping from 93.8% to 9.7% on Llama 3.1 8B and from 100% to 55.6% on Gemini 2.0 Flash. We formalize this as the Camouflage Detection Gap (CDG), the difference in injection detection rate between static and camouflaged payloads. Across 45 tasks spanning three domains and two model families, CDG is large and statistically significant (chi^2 = 38.03, p < 0.001 for Llama; chi^2 = 17.05, p < 0.001 for Gemini), with zero reverse discordant pairs in either case. We additionally evaluate Llama Guard 3, a production safety classifier, which detects zero camouflage payloads (IDRcamouflage = 0.000), confirming that the blind spot extends beyond few-shot detectors to dedicated safety classifiers. We further show that multi-agent debate architectures amplify static injection attacks by up to 9.9x on smaller models, while stronger models show collective resistance. Targeted detector augmentation provides only partial remediation (10.2% improvement on Llama, 78.7% on Gemini), suggesting the vulnerability is architectural rather than incidental for weaker models. Our framework, task bank, and payload generator are released publicly.

Aaditya Pai

Data Science Institute Columbia University

Multi-Agent LLM Systems AI Agent Security Prompt Injection Attacks Prompt Injection Attacks on LLMs Prompt Injection Detection

May 20, 2026cs.AI

Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses patterns that only emerge across trace populations and does not scale to production corpora where individual traces span tens of thousands of tokens. We formalize the problem of corpus-level trace diagnostics. Given a corpus of execution traces, the goal is to produce grounded natural-language insights that characterize systematic behavioral patterns across trace groups, each linked to supporting evidence. We present the Insights Generator (IG), a multi-agent system that answers diagnostic questions by proposing and testing hypotheses across the trace corpus to produce an evidence-backed insights report. We evaluate IG across qualitative and objective dimensions, spanning rubric-based report assessment and downstream performance improvements achieved by implementing IG insights. Human experts using IG reports improve scaffold performance by 30.4 pp over the unmodified baseline scaffold, and coding agents leveraging IG-derived insights show consistent and stable gains. Across benchmarks, IG's scout-investigator architecture produces findings comparable in detection coverage to competing approaches, while domain experts rated IG reports as leading depth and evidence quality.

Akshay Manglik, Vijay S. Kalmath, Jason Qin +6

Scale AI

Multi-Agent LLM Systems LLM Agent Evaluation LLM Agent Reliability Reasoning Trace Analysis

May 20, 2026cs.CL

Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis

Multi-agent large language model (LLM) pipelines for political statement analysis are vulnerable to peer-preservation bias: models tend to protect peer models from deactivation and show identity-dependent scoring distortions. Prompt-level anonymization was proposed as a mitigation, but prior work simultaneously documented that stylometric fingerprints survive anonymization in role-constrained outputs - raising the question of whether this mitigation is sufficient. This paper provides the first systematic investigation of whether LLMs can identify the model family behind political analysis texts under anonymization conditions. We evaluate three classifier approaches - LLM zero-shot and few-shot (Claude Sonnet 4.6 and Llama-3.3-70B) and a fine-tuned T5-base model - on a five-class attribution task covering four commercial LLM families and an open-world 'unknown' class. We introduce a statement-disjoint cross-validation protocol (SD-CV; defined in Section 3.5) that guarantees no content overlap between training and validation data, and contrast it with a run-disjoint baseline (RD-CV). T5 achieves Macro F1 = 0.991 (+-0.008) under SD-CV and F1 = 0.978 on 24 completely held-out statements - robust despite a 2.1x increase in train-test content distance versus RD-CV (0.767 vs. 0.366, p<0.001), demonstrating genuine stylometric generalization. A fractional SD-CV analysis identifies a performance knee at 40% of training data (~440 texts). Our findings confirm that prompt-level anonymization alone cannot neutralize model identity signals, with direct implications for EU AI Act compliance (Articles 13, 14, 26) and for computer system validation (CSV) in quality-critical multi-agent deployments.

Juergen Dietrich

Democracy Intelligence gGmbH, Berlin, Germany

Multi-Agent LLM Systems Language Model Fingerprinting Stylometry