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 665

May 9, 2026cs.CL

AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems

LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing work frames this as \emph{post-hoc failure attribution}, diagnosing the responsible agent and step after the trajectory has ended. However, this paradigm forfeits any opportunity to intervene while trajectory is still unfolding. In this work, we introduce AgentForesight, a framework that reframes this problem as online auditing: at each step of an unfolding trajectory, an auditor observes only the current prefix and must either continue the run or alarm at the earliest decisive error, without access to future steps. To this end, we curate AFTraj-2K, a corpus of agentic trajectories across Coding, Math, and Agentic domains, in which safe trajectories are retained under a strict curation pipeline and unsafe trajectories are annotated at the step of their decisive error via consensus among multiple LLM judges. Built on that, we develop AgentForesight-7B, a compact online auditor trained with a coarse-to-fine reinforcement learning recipe that first equips it with a risk-anticipation prior at the failure boundary on adjacent safe/unsafe prefix pairs, then sharpens this prior into precise step-level localization under a three-axis reward jointly targeting the what, where, and who of an audit verdict. Across AFTraj-2K and an external Who&When benchmark, AgentForesight-7B outperforms leading proprietary models, including GPT-4.1 and DeepSeek-V4-Pro, achieving up to +19.9% performance gain and 3

\times

lower step localization error, opening the loop from post-hoc failures detection to enabling deployment-time intervention. Project page: https://zbox1005.github.io/agent-foresight/

Boxuan Zhang, Jianing Zhu, Zeru Shi +2

Rutgers University · The University of Texas at Austin · Purdue University

Multi-Agent LLM Systems AI Agent Monitoring

May 9, 2026cs.AI

Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs

Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output directly. Such routing-only designs provide no mechanism to critique intermediate drafts or support iterative refinement. To address this limitation, we propose a critique-and-routing controller that casts multi-agent coordination as a sequential decision problem. At each turn, the controller evaluates the current draft, decides whether to stop or continue, and, if needed, selects the next agent for further refinement. We formulate this process as a finite-horizon Markov Decision Process (MDP) with explicit agent-utilization constraints, design a composite reward for controller decisions across turns, and optimize the controller via policy gradients under a Lagrangian-relaxed objective. Extensive experiments across multiple heterogeneous multi-agent systems and seven reasoning benchmarks show that our method consistently outperforms state-of-the-art baselines and substantially narrows the gap to the strongest agent, while using it for fewer than 25% of total calls.

Wenzhi Fang, Liangqi Yuan, Guangchen Lan +2

Purdue University · Yonsei University

Multi-Agent LLM Systems Multi-Agent Coordination LLM Routing Multi-Agent Reasoning RL for LLM Agents

May 9, 2026cs.AI

MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction

Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with complex, multi-step real-world tasks that demand domain-specific procedural knowledge. Reusable agent skills, which encapsulate successful problem-solving strategies, offer a natural remedy by enabling agents to build on prior experience. However, curating such skills has largely remained a manual endeavor, requiring human experts to distill rich domain knowledge into actionable guidelines. In this work, we present

\textbf{M}

ulti-agent

\textbf{IN}

duction and

\textbf{D}

eduction for

\textbf{Skill}

s (

\textbf{MIND-Skill}

), a framework that automatically induces generalizable skills from successful trajectories with robust quality guarantees. MIND-Skill consists of an induction agent which is tasked to abstract reusable skills from successful trajectories, and a deduction agent which aims to reconstruct trajectories by following the induced skills. To guarantee the quality of the generated skills, we introduce a reconstruction loss that compares input and reconstructed trajectories, an outcome loss that enforces the correctness of the reconstructed trajectories, and a rubric loss that assesses the documentation quality and regularizes the abstraction level of the generated skills according to predefined criteria. These textual losses are jointly optimized with TextGrad, and the resulting skills are evaluated on held-out tasks unseen during optimization. Experiments on AppWorld and BFCL-v3 show that MIND-Skill consistently outperforms concurrent skill generation methods.

Yixuan Li, Mingshu Cai, Ziyang Xiao +3

1Nanyang Technological University · 2Waseda University · 3Zhejiang University +1

Multi-Agent LLM Systems LLM Agent Skill Learning

May 8, 2026cs.AI

TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples

We present TraceFix, a verification-first pipeline for Large Language Model (LLM) multi-agent coordination. An agent synthesizes a protocol topology as a structured intermediate representation (IR) from a task description, generates PlusCal coordination logic, and iteratively repairs the protocol using counterexamples from the TLA+ model checker (TLC) until verification succeeds. Verified process bodies are compiled into per-agent system prompts and executed under a runtime monitor that rejects out-of-topology coordination operations. On 48 tasks spanning 16 scenario families, all tasks reach full TLC verification; 62.5% pass on the first attempt and none requires more than four repair iterations. State spaces span six orders of magnitude yet verification completes in under 60 s for every task. A 3,456-run runtime comparison shows that topology-monitored execution achieves the highest task completion (89.4% average, 81.5% full) and that runtimes using the verified protocol degrade at roughly half the rate of prompt-only and chat-only baselines when model capability is reduced. A paired ablation under a fixed runtime shows that TLC-verified protocols cut deadlock/livelock (DL/LL) from 31.1% to 14.1%, with the largest separation under fault injection.

Shuren Xia, Qiwei Li, Taqiya Ehsan +1

Rutgers University Piscataway, NJ, USA

Multi-Agent LLM Systems Multi-Agent Coordination Automated Program Repair Formal Verification Runtime Verification

May 8, 2026cs.AI

GASim: A Graph-Accelerated Hybrid Framework for Social Simulation

Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-based agents with numerical agent-based models (ABM). However, this incurs high latency due to expensive memory retrieval and sequential ABM execution. To address this challenge, we propose GASim, a graph-accelerated hybrid multi-agent framework for large-scale social simulations. For core agents driven by LLM, GASim introduces Graph-Optimized Memory (GOM) to replace intensive LLM-based retrieval pipelines with lightweight propagation over a sparse memory graph. For the majority of ordinary agents, GASim employs Graph Message Passing (GMP), substituting sequential ABM execution with parallel updates by fine-grained feature aggregation and Graph Attention Network. We further introduce Entropy-Driven Grouping (EDG) that coordinates this hybrid partitioning, leveraging information entropy to dynamically identify emergent core agents situated in information-diverse neighborhoods. Extensive experiments show that GASim not only delivers a substantial 9.94-fold end-to-end speedup over the traditional hybrid framework but also consumes less than 20% of baseline tokens, significantly reducing costs while preserving strong alignment with real-world public opinion trends. Our code is available at https://github.com/Jasmine0201/GASim.

Xuan Zhou, Yanhui Sun, Hantao Yao +3

University of Science and Technology of China · BASIS International School Park Lane Harbour

Multi-Agent LLM Systems Human Behavior Simulation Agent-Based Modeling Large Language Model-Based Social Simulation Memory-Augmented Agents

May 8, 2026cs.AI

HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization

Large Language Models have recently emerged as a promising paradigm for automated heuristic design for NP-hard combinatorial optimization problems. Despite this progress, existing LLM-based methods typically rely on monolithic workflows constrained by rigid templates, thereby restricting memory-guided exploration and triggering premature convergence to local optima. To design an autonomous and collaborative architecture, we introduce HMACE, a Heterogeneous Multi-Agent Collaborative Evolution framework that reconceptualizes heuristic search as an organizational design problem. HMACE decomposes each evolutionary generation into an autonomous, role-specialized loop with four coordinated agents: a Proposer for strategy exploration, a Generator for executable heuristic synthesis, an Evaluator for empirical assessment, and a Reflector for archive-backed memory update. By coupling behavior-aware retrieval, lightweight candidate filtering, and fitness-grounded archive updates, HMACE guides the search toward diverse and promising heuristic behaviors while avoiding redundant evaluations. Extensive evaluations on representative COPs, including TSP, Online BPP, MKP, and PFSP, show that HMACE achieves a favorable quality-efficiency trade-off compared to state-of-the-art single-agent and multi-agent baselines. In the matched LLM-driven reference comparison, HMACE achieves the lowest average gaps on TSP and Online BPP (0.464% and 0.223%, respectively), while requiring only 0.13M and 0.42M tokens for the two tasks, substantially fewer than the compared baselines.

Yuping Yan, Jirui Han, Fei Ming +2

School of Engineering Westlake University

Multi-Agent LLM Systems Multi-Agent System Optimization Automated Heuristic Design Evolutionary Optimization Large Language Model-Guided Optimization Combinatorial Optimization+1

May 8, 2026cs.MA

Insider Attacks in Multi-Agent LLM Consensus Systems

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange messages and update decisions to reach a shared outcome. However, most existing multi-agent LLM frameworks assume that all participating agents are aligned with the system objective. In practice, a malicious insider may participate as a legitimate member of the group while pursuing a hidden adversarial goal. In this work, we study insider manipulation in multi-agent LLM consensus systems. We formalize the problem as a sequential decision-making task in which a malicious agent seeks to delay or prevent agreement among benign agents. To make attack optimization tractable, we propose a world-model-based framework that learns surrogate dynamics over the latent behavioral states of benign agents and then trains an attacker using reinforcement learning based on this learned model. Preliminary results show that the trained attacker reduces the benign consensus rate and prolongs disagreement more effectively than the direct malicious-prompt baseline. These results suggest that combining latent world models with reinforcement learning is a promising direction for adaptive insider attacks in language-based multi-agent systems.

Xiaolin Sun, Zixuan Liu, Yibin Hu +1

Department of Computer Science, Tulane University, New Orleans, United States of America.

Multi-Agent LLM Systems Multi-Agent Systems Multi-Agent Consensus Multi-Agent System Security

May 7, 2026cs.LG

Dual-Agent Co-Training for Health Coaching via Implicit Adversarial Preference Optimization

Motivational-interviewing-based health coaching is an effective approach for improving mental health and promoting healthy behavior change. However, the scarcity of trained human coaches and the high cost of coaching services make such support inaccessible to many people who could benefit from it. This motivates the development of AI health coaches that can provide scalable and affordable support. Existing methods typically optimize only one side of the interaction: they either train a dialogue agent against a fixed client environment or train a client simulator against a fixed assistant. This one-sided setup can limit exploration of the interaction space and may be inefficient at developing the capabilities required by the target agent and pushing its performance boundaries. In this paper, we propose a dual-agent framework that interactively co-trains both the health coach agent and the client simulator. The coach is optimized with DPO using Pareto-dominant response pairs identified by a multi-dimensional LLM judge. In turn, the client is trained adversarially by reversing these preferences, inducing an implicit adversarial training dynamic. We further show that this co-training process admits a natural stochastic-game interpretation. Extensive experiments demonstrate that our method effectively improves coaching quality across several important dimensions.

Da Long, Lingyi Fu, Diya Michelle Rao +3

Kahlert School of Computing University of Utah · Department of Health and Kinesiology University of Utah

Adversarial Training Multi-Agent LLM Systems Emotional Support Conversation LLM Agent Training

May 7, 2026cs.LG

Conformal Agent Error Attribution

When multi-agent systems (MAS) fail, identifying where the decisive error occurred is the first step for automated recovery to an earlier state. Error attribution remains a fundamental challenge due to the long interaction traces that large language model-based MAS generate. This paper presents a framework for error attribution based on conformal prediction (CP) which provides finite-sample, distribution-free coverage guarantees. We introduce new algorithms for filtration-based CP designed for sequential data such as agent trajectories. Unlike existing CP algorithms, our approach predicts sets that are contiguous sequences to enable efficient recovery and debugging. We verify our theoretical guarantees on a variety of agents and datasets, show that errors can be precisely isolated, then use prediction sets to rollback MAS to correct their own errors. Our overall approach is model-agnostic, and offers a principled uncertainty layer for MAS error attribution. We release code at https://github.com/layer6ai-labs/conformal-agent-error-attribution.

Naihe Feng, Yi Sui, Shiyi Hou +2

Dalhousie University · Halifax, NS, Canada · Layer 6 AI +1

Agent Failure Analysis AI Agent Reliability Multi-Agent LLM Systems Conformal Prediction

May 7, 2026cs.AI

MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems

Large language model (LLM)-based Multi-agent systems (MAS) have shown promise in tackling complex collaborative tasks, where agents are typically orchestrated via role-specific prompts. While the quality of these prompts is pivotal, jointly optimizing them across interacting agents remains a non-trivial challenge, primarily due to the misalignment between local agent objectives and holistic system goals. To address this, we introduce MASPO, a novel framework designed to automatically and iteratively refine prompts across the entire system. A core innovation of MASPO is its joint evaluation mechanism, which assesses prompts not merely by their local validity, but by their capacity to facilitate downstream success for successor agents. This effectively bridges the gap between local interactions and global outcomes without relying on ground-truth labels. Furthermore, MASPO employs a data-driven evolutionary beam search to efficiently navigate the high-dimensional prompt space. Extensive empirical evaluations across 6 diverse tasks demonstrate that MASPO consistently outperforms state-of-the-art prompt optimization methods, achieving an average accuracy improvement of 2.9. We release our code at https://github.com/wangzx1219/MASPO.

Zhexuan Wang, Xuebo Liu, Li Wang +4

Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China.

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Collaboration Prompt Optimization

May 7, 2026cs.AI

NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research

Multimodal neuroimaging analysis often involves complex, modality-specific preprocessing workflows that require careful configuration, quality control, and coordination across heterogeneous toolchains. Beyond preprocessing, downstream statistical analysis and disease classification commonly require task-specific code, evaluation protocols, and data-format conventions, creating additional barriers between raw acquisitions and reproducible scientific analysis. We present NeuroAgent, an LLM-driven agentic framework that automates key preprocessing and analysis steps for heterogeneous neuroimaging data, including sMRI, fMRI, dMRI, and PET, and supports interactive downstream analysis through natural-language queries. NeuroAgent employs a hierarchical multi-agent architecture with a feedback-driven Generate-Execute-Validate engine: agents autonomously generate executable preprocessing code, detect and recover from runtime errors, and validate output integrity. We evaluate the system on 1,470 subjects pooled across all ADNI phases (CN=1,000, AD=470), where all subjects have sMRI and tabular data, with subsets also having Tau-PET (n=469), fMRI (n=278), and DTI (

n=620

). Pipeline ablation studies across multiple LLM backends show that capable models reach up to 100% intent-parsing accuracy, with the strongest backend (Qwen3.5-27B) reaching 84.8% end-to-end preprocessing step correctness. Automated recovery limits manual intervention to edge cases where human review is required via the Human-In-The-Loop interface. For Alzheimer's Disease classification using automatically preprocessed multimodal data, our agent ensemble achieves an AUC of 0.9518 with four modalities, outperforming all single-modality baselines. These results show that NeuroAgent can reduce the manual effort required for neuroimaging preprocessing and enable end-to-end automated analysis pipelines for neuroimaging research.

Lujia Zhong, Yihao Xia, Jianwei Zhang +4

1Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California · 2Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California · 3Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California

Multi-Agent LLM Systems LLM Agent Orchestration Alzheimer's Disease Classification Neuroimaging

May 7, 2026cs.GT

Sustaining Cooperation in Populations Guided by AI: A Folk Theorem for LLMs

Large language models (LLMs) are increasingly used to provide instructions to many agents who interact with one another. Such shared reliance couples agents who appear to act independently: they may in fact be guided by a common model. This coupling can change the prospects for cooperation among agents with misaligned incentives. We study settings in which multiple LLMs each advise a population of clients who participate in instances of an underlying game, creating strategic interaction at the level of the LLMs themselves. This induces a meta-game among the LLMs, mediated through clients. We first analyze the one-shot setting, where shared instructions can change equilibrium behavior only when an LLM may influence more than one role in the same interaction; in such cases, cooperation may emerge, and the effect of client share can be beneficial, harmful, or non-monotone, depending on the base game. Our main result concerns the repeated setting. We prove a folk theorem for LLMs: despite indirect observation and the clients' inability to identify which LLM advised their opponents, all feasible and individually rational outcomes can be sustained as

\varepsilon

-equilibria. The result does not follow from the standard folk theorem and requires new proof techniques. Together, these results show that shared LLM guidance can sustain cooperation among populations of agents even when the underlying incentives are misaligned.

Jonathan Shaki, Eden Hartman, Sarit Kraus +1

Bar-Ilan University, Israel

Multi-Agent LLM Systems Multi-Agent Coordination Game Theory

May 7, 2026cs.AI

Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems

LLM-based multi-agent systems are increasingly deployed for payment workflows, yet prevailing metrics, Task Success Rate (TSR) and Agent Handoff F1-Score (HF1), capture only final outcomes or unordered routing decisions. We introduce the Agentic Success Rate (ASR), a trajectory-fidelity metric that compares observed and expected agent execution sequences at the transition level, decomposing performance into Transition Recall and Transition Precision. Applied to the Hierarchical Multi-Agent System for Payments (HMASP) across 18 LLMs and 90,000 task instances, ASR reveals that 10 of 18 models systematically skip a confirmation checkpoint during payment checkout, a deviation invisible to both TSR and HF1, while 8 models enforce the checkpoint perfectly. Notably, GPT-4.1 exhibits hidden workflow shortcuts despite achieving perfect TSR and HF1, while GPT-5.2 achieves perfect ASR. Prompt refinements and deterministic routing guards guided by ASR diagnostics yield substantial TSR improvements, with gains up to +93.8 percentage points for previously struggling models, demonstrating that trajectory-level evaluation is essential in regulated domains.

Donghao Huang, Joon Kiat Chua, Zhaoxia Wang

School of Computing and Information Systems, Singapore Management University, 80 Stamford Rd, Singapore 178902, Singapore · Research and Development, Mastercard, 4250 Fairfax Dr, Arlington, VA 22203, USA

Financial Services Multi-Agent LLM Systems LLM Agent Evaluation Agentic Workflows

May 7, 2026cs.MA

AgenticPrecoding: LLM-Empowered Multi-Agent System for Precoding Optimization

Precoding is a key technique for interference management and performance improvement in multi-antenna wireless systems. However, existing precoding methods are typically developed for specific system models, objectives, and constraint sets, which limits their adaptability to the heterogeneous and evolving scenarios expected in future 6G networks. To address this limitation, we propose AgenticPrecoding, a universal multi-agent framework that automates end-to-end precoding derivation directly from user-level communication requirements. Specifically, AgenticPrecoding decomposes the derivation process into four coordinated stages: problem formulation, solver selection, prompt upsampling, and code generation, assigning each stage to a specialized agent tailored to its specific reasoning demands. We employ two LoRA-adapted reasoning agents to inject precoding-specific domain knowledge for problem formulation and solver selection, while two general-purpose Large Language Models (LLMs) handle prompt refinement and executable code generation. Furthermore, a feedback-driven refinement mechanism is incorporated to enhance code executability, constraint feasibility, and solution quality. Extensive experiments across 10 representative precoding scenarios demonstrate that AgenticPrecoding achieves superior cross-scenario adaptability compared to conventional optimization-based and LLM-based baselines.

Zijiu Yang, Zixiang Zhang, Shunpu Tang +2

College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China

Multi-Agent LLM Systems Large Language Model-Guided Optimization

May 7, 2026cs.AI

VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?

For years, we have built LLM serving systems like any other critical infrastructure: a single general-purpose stack, hand-tuned over many engineer-years, meant to support every model and workload. In this paper, we take the opposite bet: a multi-agent loop that automatically synthesizes bespoke serving systems for different usage scenarios. We propose VibeServe, the first agentic loop that generates entire LLM serving stacks end-to-end. VibeServe uses an outer loop to plan and track the search over system designs, and an inner loop to implement candidates, check correctness, and measure performance on the target benchmark. In the standard deployment setting, where existing stacks are highly optimized, VibeServe remains competitive with vLLM, showing that generation-time specialization need not come at the cost of performance. More interestingly, in non-standard scenarios, VibeServe outperforms existing systems by exploiting opportunities that generic systems miss in six scenarios involving non-standard model architectures, workload knowledge, and hardware-specific optimizations. Together, these results suggest a different point in the design space for infrastructure software: generation-time specialization rather than runtime generality. Code is available at https://github.com/uw-syfi/vibe-serve.

Keisuke Kamahori, Shihang Li, Simon Peter +1

University of Washington

Multi-Agent LLM Systems LLM Serving AI Coding Agents

May 7, 2026cs.MA

Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems

Optimizing the communication structure of large language model based multi-agent systems (LLM-MAS) has been shown to improve downstream performance and reduce token usage. Existing methods typically rely on randomly sampled training tasks. However, tasks may differ substantially in difficulty and domain, and thus they are not equally informative for updating communication structure, making optimization under limited training budgets often unstable and highly sensitive to the particular training set. To actively identify the most valuable tasks for communication-structure optimization, we propose an ensemble-based information-theoretic task selection framework. The proposed method estimates task informativeness by how much a candidate task changes the distribution over graph parameters, using ensemble Kalman inversion as an efficient and derivative-free approximation of the corresponding Bayesian update. The resulting estimator is especially suitable for black-box and noisy multi-agent systems. To enhance scalability, we construct a compact candidate pool through embedding-based representative selection and combine the informative selection with surrogate modeling and batch Thompson sampling. We validate our method in both benign settings and settings with agent attacks, demonstrating its effectiveness for communication-structure optimization under constrained computational budgets.

Huchen Yang, Xinghao Dong, Dan Negrut +1

University of Wisconsin–Madison

Multi-Agent LLM Systems Multi-Agent System Optimization Active Learning Multi-Agent Communication

May 6, 2026cs.AR

Design Conductor 2.0: An agent builds a TurboQuant inference accelerator in 80 hours

Driven by a rapid co-evolution of both harness and underlying models, LLM agents are improving at a dizzying pace. In our prior work (performed in Dec. 2025), we introduced "Design Conductor" (or just "Conductor"), a system capable of building a 5-stage Linux-capable RISC-V CPU in 12 hours. In this work, we introduce an updated multi-agent harness powered by frontier models released in April 2026, which is able to handle 80x larger tasks, at higher quality, fully autonomously. Following a brief introduction, we examine 4 designs that the system produced autonomously, including "VerTQ", an LLM inference accelerator which hard-wires support for TurboQuant in a 240-cycle pipeline, starting from the TurboQuant arXiv paper. VerTQ includes heavy compute processing, with 5129 FP16/32 units; the design was mapped to an FPGA at 125 MHz and consumes 5.7 mm^2 in TSMC 16FF (8 attention pipes). We review the key new characteristics that enabled these results. Finally, we analyze Design Conductor's token usage and other empirical characteristics, including its limitations.

The Verkor Team, Ravi Krishna, Suresh Krishna +1

The Verkor Team

AI Accelerator Inference Multi-Agent LLM Systems LLM Agent Orchestration FPGA Acceleration LLM Agent Harnesses

May 6, 2026cs.MA

SODE: Analyzing Social Dynamics in LLM Agents

As Large Language Models (LLMs) evolve into interactive agents, understanding their behavioral alignment within human social dynamics becomes essential. While behavioral game theory offers a framework to study these interactions, previous work has predominantly relied on outcome-based metrics such as average scores. This focus overlooks the mechanisms that facilitate sustainable cooperation, as identical scores can be derived from vastly different strategies. To bridge this gap, we introduce SODE (Social Dynamics Evaluation), a framework that evaluates LLM agents across three evolutionary dimensions: Direct Reciprocity for strategy adaptation, Indirect Reciprocity for reputation sensitivity, and Group Dynamics for cooperative resilience. Applying SODE reveals systematic divergences: instruction-tuned models often exhibit "passive compliance" that renders them vulnerable to exploitation, while reasoning models prioritize short-horizon optimization, destabilizing long-term cooperation. Notably, we demonstrate that a "long-horizon framing" can unlock reciprocal capabilities in reasoning models. Thus, SODE offers a systematic, mechanism-grounded benchmark for aligning AI agents with complex human social dynamics.

Inseo Jung, Yoonseok Oh, Kyungryul Back +2

Department of Computer Science, Korea University · Kakao Mobility

Multi-Agent LLM Systems LLM Agent Evaluation AI Agent Benchmarks

May 6, 2026cs.MA

Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation

LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents through temporary texts, such as drafts or chat logs; it is difficult to pinpoint the weaknesses in the generated ideas and how the agents refine them. To this end, we introduce \textbf{Evolving Idea Graphs} (EIG), a graph-based multi-agent scientific ideation framework that can generate high-performance research ideas across various benchmark-native metrics, such as novelty, feasibility, and clarity. Instead of coordinating solely through texts, EIG represents a partially formed proposal as an evolving idea graph, where nodes capture scientific claims and edges encode relations (e.g., support and conflict), enabling unresolved weaknesses to remain identifiable throughout the idea evolving process. Specifically, a learned two-head controller operates over the evolving graph to guide the ideation: one head selects graph edits for agents to execute, while the other decides when the graph is ready for commit as final proposal synthesis. On AI Idea Bench 2025 and LiveIdeaBench, EIG outperforms all compared systems on both automatic benchmark scores and blind expert ratings. Ablations further show that explicit graph state provides the main performance gains, and learned edit-and-commit control adds consistent improvements.

Jiangwen Dong, Bo Li, Wanyu Lin

1The Hong Kong Polytechnic University · 2The Hong Kong University of Science and Technology

Multi-Agent LLM Systems Scientific Hypothesis Generation Large Language Model-Guided Scientific Discovery

May 6, 2026cs.AI

SensingAgents: A Multi-Agent Collaborative Framework for Robust IMU Activity Recognition

Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is a cornerstone of mobile health, smart environments, and human-computer interaction. However, current deep learning-based HAR models often struggle with heavy reliance on labeled data, position-specific ambiguity, and a lack of transparent reasoning. Inspired by the advanced agents framework, which emulates a collaborative agent using Large Language Models (LLMs), we propose SensingAgents, a novel multi-agent system for robust IMU activity recognition. SensingAgents organizes LLM-powered agents into specialized roles: a group of Analyst Agents for position-specific sensor analysis (arm, wrist, belt, pocket), a pair of Advocate Agents that resolves sensor conflicts through dynamic and static dialectical debates, and a Decision Agent that ensures reliability under sensor drift or failure. Evaluation on the Shoaib dataset demonstrates that SensingAgents significantly outperforms state-of-the-art single-agent and multi-agent LLM models, achieving an accuracy of 79.5% in a zero setting--29% higher than existing agent models and 9.4% higher than deep learning baselines--particularly in complex scenarios where multi-sensor data is conflicting or noisy. Our work highlights the potential of multi-agent collaborative reasoning for advancing the robustness and interpretability of ubiquitous sensing systems.

Naiyu Zheng, Tianlong Yu, Haochen Yin +3

City University of Hong Kong Hong Kong · Hubei University China · The Chinese University of Hong Kong Hong Kong +1

Multi-Agent LLM Systems Human Activity Recognition

May 5, 2026cs.CL

Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining

Materials science workflows rely on structured and unstructured data from the vast body of available scientific literature. However, most of the experimental details remain buried in text, tables, graphs and figures. Thus, constructing databases that incorporate this data is a manual, time-consuming, and hard-to-scale process. Multimodal large language models have made it feasible to extract information from text and scientific figures with high speed and accuracy. This opens the possibility of an AI system that can create production-scale material databases. Material Database Agent (MDA) is a modular, multi-agent system architecture for converting research literature into structured databases. MDA accepts article PDFs as input, which are subsequently processed in parallel into markdown files and figures. Multiple sub-agents read these markdown files and figures in parallel to assemble sub-databases for each paper. These sub-databases are then compiled into a single tabular database by an agent. As opposed to using either a rule-based approach or a single-pass pipeline for extracting information, MDA is a specialized architecture for transforming the literature into a database in the field of materials science. More generally, this study provides a basis for positioning multimodal agentic information extraction as a viable means for constructing next-generation scientific databases from the primary literature.

Achuth Chandrasekhar, Omid Barati Farimani, Radheesh Sharma Meda +1

Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Biomedical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA +2

Multi-Agent LLM Systems Document Information Extraction Materials Science

May 5, 2026cs.MA

Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems

Persistent memory is turning language-model-based agents from stateless participants in isolated interactions into state-bearing components of LLM-based multi-agent systems. As memory becomes durable, reloadable, and behavior-shaping across agents, sessions, or versions, a design question arises that is not captured by retrieval accuracy or access control alone: which candidate memories should become shared institutional state? This Viewpoint frames that problem as governed collaborative memory. We argue that memory governance functions as a selection regime, determining which memory variants persist, which remain private, and which are rejected, abstained from, or superseded. We distinguish ungoverned persistence, constitutional or hybrid selection, automatic metric-based selection, and human-ratified artificial selection, emphasizing that these regimes are not a ranking but a design choice over target properties. We then describe a layered architecture that separates agent-local memory, shared institutional memory, archive memory, and project-continuity memory, with provenance and version lineage making selection inspectable. Documented traces from one running LLM-based multi-agent ecosystem illustrate unmanaged false-memory persistence, ratified institutional memory, rejection and revision, identity-preserving expansion, and governance-as-learning. The contribution is a design agenda: persistent LLM-based multi-agent systems should evaluate memory not only for recall and performance, but also for provenance fidelity, selection traceability, epistemic quality, correction pathways, and role preservation.

Diego F. Cuadros, Abdoul-Aziz Maiga, Helen Meskhidze +1

Digital Epidemiology Laboratory, Digital Futures, University of Cincinnati, Cincinnati, OH, USA · Department of Biological Sciences, University of Cincinnati, Cincinnati, OH, USA · Center for Humanities and Technology (CHaT), University of Cincinnati, Cincinnati, OH, USA +2

Multi-Agent LLM Systems LLM Agent Memory Multi-Agent Collaboration Agent Memory Management

May 5, 2026cs.MA

Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing

High-precision CNC machining of free-form aerospace components requires bounded compensations informed by inspection, simulation, and process knowledge. Off-the-shelf large language model (LLM) assistants can generate text, but they do not reliably execute risk-constrained multi-step numerical workflows or provide auditable provenance for high-stakes decisions. We present multi-agent knowledge analysis (MAKA), a human-in-the-loop decision-support architecture that separates intent routing, tools-only quantitative analysis, knowledge graph retrieval, and critic-based verification that enforces physical plausibility, safety bounds, and provenance completeness before recommendations are surfaced for human approval. MAKA is instantiated on a Ti-6Al-4V rotor blade machining testbed by fusing virtual-machining path-tracking error fields, cutting-force and deflection simulations, and scan-based 3D inspection deviation maps from 16 blades. The analysis decomposes deviation into an evidence-linked pathing component, a drift-based wear proxy capturing systematic evolution across parts, a residual systematic compliance term, and a variability proxy for instability-aware escalation. In a three-level tool-orchestration benchmark (single-step through

\geq

3-step stateful sequences), MAKA improves successful tool execution by up to 87.5 percentage points relative to an unstructured single-model interaction pattern with identical tool access. Digital twin what-if studies show MAKA can coordinate traceable compensation candidates that reduce predicted surface deviation from order

10^{-2}

in to approximately

\pm 10^{-3}

in over most of the blade within the simulation environment, providing a pre-deployment verification signal for risk-aware human decision-making.

Danny Hoang, Ryan Matthiessen, Christopher Miller +5

School of Mechanical, Aerospace, and Manufacturing Engineering, University of Connecticut, Storrs, CT, USA · Connecticut Center for Advanced Technology, East Hartford, CT, USA · Quinnipiac University, Hamden, CT, USA +1

Manufacturing Multi-Agent LLM Systems LLM Agent Orchestration Human-AI Decision Making

May 5, 2026cs.AI

QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs

Multi-agent LLM systems on edge devices need to hand off latent context efficiently, but the practical choices today are expensive re-prefill or full-precision KV transfer. We study QKVShare, a framework for quantized KV-cache handoff between agents that combines token-level mixed-precision allocation, a self-contained CacheCard representation, and a HuggingFace-compatible cache injection path. Our current results support a narrower but clearer story than the original draft: on 150 GSM8K problems with Llama-3.1-8B-Instruct, adaptive quantization remains competitive under repeated handoff and shows its clearest gains against uniform quantization in deeper-hop, higher budget settings; for handoff latency, the QKVShare path reduces TTFT relative to full re prefill at every tested context, from 130.7 ms vs. 150.2 ms at nominal 1K context to 397.1 ms vs. 1029.7 ms at nominal 8K context;. Stage timing shows that post-injection generation, not card creation, dominates the current QKVShare latency path. These results position quantized KV handoff as a promising on-device systems direction while also highlighting the need for stronger controller ablations and apples-to-apples runtime comparisons.

Pratik Honavar, Tejpratap GVSL

Mixed-Precision Quantization Multi-Agent LLM Systems KV Caching KV-Cache Management KV-Cache Quantization On-Device Inference

May 5, 2026cs.RO

Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior

Human-AI collaboration requires AI agents to understand human behavior for effective coordination. While advances in foundation models show promising capabilities in understanding and showing human-like behavior, their application in embodied collaborative settings needs further investigation. This work examines whether embodied foundation model agents exhibit emergent collaborative behaviors indicating underlying mental models of their collaborators, which is an important aspect of effective coordination. This paper develops a 2D collaborative game environment where large language model agents and humans complete color-matching tasks requiring coordination. We define five collaborative behaviors as indicators of emergent mental model representation: perspective-taking, collaborator-aware planning, introspection, theory of mind, and clarification. An automated behavior detection system using LLM-based judges identifies these behaviors, achieving fair to substantial agreement with human annotations. Results from the automated behavior detection system show that foundation models consistently exhibit emergent collaborative behaviors without being explicitly trained to do so. These behaviors occur at varying frequencies during collaboration stages, with distinct patterns across different LLMs. A user study was also conducted to evaluate human satisfaction and perceived collaboration effectiveness, with the results indicating positive collaboration experiences. Participants appreciated the agents' task focus, plan verbalization, and initiative, while suggesting improvements in response times and human-like interactions. This work provides an experimental framework for human-AI collaboration, empirical evidence of collaborative behaviors in embodied LLM agents, a validated behavioral analysis methodology, and an assessment of collaboration effectiveness.

Shinas Shaji, Teena Chakkalayil Hassan, Sebastian Houben +1

Institute of AI and Autonomous Systems (A2S), Hochschule Bonn-Rhein-Sieg, Grantham-Allee 20, Sankt Augustin, 53757, Germany. · 3Fraunhofer Institute for Intelligent Analysis and Information SystemsMay (IAIS), Schloss Birlinghoven, Sankt Augustin, 53757, Germany. · 2Division for Systems and Control, Chalmers University of Technology, Chalmersplatsen 1, Gothenburg, 41296, Sweden.

Multi-Agent LLM Systems Theory of Mind LLM Agent Evaluation Embodied AI Human-AI Collaboration

May 5, 2026cs.LG

LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing

Additive manufacturing (AM) continues to transform modern manufacturing by enabling flexible, on-demand production of complex geometries across diverse industries. Fused filament fabrication (FFF) has extended AM to laboratories, classrooms, and small production environments, but this accessibility shifts process-planning responsibility to users who may lack manufacturing expertise. A syntactically valid slicer profile can still encode thermally or geometrically harmful settings, and subtle G-code edits can alter extrusion, cooling, or adhesion before a print begins. Pre-print G-code screening catches accidental or adversarial machine-program errors before material or machine time is wasted. This paper proposes LLM-ADAM as a generalizable LLM framework for pre-print anomaly detection in AM. The framework decomposes the task into three roles: Extractor-LLM maps a G-code file to a structured process-parameter schema; Reference-LLM converts printer and material documentation into aligned operating ranges; and Judge-LLM interprets a deterministic deviation table and G-code evidence to decide whether a part is non-defective or belongs to an anomaly class. Printers, materials, and LLM backbones are interchangeable test conditions, not fixed assumptions. We evaluate the framework on an N=200 FFF G-code corpus spanning two desktop printer families, two materials, and five classes including non-defective, under-extrusion, over-extrusion, warping, and stringing. The best framework configuration reaches 87.5% accuracy, compared with 59.5% for the strongest engineered single-LLM baseline. The results show that structured decomposition, rather than backbone strength alone, is the dominant source of improvement, with defect classes identified at or near ceiling for leading configurations while residual errors concentrate on conservative false alarms for non-defective samples.

Ahmadreza Eslaminia, Chuhan Cai, Cameron Smith +5

Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA · Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA · Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI 48109, USA +1

Multi-Agent LLM Systems Industrial Anomaly Detection Additive Manufacturing Anomaly Detection

May 5, 2026cs.MA

Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems

Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects rather than base-model capability. Existing responses split between cataloguing failure modes empirically and shipping declarative orchestration frameworks as engineering tools; neither delivers a principled mapping from coordination configuration to predictable failure-mode signature. We argue that coordination should be treated as a configurable architectural layer, separable from agent logic and from information access, enabling architectural reasoning rather than only engineering productivity. We instantiate this with an information-controlled design on prediction markets: a single LLM, fixed tools, fixed per-call output cap, and fixed prompt template across five reference coordination configurations, with total compute per question treated as an endogenous architectural output. The Murphy decomposition of the Brier score separates calibration from discriminative power, so configurations leave distinguishable signatures even when aggregate scores coincide. On 100 Polymarket binary markets resolved after the model's training cutoff (claude-opus-4-6) we report Murphy signatures, a cost-quality Pareto frontier, category-conditioned analysis, and a bootstrap power-projection. Three of five pre-specified predictions are upheld in direction; two configurations dominate the Pareto frontier within this regime; exploratory bootstrap intervals separate consensus alignment from others, though pairwise tests do not survive Bonferroni correction at n=100. We also deploy the same configurations as live agents on Foresight Arena under web-search-enabled conditions, as an on-chain replication channel accumulating in parallel. Harness, trace dataset, and production agents are released. We position this as a methodology-validating first instantiation, not a general cross-model claim.

Maksym Nechepurenko, Pavel Shuvalov

Devnull FZCO · Dubai, UAE

Multi-Agent LLM Systems Multi-Agent Coordination Prediction Markets

May 4, 2026cond-mat.mtrl-sci

From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categories: Knowledge Infrastructure, systems that structure, retrieve, synthesize, and validate scientific information; and Action Systems, systems that execute, coordinate, or automate scientific work across computational and experimental environments. The submissions reveal a shift from single-purpose LLM tools toward integrated, multi-agent workflows that combine retrieval, reasoning, tool use, and domain-specific validation. Prominent themes include retrieval-augmented generation as grounding infrastructure, persistent structured knowledge representations, multimodal and multilingual scientific inputs, and early progress toward laboratory-integrated closed-loop systems. Together, these results suggest that LLMs are evolving from general-purpose assistants into composable infrastructure for scientific reasoning and action. This work provides a community snapshot of that transition and a practical taxonomy for understanding emerging LLM-enabled workflows in materials science and chemistry.

Aritra Roy, Kevin Shen, Andrew MacBride +350

Multi-Agent LLM Systems AI Agents for Scientific Discovery LLM Tool Use

May 4, 2026cs.SE

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs depends on both the model weights and the harness around them, which governs what information to store, retrieve, and present to the model. For long-horizon research workflows, the central failure mode is not a visible breakdown but a plausible unsupported success: a long-running agent can produce claims whose evidential support is incomplete, misreported, or silently inherited from the executor's framing. Therefore, we present ARIS as a research harness that coordinates machine-learning research workflows through cross-model adversarial collaboration as a default configuration: an executor model drives forward progress while a reviewer from a different model family is recommended to critique intermediate artifacts and request revisions. ARIS has three architectural layers. The execution layer provides more than 65 reusable Markdown-defined skills, model integrations via MCP, a persistent research wiki for iterative reuse of prior findings, and deterministic figure generation. The orchestration layer coordinates five end-to-end workflows with adjustable effort settings and configurable routing to reviewer models. The assurance layer includes a three-stage process for checking whether experimental claims are supported by evidence: integrity verification, result-to-claim mapping, and claim auditing that cross-checks manuscript statements against the claim ledger and raw evidence, as well as a five-pass scientific-editing pipeline, mathematical-proof checks, and visual inspection of the rendered PDF. A prototype self-improvement loop records research traces and proposes harness improvements that are adopted only after reviewer approval.

Ruofeng Yang, Yongcan Li, Shuai Li

Shanghai Jiao Tong University · Shanghai Innovation Institute

AI Agent Reliability Multi-Agent LLM Systems LLM Agent Orchestration Autonomous Research Agents LLM Agent Reliability Scientific Claim Verification

May 4, 2026cs.CL

Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studies RL for LLM-based multi-agent systems through orchestration traces: temporal interaction graphs whose events include sub-agent spawning, delegation, communication, tool use, return, aggregation, and stopping decisions. Using this lens, we identify three technical axes. First, reward design spans eight families, including orchestration rewards for parallelism speedup, split correctness, and aggregation quality. Second, reward and credit signals attach to eight credit- or signal-bearing units from token to team; explicit counterfactual message-level credit remains especially sparse in our curated pool. Third, orchestration learning decomposes into five sub-decisions: when to spawn, whom to delegate to, how to communicate, how to aggregate, and when to stop. In our curated pool as of May 4, 2026, we found no explicit RL training method for the stopping decision. We connect academic methods to public industrial evidence from Kimi Agent Swarm, OpenAI Codex, and Anthropic Claude Code. The resulting scale gap is a gap between publicly reported deployment envelopes and open academic evaluation regimes, not independent verification of industrial training traces. We release the artifact at https://github.com/xxzcc/awesome-llm-mas-rl, including an 84-entry tagged paper pool, a 32-record exclusion log, scripted corpus statistics, and a minimal JSON schema for replayable orchestration traces.

Chenchen Zhang

Independent Researcher

Multi-Agent LLM Systems LLM Agent Orchestration Multi-Agent Systems RL for LLM Agents