Multi-Agent LLM Systems

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

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

Jul 13Week of Sep 28

Latest papers 668

Jun 16, 2026cs.MA

Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization

Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment monitoring. However, existing LLM-based data science agents and AutoML systems mainly focus on isolated workflow stages, leaving limited support for lifecycle-level orchestration, artifact governance, human oversight, and drift-aware adaptation. This paper proposes a trustworthy self-composable BDaaS frame work based on LLM-orchestrated multi-agent collaboration. The proposed architecture decomposes the BDaaS lifecycle into specialized agents for data ingestion, data cleaning, feature engineering, AutoML training, model evaluation, MLOps de ployment, monitoring, and drift detection. A central LLM or chestration layer coordinates agent execution, validates interme diate outputs, manages workflow context, and enables dynamic workflow composition. The framework also incorporates shared artifact governance, reproducibility support, human-in-the-loop checkpoints, and drift-aware feedback loops. A prototype-based evaluation is conducted using controlled tabular benchmark datasets with missing values, categorical variables, outliers, class imbalance, and simulated covariate drift. Compared with manual ML, AutoML-only, and single-agent LLM baselines, the pro posed multi-agent BDaaS pipeline achieves competitive predictive performance while improving lifecycle-level reliability, including workflow completion, artifact traceability, deployment readiness, reproducibility, and drift recovery. The results suggest that LLM-orchestrated multi-agent systems can extend conventional AutoML toward trustworthy, adaptive, and production-oriented BDaaS lifecycle automation.

Aueaphum Aueawatthanaphisut, Badri Raj Lamichhane

School of Information, Computer, and Communication Technology Sirindhorn International Institute of Technology, Thammasat University Pathum Thani, Thailand

Multi-Agent LLM Systems Automated Machine Learning

Jun 16, 2026cs.CL

Environment-Grounded Automated Prompt Optimization for LLM Game Agents

LLM agents in interactive environments are highly sensitive to their prompts, yet prompt engineering remains a manual, task-specific process. We introduce an automated prompt optimization framework for LLM agents that decomposes the observation-to-action pipeline into a goal-conditioned descriptor agent and an action selection agent, and iteratively refines each module's prompt through an LLM-driven evolutionary loop guided by environment returns. We propose a behavior analyzer to attribute episode outcomes to specific prompt components, and a mutator to propose targeted revisions to the prompt, before validating them through environment rollouts. We evaluate on all five BabyAI tasks in the BALROG benchmark, comparing our pipeline against BALROG's RobustCoTAgent under both plain and guided prompt initializations. Optimization improves performance consistently across tasks and conditions, without requiring updates to the model weights. On PutNext, a multi-step coordination task where the RobustCoTAgent achieves 0% success, our framework reaches up to 72.5% success rate using the same underlying LLM with optimized prompts. These results suggest that a multi-agent framework, combined with automatic prompt optimization, enhances LLMs without the need for fine-tuning or extensive human supervision.

Rean Clive Fernandes, Lukas Fehring, Theresa Eimer +2

Lamarr institute for ML and AI TU Dortmund University · Leibniz University Hannover · L3S Research Center

Multi-Agent LLM Systems Game-Playing Agents Automatic Prompt Optimization LLM Agents

Jun 16, 2026cs.CL

MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation

While Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large Vision-Language Models, it remains highly susceptible to cross-modal hallucinations, causal fabrications, and sycophancy. Furthermore, existing mitigation pipelines often face an intervention paradox: static rules tend to unnecessarily disrupt accurate generations, whereas leaving the multi-modal reasoning completely unguided allows existing mismatches to cascade into severe logical fabrications. To quantify and mitigate these hallucinations, we propose a Multi-Agent system, MODE-RAG, driven by Variational Free Energy (VFE) and internal attention states to dynamically gate interventions. High-risk queries are routed to five stage-specific agents, integrating Monte Carlo Tree Search (MCTS) for rigorous causal derivation and logit perturbations to penalize sycophancy. Dedicated Correction and Overseer agents ensure formatting stability and perform post-hoc factual verification. To objectively evaluate our approach, we introduce ModeVent, a challenging subset derived from the MultiVent dataset. Extensive experiments indicate that our system effectively reduces hallucination rates and logical fabrication, significantly improving the robustness of M-RAG systems.

Zehang Wei, Jiaxin Dai, Jiamin Yan +1

School of AI and Automation, Huazhong University of Science and Technology, China · School of Computer Science & Tech, Huazhong University of Science and Technology

Multimodal RAG Multi-Agent LLM Systems Multimodal Hallucination Multimodal Model Evaluation VLM Hallucination Mitigation

Jun 15, 2026cs.LG

Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems

Multi-agent LLM systems share state through memory stores, vector indices, and tool registries. We model such sharing as long-running read-generate-write operations under deterministic-generation semantics -- the regime durable-execution engines enforce by deterministic replay -- and formalize four concurrency anomalies in TLA+: stale-generation, phantom-tool, causal-cascade, and tool-effect reordering, structural analogues of classical isolation anomalies, each with a TLC counter-example. The exclusion lattice over these anomalies is trivial; the contribution is the mechanically verified realizability and strict separation of one maximal chain within it,

L_0 \subsetneq \cdots \subsetneq L_4

, to our knowledge the first machine-checked consistency hierarchy for such runtimes. A development of 274 Verus obligations (zero assume, zero admit; trust base: two structural axioms and a mutex correspondence) proves the detectors sound and complete against the specifications and each runtime its avoidance set. Three deployed Rust runtimes realize L0-L1 (pessimistic locking, serializable snapshot isolation, default-SI), each verified against stale-generation and refined to its state machine; L2-L4 are exec-mode-verified with dependency-free prevention twins (A3, A6, A2: 0/1000 versus 1000/1000), and L2 is run live across three model families (A3 prevented in all 120 retracted sessions). We reproduce a silent lost update in ByteDance's deer-flow, formalizing its fix as a verified

L_0 \to L_1

refinement, and exhibit tool-effect reordering in LangGraph's ToolNode on unmodified output, removed by an L3 commit-order sequencer. The verified detector, refinements, and realizability artifacts are the contribution; the phenomena and lattice are classical.

Sajjad Khan

independent researcher

Multi-Agent LLM Systems Formal Verification Consistency Models

Jun 15, 2026cs.AI

Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification

Accurate Harmonized Tariff Schedule (HTS) code classification is essential for customs clearance, duty assessment, trade statistics, and regulatory compliance in maritime logistics. However, exact HTS classification remains challenging because product descriptions are often short, incomplete, or ambiguous, while correct classification depends on hierarchical tariff structures, legal notes, and jurisdiction-specific rules. This paper proposes an agentic large language model (LLM) framework for Canadian 10-digit HTS code classification in smart-port and maritime logistics environments. The framework integrates multi-agent information retrieval, semantic retrieval over official tariff documents, evidence-grounded reasoning, consensus-based validation, element-wise voting across hierarchical code components, confidence estimation, and human-in-the-loop escalation. We evaluate the framework on a private dataset of 3,300 domain-expert-labeled product records collected from logistics and delivery contexts. Experimental results show that exact 10-digit classification remains difficult even for advanced LLMs, with performance decreasing from coarse chapter-level prediction to fine-grained tariff and statistical suffix assignment. These findings demonstrate the need for evidence-grounded, uncertainty-aware, and human-centered classification workflows rather than fully autonomous single-step prediction. The proposed framework supports more interpretable, accountable, and compliance-oriented HTS classification for maritime logistics and smart-port operations. Our code is available at https://github.com/Analytics-Everywhere-Lab/hts.

Truong Thanh Hung Nguyen, Khanh Van Quynh Nguyen, Hoang-Loc Cao +5

Analytics Everywhere Lab, University of New Brunswick, Canada · University of Economics Ho Chi Minh City, Vietnam

Hierarchical Classification Multi-Agent LLM Systems LLM Grounding

Jun 15, 2026cs.CL

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused on lecture content automation and simulations, which often fall short of modelling multimodal and embodied instructional methods tailored for the individual learner. To this end, we propose LectūraAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, LectūraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents through research, planning, review, and embodied delivery of lecture contents that adapt to a learner's needs. The framework offers three main contributions: (1) a hierarchical multi-agent architecture for end-to-end personalized learning; (2) an adaptive embodied teaching mechanism, wherein the ProfessorAgent executes visible and pedagogically motivated teaching actions (e.g., handwrite, highlight, underline, etc.) over contents in a teaching environment; and (3) a Teaching Action-Speech Alignment (TASA) algorithm that employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. We evaluate LectūraAgents on diverse courses at high school, undergraduate, and graduate levels using sample-specific rubric-based analysis; with generated lecture materials and teaching actions assessed and validated by expert educators. Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches, positioning LectūraAgents as a pedagogically well-grounded framework for personalized learning at scale.

Jaward Sesay, Yue Yu, Siwei Dong +1

Beijing Institute of Technology · Peking University · Beijing Academy of Artificial Intelligence

Multi-Agent LLM Systems Intelligent Tutoring Systems Educational Technology AI in Education Embodied AI Teacher-Student Learning

Jun 15, 2026cs.AI

State-Grounded Multi-Agent Synthetic Data Generation for Tool-Augmented LLMs

Training tool-augmented LLM agents requires large corpora of multi-turn, tool-grounded conversational data that is expensive to annotate, privacy-constrained in production settings, and largely absent from public datasets. We present StateGen, a synthetic data generation platform that produces scored, reasoning-trace-rich training conversations by orchestrating a four-role LLM loop: a persona-conditioned user simulator, an agent under test, a state-grounded tool simulator, and a multi-axis LLM judge. The key architectural contribution is an authoritative state manager that maintains a structured world-state object across turns, enforcing a backend-is-truth invariant that eliminates the dominant class of tool-call hallucinations by construction. StateGen extends naturally to hierarchical multi-agent settings by declaring sub-agents as tools, all sharing a single state object. We report results on 64,698 evaluated conversations across three production corpora: tool-call hallucination scores reach 9.66/10, the system supports persona-driven variation via a 23-dimensional trait vector, and a cleanly separated train and golden evaluation set split confirms the data is not memorization bait (per-criterion gap analysis). Comparison with eight external systems shows that no single publicly available platform combines multi-turn generation, state-grounded tool simulation, hierarchical multi-agent support, and built-in judge scoring.

Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu +10

PayPal AI

Multi-Agent LLM Systems Tool-Augmented Language Model Agents LLM Tool Use LLM Agent Training Synthetic Data Generation for Language Models

Jun 14, 2026cs.MA

DeepRoot: A KG-Coordinated Multi-Agent System for Therapeutic Reasoning over Historical Medical Texts

Historical medical archives and traditional medicines hold immense potential for drug discovery and remain a primary source for current drug development. However, pre-ontological prose and idiosyncratic taxonomies prevent the standardization and medical modernization of the data for use in current biomedical pipelines. Furthermore, no existing LLM agent system, whether tool-calling, retrieval-augmented, or agentic deep-research, can convert such text into verifiable drug-discovery leads at scale. We close this gap with DeepRoot, a multi-agent LLM system that jointly builds and utilizes a verified knowledge graph, showing that grounding and reasoning -- often conflated -- are separable axes the system can compose for therapeutic reasoning. Applied to the Shen Nong Ben Cao Jing, DeepRoot recovers

10

of

21

held-out compound-disease treatment pairs at R@

20

(

47.6\%

vs

4.8\%

for a raw corpus LLM and

\sim\!2.4\%

random) and dominates an LLM-as-judge audit for reasoning quality over baseline LLMs and LLMs with direct tool-call access to the same APIs DeepRoot itself queries. Tool-using LLMs hallucinate evidence on

87\%

of claims, versus 7-10% for DeepRoot. Graph-only inference hallucinates

0\%

but ranks lowest on reasoning coherence; DeepRoot KG+LLM is the only condition to win on both axes, pointing toward a route for systematic mining and repurposing of historical medical knowledge.

Zijian Carl Ma, Sean J. Wang, Sijbren Kramer +1

Department of Bioengineering · Stanford University · Amazon AWS AI

Historical Document Analysis Multi-Agent LLM Systems AI Agents for Scientific Discovery Knowledge Representation Knowledge Graph Question Answering LLM Agent Reliability+2

Jun 13, 2026cs.CL

Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering

Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Method: We designed a multi-agent peer-reviewed reasoning method in which multiple LLM agents independently generate chain-of-thought reasoning with candidate answers, then act as peer reviewers to evaluate each other's reasoning for factual correctness and logical soundness. The highest-rated reasoning chain is selected to produce the final answer. Experiments were conducted with five state-of-the-art LLMs (Llama-3.1-8B, Qwen2.5-7B, Phi-4, DeepSeek-LLM-7B, GPT-oss-20B) on three benchmark datasets: HeadQA, MedQA-USMLE, and PubMedQA. Performance was compared against single-model chain-of-thought reasoning and chain-of-thought-based majority voting. Results: Peer-reviewed reasoning consistently outperformed both baselines. The best model combination achieved an average accuracy of 0.820 across datasets, exceeding the strongest single model (0.777) and majority voting ensembles (up to 0.789). The method also scaled effectively with more participating models, while peer assessments reliably distinguished high- from low-quality reasoning chains. Conclusion: The proposed multi-agent peer-reviewed reasoning method enables LLMs to act as both solvers and evaluators, yielding superior performance in MedQA. By emphasizing reasoning quality rather than answer agreement alone, this approach improves accuracy, interpretability, and robustness, offering a promising direction for trustworthy biomedical AI systems.

Zaifu Zhan, Shuang Zhou, Rui Zhang

Department of Electrical and Computer Engineering, University of Minnesota, 200 Union St SE, 55455, Minneapolis, MN, United States · Division of Computational Health Sciences, Department of Surgery, University of Minnesota, 420 Delaware St SE, 55455, Minneapolis, MN, United States

Multi-Agent LLM Systems LLM Answer Verification Medical QA Multi-Agent Reasoning Clinical Language Model Evaluation

Jun 13, 2026cs.DC

CoAgent: Concurrency Control for Multi-Agent Systems

Multi-agent LLM systems -- coding agents, devops agents, document agents -- now routinely run several agents in parallel against the same git tree, Kubernetes cluster, or document. As soon as two of them mutate shared state, they enter the regime classical concurrency control has studied for decades, but classical mechanisms fit LLM agents poorly. A single agent transaction spans minutes of inference, read sets are broad and opaque rather than statically inferable, and the live state agents act on admits neither fork nor buffer, so writes take effect the moment they execute. Locks block long inference intervals; OCC abort-and-retry discards minutes of work on every conflict. This paper builds concurrency control on a capability classical transactions lack: the LLM inside each agent can judge whether a conflicting write invalidates its plan, and can repair exactly the operations that depended on it. Control therefore turns advisory: the runtime informs, the agent repairs. Our protocol, MTPO (Monotonic Trajectory Pre-Order), fixes a serialization order at launch, serves each read the order-filtered value, and applies writes speculatively in place; a one-way notification asks an affected reader to re-judge and patch its plan, while the framework mechanically undoes and reorders misplaced writes through the saga-style inverse each tool registers in advance. At quiescence the run is serializable in the pre-decided order. We realize MTPO as CoAgent, toolcall middleware whose privileged ToolSmith grows footprint-declared, undoable tools online. On ten contended workloads, CoAgent stays within 5% of serial correctness at a

1.4\times

speedup and near-serial token cost, where 2PL and OCC surrender nearly all concurrency gains; on a bash-only target system, it grows a 25-tool library online and lifts the task pass rate from 45/71 to 63/71 at

0.80\times

the time and

0.86\times

the cost.

Hongtao Lyu, Dingyan Zhang, Mingyu Wu +2

Shanghai Jiao Tong University China

Multi-Agent LLM Systems Multi-Agent Coordination Multi-Agent Systems

Jun 13, 2026cs.AI

Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation

We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system converts user intent into structured API calls, enabling efficient access to satellite imagery and environmental datasets. The architecture integrates three agents: Guardrail for safety and policy enforcement, General-QA for intent interpretation, and Recommender-Analyst for schema-aware API call generation. This coordinated design ensures reliable, semantically aligned interaction with external data services. The modular framework is portable across platforms through API schema substitution and supports applications in environmental monitoring, disaster response, and climate analysis. It establishes a scalable interface between user intent and geospatial infrastructure, enabling streamlined and automated Earth observation workflows. Preliminary experiments under adversarial multi-turn settings show that prompt-level safety instructions improve robustness, although rare high-impact failures persist in API manipulation scenarios and highlight the need for adaptive, system-level defenses that balance safety, usability, and cost efficiency, which motivates the use of our intercept-level Guardrail agent.

Kyle Gao, Joel Cumming, Jonathan Li +2

Dept. of Systems Design Engineering, University of Waterloo, Waterloo, ON, N2L 3G1, Canada · SkyWatch, Kitchener, ON, N2H 2G8, Canada · Dept. of Geography and Environmental Management, University of Waterloo, Waterloo, ON, N2L 3G1, Canada +1

Multi-Agent LLM Systems LLM Tool Use Information Retrieval LLM Safety Evaluation LLM Agent Safety

Jun 13, 2026cs.LG

TriAdReview: Triangular Adversarial Review Architecture for Multi-Model Technical Document Generation

Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage. We propose TriAdReview, a triangular adversarial review architecture that employs two independent reviewer models (engineering and boundary perspectives) and a triangular judging mechanism to iteratively improve a generator model's output. We evaluate TriAdReview across five benchmark tasks - architecture design, code generation, proposal review, security audit, and requirements analysis - using three configurations: single model (baseline), dual model (single review), and triple model (full system). Results across 75 experiments (n=5 per cell) show that the triple model configuration achieves a 10.1% overall improvement over the single model baseline (26.2 vs. 23.8 out of 50; p<0.05, paired t-test), with particularly strong gains on security audit (+27.6%), code generation (+20.8%), and architecture design (+15.6%). A second scorer (mimo-v2.5-pro) confirms the direction with a smaller effect (+2.7%), suggesting moderate inter-rater agreement. However, the system shows a -7.5% degradation on requirements analysis, revealing that adversarial review architectures have a structural bias toward simplification that is counterproductive for completeness-oriented tasks. We analyze this boundary condition through a task-type framework and demonstrate that reviewer prompt adaptation partially mitigates the issue. Our findings provide the first empirical characterization of when multi-model adversarial review helps versus harms, with implications for the design of collaborative AI systems.

Zhiqiang Zhou, Junliang Dai, Xu Ling

Hunan Chemical Industry Vocational and Technical College, Hunan, China

Multi-Agent LLM Systems LLM Evaluation LLM Security Text Generation

Jun 12, 2026cs.MA

Resilient Consensus in Agentic AI

Large language model (LLM) agents are increasingly deployed in multi-agent systems where they must coordinate and agree on shared decisions. We ask whether classical resilient consensus theory, developed for deterministic agents, transfers to LLM agents that may behave adversarially. Framing LLM agreement as a Byzantine consensus game, we run controlled experiments on complete and general communication graphs. We find that prompted LLM agents fail to reach agreement that is achievable in principle: consensus can fail even in settings where classical theory guarantees that a convergent algorithm exists, and this failure persists across temperatures and horizons. At the same time, wrapping the agents with classical resilient consensus filters improves agreement. The benefit of filtering depends on how much robustness the underlying topology already provides. Our results suggest that classical resilient consensus theory is a useful lens for the safety of agentic AI.

Sribalaji C. Anand, George J. Pappas

1KTH, Sweden. · University of Pennsylvania, United States.

Multi-Agent LLM Systems Multi-Agent Consensus LLM Agent Safety LLM Agent Reliability

Jun 12, 2026cs.RO

DynaHMRC: Decentralized Heterogeneous Multi-Robot Collaboration for Dynamic Tasks with Large Language Models

Large language models (LLMs) provide robots with richer task understanding and adaptability, making them promising for coordinating heterogeneous multi-robot systems in long-horizon tasks. Despite this potential, several challenges remain underexplored: (1) Centralized LLM schedulers scale poorly as team size and environmental complexity increase. A single model must process excessive contextual information, and long-context approximation may degrade reasoning quality; (2) Existing task formulations insufficiently consider dynamic settings, while robust adaptation to evolving task conditions is essential for real-world deployment; (3) Domain-specific data scarcity limits specialized robotic reasoning, making proprietary general-purpose models inefficient for expert tasks. To address these limitations, we propose DynaHMRC, a decentralized framework in which each robot acts as a role-aware LLM agent. This design mitigates the single-model context bottleneck and supports flexible collaboration across heterogeneous team configurations. DynaHMRC organizes collaboration as a four-stage closed-loop process: self-description, task allocation with leadership bidding, leader election, and reflective execution, supported by executable robot interfaces. We further develop a benchmark covering three task families, four dynamic variations, and six team configurations to systematically study dynamic task modeling. In addition, we conduct an empirical analysis to guide the construction of domain-specific expert datasets and fine-tune pretrained LLMs to improve specialized competence. Experiments show that DynaHMRC achieves higher success rates than strong baselines with fewer action and communication steps, while demonstrating promising scalability trends as team size grows within the evaluated settings.

Wenhao Yu, Yu'ang Xie, Yifan Duan +5

University of Science and Technology of China (USTC) · University of Macau (UM)

Multi-Agent LLM Systems Multi-Robot Coordination Multi-Robot Task Allocation

Jun 12, 2026cs.AI

Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows

Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with modern structured agent workflows, in which independent branches explore subtasks, retrieve evidence, or generate candidate solutions before a final synthesis step. Existing systems typically merge these branches by concatenating their textual outputs, which discards the parallel structure and incurs redundant prefill computation. In this work, we introduce Parallel-Synthesis, a plug-and-play framework that enables a synthesizer to directly consume the KV caches produced by parallel worker agents. Parallel-Synthesis combines a cache mapper that calibrates independently generated branch caches with a fine-tuned synthesizer adapter that enables generation from this non-sequential cache interface. We train Parallel-Synthesis using data that exposes the synthesizer to parallel cache contexts, teaches aggregation across cached branches, and distills reasoning behavior from standard text-concatenation-based synthesis. Across nine downstream datasets spanning math, science QA, code generation, GAIA, and multi-agent database diagnosis, Parallel-Synthesis matches or outperforms text-based synthesis on seven datasets and remains close on the other two. It also reduces time-to-first-token by 2.5x-11x, suggesting that direct cache-based synthesis is a promising interface for more native and efficient synthesis over parallel agent branches.

Shikun Liu, Mufei Li, Dongqi Fu +5

1Georgia Institute of Technology · 2Meta

Multi-Agent LLM Systems KV-Cache Management LLM Agent Workflow Optimization LLM Inference Acceleration

Jun 12, 2026cs.LG

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems

Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights. Extending this paradigm to multi-LLM agentic systems is crucial: existing methods suffer from inaccurate credit assignment and lack convergence guarantees. We propose \textbf{G}raph-based \textbf{T}arget \textbf{B}ack-\textbf{P}ropagation (GTBP), a context adaptation framework for agentic workflows modeled as directed acyclic graphs. GTBP propagates local target outputs backward through the workflow graph and uses target--output discrepancies to guide a stage-wise prompt update mechanism. Theoretically, we show that GTBP's stage-wise prompt updates become stable over iterations, and that a sufficiently capable LLM optimizer can decrease the overall objective. Empirically, GTBP consistently outperforms strong baselines across three benchmarks while maintaining comparable computational cost.

Tan Zhu, Tong Yao, Kananart Kuwaranancharoen +4

Retail Intelligence, Walmart Global Tech, Sunnyvale, CA, USA

Multi-Agent LLM Systems Large Language Model-Guided Optimization LLM Agent Orchestration Automatic Prompt Optimization

Jun 12, 2026cs.LG

Trust but Verify: Mitigating Medical Hallucinations via Post-Hoc Adversarial Auditing and Multi-Agent Feedback Loops

Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved. This study examine whether LLMs recommend recently banned or withdrawn pharmaceuticals when answering clinical questions and tests an agent-based method for reducing such errors. We developed a five-agent "Trust but Verify" system using a single LLM backbone. To measure regulatory knowledge obsolescence, we created an adversarial dataset of 103 clinical MCQs where historically correct answers now refer to banned substances. This scale ensures statistical significance across various therapeutic classes. We evaluated three open-access model families (GPT-OSS, Llama-3, Falcon-3) under vanilla and agentic conditions. Performance was measured via pointwise score, label accuracy, Hallucination Error Rate (HER), and Component Fidelity (CF) score. We also observed clinical safety regression in proprietary models. In default configurations, all models showed high hallucination rates, consistently selecting banned drugs that matched training data patterns. Our proposed agentic architecture reduced HER by approximately 53% across models. Pointwise scores shifted from -0.25 (unsafe recommendation) toward 0.0 (appropriate refusal). The safety audit intercepted dangerous outputs even when models' parametric knowledge favored the banned substance. The proposed multi-agent framework offers a model-agnostic method for enforcing regulatory compliance that prioritizes patient safety over fluent text generation. Our work demonstrates a practical approach for deploying autonomous AI systems in safety-critical healthcare settings. It shows how real-time regulatory data can be integrated into LLM pipelines to support clinical decision-making.

Muhammad Osama, Maheera Amjad, Zartasha Mustansar +2

Data Science and Machine Learning Lab, SINES, NUST · CEME, NUST

Multi-Agent LLM Systems LLM Hallucination Mitigation LLM Auditing Clinical QA Medical LLMs

Jun 11, 2026cs.SE

Knowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces

Reliable operation of multi-agent large language model (LLM) systems depends on debugging long execution traces, where the few causally decisive events are buried in unstructured logs of messages, routes, memory writes, and tool calls. The standard tool is counterfactual replay (rewind, edit, and re-run the trajectory to measure each event's effect), but its cost grows linearly with the number of candidate events, making exhaustive replay infeasible at scale. We frame trace debugging as a knowledge-based decision-support problem. Each trace is compiled into a structured event knowledge graph over routing, memory, tool-use, uncertainty, and latent evidence, and a calibrated predictor decides where a scarce replay budget should be spent. We do not propose a new replay oracle; we propose a method to predict its results without paying the replay cost. We formulate zero-replay counterfactual-effect prediction: given a trace under a fixed budget, predict which events the oracle would mark high-effect before any replay is performed. BranchPoint-Latent is a lightweight predictor over observable, structural, uncertainty, and latent features of the knowledge graph. Calibrated against a deterministic replay oracle across 37 trace families, a single learning-to-rank gradient-boosted predictor raises per-trace localization (Branch Recall@5) from 0.73 to 0.93 on held-out families at zero oracle-replay cost. Rather than claiming universal dominance, we characterize when cheap graph centrality suffices and when learned evidence is necessary. The result is an auditable, cost-efficient decision-support system for AI-reliability debugging, positioned explicitly on the cost-accuracy frontier with reproducible artifacts.

Dong Ho Kang, Hyeonjeong Cha, Daein Weon

aUstechlab, Republic of Korea · bEwha Womans University, Seoul, Republic of Korea · cKookmin University, Seoul, Republic of Korea

Multi-Agent LLM Systems Counterfactual Prediction LLM Agents LLM Agent Reliability

Jun 11, 2026cs.CL

LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis

Rare diseases affect over

300

million patients across more than

7{,}000

conditions, yet no single hospital encounters enough cases of any one condition for reliable diagnosis. Cross-hospital collaboration could help by allowing a diagnosing institution to use distributed, case-specific diagnostic evidence, but privacy regulations restrict the transmission of identifiable clinical text across institutional boundaries. This setting raises two challenges: existing medical agent systems often rely on textual evidence exchange, while raw latent states such as hidden states and KV caches may still reveal prompt-derived clinical content. We introduce LatentDx, a latent multi-agent communication framework in which hospital agents keep private clinical records and retrieved cases local, and send compact latent KV blocks to a host agent for rare-disease diagnosis. LatentDx supports two deployment settings: same-backbone hospital agents use latent KV distillation, while hospitals with different LLM backbones use cross-family latent alignment. On CrossRare-Bench, a self-built large-scale rare-disease benchmark with hospital-level partitions, LatentDx improves cross-hospital diagnostic performance while reducing reconstructable clinical content relative to raw-latent communication baselines.

Ziqing Wang, Lili Zhao, Kaize Ding

Northwestern University

Multi-Agent LLM Systems Rare Disease Diagnosis Privacy-Preserving ML Multi-Agent Communication

Jun 11, 2026cs.IR

Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance

University students often struggle to navigate complex academic policies, leading to advising bottlenecks and delayed access to critical information. Although large language models (LLMs) offer promise for automated assistance, their tendency toward hallucination and inability to enforce institutional constraints make them unsuitable for high-stakes policy guidance without careful architectural design. We present Carolina Guide, a retrieval-augmented generation (RAG) system for academic policy assistance at the University of South Carolina (USC). The system employs a modular multi-agent pipeline with institutional guardrails to provide citation-supported, policy-grounded answers to student queries while refusing unsafe requests such as course recommendations or personalized advising. We evaluate the system on a 90 query test set across 6 departments, achieving 98.9% retrieval success at the >= 2 threshold (genuinely relevant results) with the first relevant chunk at rank-1 for 98.9% of queries (MRR at 10 for rel >= 2 = 0.989). Through systematic baseline comparisons and ablation studies, we show that each architectural component-MMR reranking, adequate retrieval context (k=20), and citation enforcement-contributes measurable practical value despite limited statistical power at 90 queries. The evaluation of the guardrail on 30 adversarial queries demonstrates Safety F1 of 0.89, correctly refusing 86% of unsafe queries while maintaining 93% coverage of benign queries. These results show that production-ready LLM systems for institutional policy guidance require rethinking standard RAG patterns to prioritize safety, transparency, and departmental autonomy over conversational sophistication.

Ben Torsion, Jun Zhou

University of South Carolina, Columbia, South Carolina, USA · University of South Carolina, Columbia, USA

Multi-Agent LLM Systems LLM Guardrails Agentic RAG RAG Evaluation

Jun 11, 2026cs.AI

Confidence Composition for Multiagent Language Model Systems

Multiagent language model systems, such as collaborative reasoning and debate, produce multiple correlated candidate answers and confidence signals. However, these signals are usually calibrated only at the individual agent level, and provide no principled confidence estimate for the system's final answer. We formulate this as a confidence composition problem where combining confidence across agents and reasoning stages while preserving both selective utility and probabilistic reliability. We study confidence-aware routing and log-odds pooling protocols that select among candidate answers and output a system-level confidence. Across five benchmarks, 30 heterogeneous and homogeneous model pairs, and two confidence estimators, our gated-fusion methods improve AUARC and reduce Brier score over single agent, standard debate, and selective debate baselines, while retaining competitive weighted F1-score as a correctness metric. We further show that our log-odds fusion is overconfident due to correlated intermediate signals. We propose a shared dependence discount that substantially improves reliability while preserving predictions.

Ali Elahi, Michael J. Curry, Barbara Di Eugenio

University of Illinois Chicago

Multi-Agent LLM Systems Probability Calibration Multi-Agent Debate LLM Agent Reliability

Jun 11, 2026cs.RO

Multi-Modal Multi-Agent Robotic Cognitive Alignment enabled by Non-Invasive Consumer Brain Computer Interfaces: A Proof of Concept Exploration

While non-verbal behaviors and expressive movements are essential for natural human-robot interaction, existing methods often overlook a crucial element: the human's internal cognitive state. Frequently, proactive multi-agent systems can interrupt humans at inopportune moments, leading to cognitive overload and decreased task performance. This paper introduces a framework for generating "cognitively aligned" multi-agent interactions, enhancing the ability of robotic systems to contextually defer communications to the user of an agent system during moments of high human mental workload and engagement. We present the design and implementation of a closed-loop architecture that explores the interplay between autonomous task execution and real-time neurophysiological focus. Using a consumer-grade Brain-Computer Interface (BCI), our approach continuously monitors Electroencephalography (EEG) spectral band powers while a human performs an engagement-inducing task. We propose an engagement-driven pipeline where an HTTP-based signaling mechanism places a primary agent's sensory inputs and audio outputs into a holding state upon detecting high engagement. This allows secondary agents to seamlessly process complex, delegated tasks in the background. Once the human's cognitive state returns to a lower cognitive load baseline, the primary agent releases the queued agent message. Our preliminary results demonstrate the feasibility of leveraging real-time signal processing, Large Language Models (LLMs), and physical robotic embodiments to create cognitively-aware, non-intrusive multi-agent systems.

Nataliya Kosmyna, Liz Jenkins, Anoop K. Sinha

GOOGLE, Paradigms of Intelligence, Cambridge, MA, United States · GOOGLE, Paradigms of Intelligence, Mountain View, CA, United States

Multi-Agent LLM Systems Human-Robot Interaction

Jun 11, 2026cs.CY

AgentSociety 2: An Integrated Research Environment for Executable Social Science

AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or laboratory protocols, but integrated social processes involving situated participants, interaction contexts, interventions, and outcomes. Yet a critical link is missing: existing systems either assist isolated research tasks or simulate agents as experimental subjects, leaving the research workflow and simulated society decoupled. Here we introduce AgentSociety 2, an Integrated Research Environment for executable social science. It couples two roles of LLM agents in the same runtime: AI social scientists that coordinate literature grounding, hypothesis generation, experiment design, simulation execution, result interpretation, and manuscript drafting; and silicon participants that generate behavioral responses within configurable social environments. This dual-role design turns hypotheses into auditable agent behaviors, environment rules, interventions, and measurements, thereby supporting an end-to-end workflow. Across seven illustrative studies spanning micro-level social-science laboratory experiments, meso-level dynamics in social media, and macro-level urban scenarios, we demonstrate its capacity to support diverse disciplinary questions, reproduce major qualitative patterns from prior studies, identify informative deviations, and enable large-scale simulations through optimized agent-environment interactions. By preserving human researchers' high-level agency while delegating procedural orchestration to agentic systems, it provides a human-in-the-loop and controllable infrastructure for next-generation computational social science, with broader applications in scalable computational social experimentation and AI-enabled social governance platforms.

Jinghua Piao, Jun Zhang, Haoyu Huang +16

Department of Electronic Engineering, Tsinghua University · School of Environment, Tsinghua University · School of Public Policy and Management, Tsinghua University +2

Multi-Agent LLM Systems AI Agents for Scientific Discovery Human Behavior Simulation Computational Social Science Large Language Model-Based Social Simulation

Jun 11, 2026cs.CL

PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue

Empathetic spoken dialogue systems require not only semantically appropriate responses but also emotionally aligned prosodic expression. However, cascade pipelines often discard acoustic cues during speech-to-text conversion, while end-to-end speech models lack interpretable control over emotion and knowledge integration. To address these challenges, we propose PRISM, a multi-agent framework for empathetic spoken dialogue that decouples speech perception, response generation, and speech synthesis into coordinated components. PRISM introduces a prosody-to-language translation mechanism to stabilize large language model reasoning and enables on-demand invocation of external knowledge tools for empathetic dialogue generation. Experimental results demonstrate that PRISM achieves consistent improvements in empathy, prosodic appropriateness, and text response generation quality across objective and subjective metrics. Our code is available at: https://github.com/Bxzfrm/PRISM.

Wen Zhang, Xiaocui Yang, Zhuoyue Gao +3

School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China

Multi-Agent LLM Systems Spoken Dialogue Systems Speech Prosody Emotion-Aware Dialogue Generation

Jun 9, 2026cs.LG

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet deploy only a single workflow, leaving complementary candidates unused, while query-level methods synthesize a new workflow per query at substantial inference cost. Our motivating analysis shows these paradigms are more complementary than competing: workflows discovered during offline search often solve different subsets of queries, and many queries handled by expensive query-level generation can already be solved by cheaper precomputed workflows. This suggests a different objective: rather than searching for one universally best workflow or regenerating one per instance, we should build a compact bank of reusable, complementary workflows and select among them adaptively at inference time. Doing so requires solving three coupled problems: generating complementary rather than redundant candidates, compressing them into a small deployable portfolio, and assigning each query to the right workflow under a performance-cost trade-off. To this end, we present FlowBank, a three-stage framework for portfolio-based agentic workflow optimization. Diversifying proposes DiverseFlow to steer search toward under-covered queries and produce a high-coverage candidate pool. Curating proposes CuraFlow to compress this pool into a compact portfolio with minimal redundancy. Matching casts deployment as edge-value prediction on a query-workflow bipartite graph and routes each incoming query to the portfolio member with the best predicted utility. Across five benchmarks, FlowBank achieves the highest average score among the evaluated methods while remaining cost-competitive, improving over the strongest automated and handcrafted baselines by 4.26% and 14.92% relative, respectively.

Lingzhi Yuan, Chenghao Deng, Fangxu Yu +3

University of Maryland, College Park · Amazon

Multi-Agent LLM Systems Multi-Agent System Optimization Large Language Model-Guided Optimization Agentic Workflows LLM Agent Workflow Optimization

Jun 9, 2026cs.LG

Cross-Agent Learning Signals Enable Coordinated Role-Decomposed LLM Training

Agentic search systems must coordinate evidence acquisition and response generation, yet existing approaches either couple both roles under a single agent objective or decompose them without disentangling their respective contributions to the final outcome. We introduce DAC (Divide and Cooperate), a role-decomposed training framework that, given task-specific external verification signals, trains a searcher and a generator with role-specific cross-verification rewards. DAC allows the generator to abstain when the retrieved evidence appears insufficient, and uses this decision together with externally evaluated search sufficiency to assign appropriate credit to each role. To prevent degenerate over-abstention, we further introduce hard-positive evidence augmentation, which discourages abstaining on sufficient but hard evidence. Across seven general and multi-hop QA benchmarks and two model backbones, DAC consistently outperforms strong single-agent and multi-agent baselines. Controlled evaluations show that these gains arise from coordinated improvements in both search and generation. Our results highlight the importance of explicitly and properly assigning credit across interacting roles when training agentic search systems.

Jaewan Park, Solbee Cho, Jay-Yoon Lee

Seoul National University

Multi-Agent LLM Systems Multi-Agent Collaboration Agentic RAG LLM Agent Training Multi-Agent Reinforcement Learning

Jun 9, 2026cs.MA

Decentralized Multi-Agent Systems with Shared Context

Multi-agent systems (MAS) can scale large language model agents on long-horizon tasks by running them in parallel, yet existing designs waste much of this parallelism in bubbles: agent time spent waiting on others or redoing a peer's work. These bubbles stem from how agents communicate. Independent agents share nothing and rediscover what their peers have already found; peer-communicating agents wait at synchronous rounds; and under centralized orchestration, the main agent blocks on its sub-agents while progress is relayed. We propose Decentralized Language Models (DeLM), a MAS framework on top of existing agent harnesses that squeezes out these bubbles by replacing the main agent with a shared context and a task queue. Agents asynchronously claim tasks, publish findings as soon as they are available, and build on or correct one another's progress, with every peer's status visible to all. On long-horizon tasks from Terminal-Bench 4.0 and DeepSWE v1.1, and on SWE-bench Verified, DeLM is both more accurate and faster than Codex, Claude Code, their native subagents, and AOrchestra in every setting, improving accuracy by up to 17.5 points over the strongest baseline and running up to 2.49x faster than the harness it builds on. On ProgramBench, where agents rebuild programs from scratch, DeLM makes faster progress than Claude Code and finishes a 120-minute budget up to 19.9 points higher in test pass rate. The code is available on our project website at https://yuzhenmao.github.io/DeLM/.

Yuzhen Mao, Jerry Gu, Aadi Chauhan +3

Stanford University

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

Jun 9, 2026cs.CL

TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning

Spreadsheets and tables are widely used representations for structured data analysis, but effective analysis still requires substantial manual effort and domain expertise. Recent large language model (LLM) agents can automate parts of this process, but they often provide limited transparency into intermediate decisions, rely on implicit assumptions, struggle with multi-table comparison, and repeat similar workflows without adapting to a user's preferences. This paper presents TabClaw, an open-source interactive AI agent for spreadsheet manipulation and table reasoning. Users upload CSV or Excel files and issue natural-language requests; TabClaw clarifies ambiguous intent, exposes an editable execution plan, streams a ReAct-style tool-using analysis loop, dispatches specialist agents for parallel multi-table reasoning, and synthesizes findings with explicit consensus and uncertainty markers. Beyond one-off analysis, TabClaw records completed workflows, extracts persistent user memory, distills reusable skills from repeated tool-use patterns, supports package-style skill import, and upgrades skills from negative feedback. Experiments on spreadsheet manipulation and table reasoning benchmarks show that TabClaw improves executable task completion and reasoning performance while preserving an inspectable user workflow. This paper shows how TabClaw turns spreadsheets and tables into inspectable analytical workflows while gradually personalizing itself to recurring data-analysis tasks. Our code is available.

Mingyue Cheng, Shuo Yu, Daoyu Wang +5

Multi-Agent LLM Systems LLM Agent Skill Learning Tool-Using Agents Spreadsheet Automation LLM Reasoning Data Analysis Agents

Jun 8, 2026cs.AI

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite. Recent work explores a paradigm where a main agent decomposes tasks and dispatches subtasks to subagents, which execute and return only summarized results, conserving the main agent's context budget. However, performing this well requires delegation intelligence: the ability to decompose complex tasks, determine when and what to delegate, and integrate returned results into the ongoing workflow. Training data for this capability is scarce in naturally occurring text, and to our knowledge, how to synthesize such data and train models to acquire this capability remains largely unexplored in the open-source community. To bridge this gap, we present a preliminary exploration targeting deep research, a representative long-horizon agent task. Specifically, we design a harness that guides the model toward high-quality task decomposition and delegation, while constraining subagents to return results properly to support the main agent's workflow. The harness-guided trajectories naturally encode correct delegation decisions, which we use as supervised fine-tuning data to internalize delegation intelligence into model weights. Our resulting model, SearchSwarm-30B-A3B, achieves 68.1 on BrowseComp and 73.3 on BrowseComp-ZH, the best results among all models of comparable scale. We will release our harness, model weights, and training data to facilitate future research.

Pu Ning, Quan Chen, Kun Tao +7

Tsinghua University · Peking University · Ant Group +1

Multi-Agent LLM Systems LLM Agent Orchestration LLM Agent Training Task Decomposition Long-Horizon LLM Agents Autonomous Research Agents

Jun 7, 2026cs.AI

ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems

Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, yet these approaches remain challenged by noisy trajectories, insufficient modeling of memory-skill relations, and reliance on additional training or high-quality supervision. To address these limitations, we propose ConMem, a relation-aware and training-free framework that enables efficient multi-agent adaptation through cross-experience coordination. Specifically, ConMem distills historical interaction trajectories into structured memory cards to capture reusable strategies and cues, organizing them into a relation-aware memory graph. At runtime, ConMem retrieves cards according to task needs and coordinates them through the card graph to resolve strategy conflicts and recover their dependencies. Combined, these modules yield structured and relation-aware guidance, enabling robust, lightweight adaptation in multi-agent systems without additional training. Extensive experiments across multiple benchmarks and mainstream MAS architectures show consistent gains over existing memory architectures, with improved inference-time efficiency through pruning more than 50% of expanded candidates and reducing planning overhead by over 80%. Our codes are available at https://anonymous.4open.science/r/ConMemCode

Zhixun Tan, Qiang Chen, Tairan Huang +2

Central South University · The Hong Kong University of Science and Technology

Multi-Agent LLM Systems Multi-Agent Coordination LLM Agent Memory Graph-Based Agent Memory Memory-Augmented Language Model Agents