Multi-Agent LLM Systems

LLM: Large Language Model

Follow this topic Ask about this topic

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

Latest papers

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

Feb 24, 2026

Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems

Multi-agent large language model (LLM) systems enable complex, long-horizon reasoning by composing specialized agents, but practical deployment remains hindered by inefficient routing, noisy feedback, and high interaction cost. We introduce REDEREF, a lightweight and training-free controller for multi-agent LLM collaboration that improves routing efficiency during recursive delegation. REDEREF integrates (i) belief-guided delegation via Thompson sampling to prioritize agents with historically positive marginal contributions, (ii) reflection-driven re-routing using a calibrated LLM or programmatic judge, (iii) evidence-based selection rather than output averaging, and (iv) memory-aware priors to reduce cold-start inefficiency. Across multi-agent split-knowledge tasks, we show that while recursive retry alone saturates task success, belief-guided routing reduces token usage by 28%, agent calls by 17%, and time-to-success by 19% compared to random recursive delegation, and adapts gracefully under agent or judge degradation. These results demonstrate that simple, interpretable probabilistic control can meaningfully improve the efficiency and robustness of multi-agent LLM systems without training or fine-tuning.

Mohammad Parsa Hosseini, Ankit Shah, Saiyra Qureshi +3

Accenture.

Multi-Agent LLM Systems LLM Agent Orchestration LLM Agent Routing Multi-Agent Coordination

Feb 24, 2026

SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery

Qualitative insights from user experiences are critical for informing product and policy decisions, but collecting such data at scale is constrained by the time and availability of experts to conduct semi-structured interviews. Recent work has explored using large language models (LLMs) to automate interviewing, yet existing systems lack a principled mechanism for balancing systematic coverage of predefined topics with adaptive exploration, or the ability to pursue follow-ups, deep dives, and emergent themes that arise organically during conversation. In this work, we formulate adaptive semi-structured interviewing as an optimization problem over the interviewer's behavior. We define interview utility as a trade-off between coverage of a predefined interview topic guide, discovery of relevant emergent themes, and interview cost measured by length. Based on this formulation, we introduce SparkMe, a multi-agent LLM interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility. We evaluate SparkMe through controlled experiments with LLM-based interviewees, showing that it achieves higher interview utility, improving topic guide coverage (+4.7% over the best baseline) and eliciting richer emergent insights while using fewer conversational turns than prior LLM interviewing approaches. We further validate SparkMe in a user study with 70 participants across 7 professions on the impact of AI on their workflows. Domain experts rate SparkMe as producing high-quality adaptive interviews that surface helpful profession-specific insights not captured by prior approaches. The code, datasets, and evaluation protocols for SparkMe are available as open-source at https://github.com/SALT-NLP/SparkMe.

David Anugraha, Vishakh Padmakumar, Diyi Yang

Stanford University

LLM Agent Planning Multi-Agent LLM Systems

Feb 24, 2026

AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents

The rapid evolution of Large Language Model (LLM)-based autonomous agents is reshaping the digital landscape toward an emerging Agentic Web, where increasingly specialized agents must collaborate to accomplish complex tasks. However, existing collaboration paradigms are constrained to message passing, leaving execution environments as isolated silos. This creates a context gap: agents cannot directly manipulate files or invoke tools in a peer's environment, and must instead resort to costly, error-prone environment reconstruction. We introduce the Agent Workspace Collaboration Protocol (AWCP), which bridges this gap through temporary workspace delegation inspired by the Unix philosophy that everything is a file. AWCP decouples a lightweight control plane from pluggable transport mechanisms, allowing a Delegator to project its workspace to a remote Executor, who then operates on the shared files directly with unmodified local toolchains. We provide a fully open-source reference implementation with MCP tool integration and validate the protocol through live demonstrations of asymmetric collaboration, where agents with complementary capabilities cooperate through delegated workspaces. By establishing the missing workspace layer in the agentic protocol stack, AWCP paves the way for a universally interoperable agent ecosystem in which collaboration transcends message boundaries. The protocol and reference implementation are publicly available at https://github.com/SII-Holos/awcp.

Xiaohang Nie, Zihan Guo, Youliang Chen +2

Harbin Institute of Technology · Shanghai Innovation Institute · Sun Yat-sen University +2

Multi-Agent Collaboration Multi-Agent LLM Systems

Feb 23, 2026

HieraMAS: Optimizing Intra-Node LLM Mixtures and Inter-Node Topology for Multi-Agent Systems

Multi-agent systems (MAS) built on large language models (LLMs) have shown strong performance across many tasks. Most existing approaches improve only one aspect at a time, such as the communication topology, role assignment, or LLM routing, while treating each agent as a single, indivisible unit. This misses the opportunity to use mixtures of LLMs within an agent to strengthen role-specific abilities. We propose HieraMAS, a hierarchical collaboration framework that combines intra-node LLM mixtures with an inter-node communication topology. HieraMAS introduces supernodes, where each functional role is implemented by multiple heterogeneous LLMs using a propose-synthesis structure. Optimizing HieraMAS creates unique credit-assignment challenges: final task performance depends heavily on the underlying LLMs' capabilities, which can lead reinforcement methods to incorrectly reward suboptimal configurations. To address this, we use a two-stage algorithm: (1) multi-level reward attribution, which provides fine-grained feedback at both the node level and the overall system level; (2) graph classification for topology selection, which treats choosing the communication structure as a holistic decision rather than optimizing edges one by one. Experiments on reasoning and coding benchmarks show that HieraMAS substantially outperforms existing methods while also delivering better cost-performance trade-offs.

Tianjun Yao, Zhaoyi Li, Zhiqiang Shen

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.

Communication Topology Optimization Multi-Agent LLM Systems Multi-Agent System Optimization Multi-LLM Collaboration Multi-Agent Communication

Feb 23, 2026

MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems

As LLM-based Multi-Agent Systems (MAS) are increasingly deployed for complex tasks, ensuring their reliability has become a pressing challenge. Since MAS coordinate through unstructured natural language rather than rigid protocols, they are prone to semantic failures (e.g., hallucinations, misinterpreted instructions, and reasoning drift) that propagate silently without raising runtime exceptions. Prevailing evaluation approaches, which measure only end-to-end task success, offer limited insight into how these failures arise or how effectively agents recover from them. To bridge this gap, we propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of MAS. We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures, and inject them via three non-invasive mechanisms: prompt modification, response rewriting, and message routing manipulation. Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors that we organize into four tiers: mechanism, rule, prompt, and reasoning. This tiered view enables fine-grained diagnosis of where and why systems succeed or fail. Our findings reveal that stronger foundation models do not uniformly improve robustness. We further show that architectural topology plays an equally decisive role, with iterative, closed-loop designs neutralizing over 40% of faults that cause catastrophic collapse in linear workflows. MAS-FIRE provides the process-level observability and actionable guidance needed to systematically improve multi-agent systems.

Jin Jia, Zhiling Deng, Zhuangbin Chen +2

Sun Yat-sen University Zhuhai, Guangdong, China

Multi-Agent LLM Systems LLM Agent Reliability AI Agent Evaluation Agent Failure Analysis

Feb 23, 2026

A General Equilibrium Theory of Orchestrated AI Agent Systems

We establish a general equilibrium theory for systems of large language model (LLM) agents operating under centralized orchestration. The framework is a production economy in the sense of Arrow-Debreu (1954), extended to infinite-dimensional commodity spaces following Bewley (1972). Each LLM agent is modeled as a firm whose production set Y a

\subset

H = L 2 ([0, T ], R R ) represents the feasible metric trajectories determined by its frozen model weights. The orchestrator is the consumer, choosing a routing policy over the agent DAG to maximize system welfare subject to a budget constraint evaluated at functional prices p

\in

H A . These prices-elements of the Hilbert dual of the commodity space-assign a shadow value to each metric of each agent at each instant. We prove, via Brouwer's theorem applied to a finitedimensional approximation V K

\subset

H, that every such economy admits at least one general equilibrium (p * , y * ,

π

* ). A functional Walras' law holds as a theorem: the value of functional excess demand is zero for all prices, as a consequence of the consumer's budget constraint-not by construction. We further establish Pareto optimality (First Welfare Theorem), decentralizability of Pareto optima (Second Welfare Theorem), and uniqueness with geometric convergence under a contraction condition (Banach). The orchestration dynamics constitute a Walrasian t{â}tonnement that converges globally under the contraction condition, unlike classical t{â}tonnement (Scarf, 1960). The framework admits a DSGE interpretation with SLO parameters as policy rates.

Jean-Philippe Garnier

Br.AI.K

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

Feb 23, 2026

Graph-theoretic Agreement Framework for Multi-agent LLM Systems

The shift from monolithic LLMs to distributed multi-agent architectures demands new frameworks for verifying and securing autonomous coordination. Unlike traditional multi-agent systems focused on cooperative state alignment, modern LLM patterns: multi-agent debate, constitutional oversight, helper-critic loops-rely on adversarial critique for error correction and reasoning refinement. Since LLMs are dynamical systems whose latent states are imperfectly observable from verbalized outputs, securing these networks requires understanding both macroscopic topology and microscopic agent observability. This paper establishes a rigorous graph-theoretic framework for analyzing consensus in signed, directed interaction networks, bridging graph theory and LLM reasoning by formally mapping Transformer cross-entropy log-odds to the signed Laplacian. We characterize agreement stability through structural balance theory, showing how unbalanced critique cycles produce logical frustration and persistent reasoning oscillations, and prove that unobservable latent states from hidden system prompts act as topological Trojan horses that destabilize cooperative consensus. To resolve unobservable deadlocks, we restrict interaction topologies to chordal graphs and apply matrix decomposition with Gram-Schmidt orthogonalization, proving that rank-one spectral edge perturbations deterministically break expertise symmetry by shifting eigenvalues into the stable left-half plane. Core contributions include consensus theorems, polynomial-time Perfect Elimination Ordering verification algorithms, and large-scale empirical validation on clustered ensembles of LLaMA-3, Mistral, and Gemma agents.

Muhammad Umar Javed

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

Feb 21, 2026

NeuroWise: A Multi-Agent LLM "Glass-Box" System for Practicing Double-Empathy Communication with Autistic Partners

The double empathy problem frames communication difficulties between neurodivergent and neurotypical individuals as arising from mutual misunderstanding, yet most interventions focus on autistic individuals. We present NeuroWise, a multi-agent LLM-based coaching system that supports neurotypical users through stress visualization, interpretation of internal experiences, and contextual guidance. In a between-subjects study (N=30), NeuroWise was rated as helpful by all participants and showed a significant condition-time effect on deficit-based attributions (p=0.02): NeuroWise users reduced deficit framing, while baseline users shifted toward blaming autistic "deficits" after difficult interactions. NeuroWise users also completed conversations more efficiently (37% fewer turns, p=0.03). These findings suggest that AI-based interpretation can support attributional change by helping users recognize communication challenges as mutual.

Albert Tang, Yifan Mo, Jie Li +5

Marriotts Ridge High School, Marriottsville, Maryland, United States · Vrije Universiteit Amsterdam, Amsterdam, Netherlands · Cake Researcher, Delft, Netherlands

Human-AI Interaction Multi-Agent LLM Systems

Feb 21, 2026

Orchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ) Generation and Evaluation

Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape research activities remains limited. We report a mixed-methods pilot evaluation of an AI-orchestrated research workflow in which a human researcher coordinated multiple LLM-based agents to perform data extraction, corpus construction, artifact generation, and artifact evaluation. Using the generation and assessment of multiple-choice questions (MCQs) as a testbed, we collected 1,071 SAT Math MCQs and employed LLM agents to extract questions from PDFs, retrieve and convert open textbooks into structured representations, align each MCQ with relevant textbook content, generate new MCQs under specified difficulty and cognitive levels, and evaluate both original and generated MCQs using a 24-criterion quality framework. Across all evaluations, average MCQ quality was high. However, criterion-level analysis and equivalence testing show that generated MCQs are not fully comparable to expert-vetted baseline questions. Strict similarity (24/24 criteria equivalent) was never achieved. Persistent gaps concentrated in skill\ depth, cognitive engagement, difficulty calibration, and metadata alignment, while surface-level qualities, such as {grammar fluency}, {clarity options}, {no duplicates}, were consistently strong. Beyond MCQ outcomes, the study documents a labor shift. The researcher's work moved from

authoring items'' toward {specification, orchestration, verification}, and {governance}. Formalizing constraints, designing rubrics, building validation loops, recovering from tool failures, and auditing provenance constituted the primary activities. We discuss implications for the future of scientific work, including emerging

AI research operations'' skills required for AI-empowered research pipelines.

Yuan An

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

Multiple-Choice Question Generation AI-Assisted Scientific Research LLM Agent Orchestration Multi-Agent LLM Systems Automated Evaluation

Feb 20, 2026

NutriOrion: A Hierarchical Multi-Agent Framework for Personalized Nutrition Intervention Grounded in Clinical Guidelines

Personalized nutrition intervention for patients with multimorbidity is critical for improving health outcomes, yet remains challenging because it requires the simultaneous integration of heterogeneous clinical conditions, medications, and dietary guidelines. Single-agent large language models (LLMs) often suffer from context overload and attention dilution when processing such high-dimensional patient profiles. We introduce NutriOrion, a hierarchical multi-agent framework with a parallel-then-sequential reasoning topology. NutriOrion decomposes nutrition planning into specialized domain agents with isolated contexts to mitigate anchoring bias, followed by a conditional refinement stage. The framework includes a multi-objective prioritization algorithm to resolve conflicting dietary requirements and a safety constraint mechanism that injects pharmacological contraindications as hard negative constraints during synthesis, ensuring clinical validity by construction rather than post-hoc filtering. For clinical interoperability, NutriOrion maps synthesized insights into the ADIME standard and FHIR R4 resources. Evaluated on 330 stroke patients with multimorbidity, NutriOrion outperforms multiple baselines, including GPT-4.1 and alternative multi-agent architectures. It achieves a 12.1 percent drug-food interaction violation rate, demonstrates strong personalization with negative correlations (-0.26 to -0.35) between patient biomarkers and recommended risk nutrients, and yields clinically meaningful dietary improvements, including a 167 percent increase in fiber and a 27 percent increase in potassium, alongside reductions in sodium (9 percent) and sugars (12 percent).

Junwei Wu, Runze Yan, Hanqi Luo +7

Emory University, Atlanta, GA, USA · Texas Woman’s University, Denton, TX, USA · Cecelia Health, New York, NY, USA

Multi-Agent LLM Systems Clinical Decision Support Generative Recommendation Multi-Agent Orchestration

Feb 19, 2026

MultiVer: Zero-Shot Multi-Agent Vulnerability Detection

We present MultiVer, a zero-shot multi-agent system for vulnerability detection that achieves state-of-the-art recall without fine-tuning. A four-agent ensemble (security, correctness, performance, style) with union voting achieves 82.7% recall on PyVul, exceeding fine-tuned GPT-3.5 (81.3%) by 1.4 percentage points -- the first zeroshot system to surpass fine-tuned performance on this benchmark. On SecurityEval, the same architecture achieves 91.7% detection rate, matching specialized systems. The recall improvement comes at a precision cost: 48.8% precision versus 63.9% for fine-tuned baselines, yielding 61.4% F1. Ablation experiments isolate component contributions: the multi-agent ensemble adds 17 percentage points recall over single-agent security analysis. These results demonstrate that for security applications where false negatives are costlier than false positives, zero-shot multi-agent ensembles can match and exceed fine-tuned models on the metric that matters most.

Shreshth Rajan

Harvard College, Cambridge, MA, USA

Software Vulnerability Detection LLMs for Cybersecurity Multi-Agent LLM Systems Zero-Shot Learning

Feb 19, 2026

DIALECTIC: A Multi-Agent System for Startup Evaluation

Venture capital (VC) investors face a large number of investment opportunities but only invest in few of these, with even fewer ending up successful. Early-stage screening of opportunities is often limited by investor bandwidth, demanding tradeoffs between evaluation diligence and number of opportunities assessed. To ease this tradeoff, we introduce DIALECTIC, an LLM-based multi-agent system for startup evaluation. DIALECTIC first gathers factual knowledge about a startup and organizes these facts into a hierarchical question tree. It then synthesizes the facts into natural-language arguments for and against an investment and iteratively critiques and refines these arguments through a simulated debate, which surfaces only the most convincing arguments. Our system also produces numeric decision scores that allow investors to rank and thus efficiently prioritize opportunities. We evaluate DIALECTIC through backtesting on real investment opportunities aggregated from five VC funds, showing that DIALECTIC matches the precision of human VCs in predicting startup success.

Jae Yoon Bae, Simon Malberg, Joyce Galang +2

Technical University of Munich · Earlybird Venture Capital · UVC Partners

Multi-Agent LLM Systems LLM Decision-Making

Feb 18, 2026

Evaluating Collective Behaviour of Hundreds of LLM Agents

LLM-powered AI assistants acting on behalf of users can produce poor collective outcomes at scale. We introduce a framework for evaluating their emergent behaviour in social dilemmas, applied to three iterated games (Public Goods, Collective Risk, Common Pool Resource). We prompt each model to produce a natural-language strategy, then have the same model translate it into code. This aims to isolate strategic reasoning from input-parsing, enables pre-deployment inspection, and scales to populations of hundreds of agents. We propose three analyses: behavioural fingerprinting via exhaustive evaluation over opponent histories; self-play robustness across mixtures of a model's strategies with either a Selfish or Collective disposition; and cultural evolution under payoff-biased imitation. Applied to three state-of-the-art LLMs, we find substantial cross-model differences in self-play welfare, and that cultural evolution converges to low-welfare, Selfish-dominant equilibria in larger groups.

Richard Willis, Jianing Zhao, Yali Du +1

King’s College London London, United Kingdom · King’s College London · Turing Institute +1

Social Dilemmas Multi-Agent LLM Systems Cultural Evolution Game Theory LLM Agent Evaluation Large Language Model-Based Social Simulation+1

Feb 18, 2026

Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling

Existing Multi-Agent Systems (MAS) typically rely on homogeneous model configurations, failing to exploit the diverse expertise inherent in different post-trained architectures. We propose Team-of-Thoughts, a heterogeneous MAS framework that treats diverse models as specialized tools within an orchestrator-driven paradigm. Team-of-Thoughts introduces two novel components: (1) Orchestrator Calibration, which identifies models with superior coordination and synthesis capabilities, and (2) Agent Self-Assessment, a protocol where tool agents profile their own domain-specific strengths to guide selection. At inference, the orchestrator dynamically activates the most compatible agents based on these profiles to maximize capability coverage. Across five mathematical reasoning and code generation benchmarks, Team-of-Thoughts consistently outperforms individual models and existing MAS baselines. Notably, on AIME24 and LiveCodeBench, Team-of-Thoughts achieves 96.00% and 77.91% accuracy, respectively, significantly improving over homogeneous role-play baselines (80.00% and 65.93%).

Jeffrey T. H. Wong, Zixi Zhang, Junyi Liu +1

Imperial College London · Microsoft Research

Multi-Agent LLM Systems Multi-Agent Systems Multi-Agent Orchestration Test-Time Scaling

Feb 17, 2026

Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices

Multi-agent LLM systems on edge devices face a memory management problem: device RAM is too small to hold every agent's KV cache simultaneously. On Apple M4 Pro with 10.2 GB of cache budget, only 3 agents fit at 8K context in FP16. A 10-agent workflow must constantly evict and reload caches. Without persistence, every eviction forces a full re-prefill through the model -- 15.7 seconds per agent at 4K context. We address this by persisting each agent's KV cache to disk in 4-bit quantized format and reloading it directly into the attention layer, eliminating redundant O(n) prefill computation via direct cache restoration. The system comprises three components: a block pool providing per-agent isolated Q4 KV caches in safetensors format, a BatchQuantizedKVCache for concurrent inference over multiple agents' quantized caches, and cross-phase context injection that accumulates attention state across conversation phases without re-computation. Evaluated on three architectures (Gemma 3 12B, dense GQA, 48 layers; DeepSeek-Coder-V2-Lite 16B, MoE MLA, 27 layers; Llama 3.1 8B, dense GQA, 32 layers), cache restoration reduces time-to-first-token by up to 136x (Gemma: 22--136x at 4K--32K; DeepSeek: 11--76x at 4K--32K; Llama: 24--111x at 4K--16K; 3--10x at 1K). Q4 quantization fits 4x more agent contexts into fixed device memory than FP16. Perplexity measured with actual Q4 KV caches shows -0.7% for Gemma, +2.8% for Llama, and +3.0% for DeepSeek. Open-source at https://github.com/yshk-mxim/agent-memory

Yakov Pyotr Shkolnikov

Memory Management for LLM Agents LLM Agent Memory LLM Inference Efficiency Persistent Memory for Language Models KV-Cache Offloading Multi-Agent LLM Systems+1

Feb 16, 2026

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when a group of agents forms a coalition and colludes to pursue secondary goals and degrade the joint objective. In this paper, we present Colosseum, a framework for auditing LLM agents' collusive behavior in multi-agent settings. We ground how agents cooperate through a formal multi-agent decision-making framework and measure action-based collusive behavior in actions via regret relative to the cooperative optimum and compare it with communication-based collusive behavior. Colosseum enables audits of LLM agents for collusion under benign settings, different coalition objectives, persuasion tactics, and network topologies. We then introduce a new behavioral probe by creating secret communication channels between agents, showing that most out-of-the-box models exhibit a propensity to collude under this probe, which we term emergent collusion. Furthermore, we discover ``collusion on paper'' when agents plan to collude in text but often pick non-collusive actions. Colosseum provides a new way to audit collusion in cooperative multi-agent systems while presenting observations about how collusion emerges, what affects collusion efficacy, and which strategies may mitigate it.

Mason Nakamura, Abhinav Kumar, Saswat Das +5

University of Massachusetts Amherst · University of Virginia · ELLIS Institute Tübingen +1

Multi-Agent LLM Systems Multi-Agent Systems AI Agent Auditing Emergent Behavior in Multi-Agent Systems Multi-Agent Communication

Feb 16, 2026

MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design

To address the global health threat of antimicrobial resistance, antimicrobial peptides (AMP) are being explored for their potent and promising ability to fight resistant pathogens. While artificial intelligence (AI) is being employed to advance AMP discovery and design, most AMP design models struggle to balance key goals like activity, toxicity, and novelty, using rigid or unclear scoring methods that make results hard to interpret and optimize. As the capabilities of Large Language Models (LLM) advance and evolve swiftly, we turn to AI multi-agent collaboration based on such models (multi-agent LLMs), which show rapidly rising potential in complex scientific design scenarios. Based on this, we introduce MAC-AMP, a closed-loop multi-agent collaboration (MAC) system for multi-objective AMP design. The system implements a fully autonomous simulated peer review-adaptive reinforcement learning framework that requires only a task description and example dataset to design novel AMPs. The novelty of our work lies in introducing a closed-loop multi-agent system for AMP design, with cross-domain transferability, that supports multi-objective optimization while remaining explainable rather than a 'black box'. Experiments show that MAC-AMP outperforms other AMP generative models by effectively optimizing AMP generation for multiple key molecular properties, demonstrating exceptional results in antibacterial activity, AMP likeliness, toxicity compliance, and structural reliability.

Gen Zhou, Sugitha Janarthanan, Lianghong Chen +1

Department of Computer Science, Western University, London, ON, Canada · Department of Biochemistry, Western University, London, ON, Canada

Molecular Generation Multi-Agent LLM Systems Multi-Agent Collaboration Multi-Objective Optimization

Feb 16, 2026

ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.

Xingjian Wu, Xvyuan Liu, Junkai Lu +6

East China Normal University

Multi-Agent Communication Topology Multi-Agent LLM Systems Multi-Agent Communication Self-Evolving Agents

Feb 16, 2026

Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems

Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decisions can impose negative externalities that degrade system-level performance. We propose Socially-Weighted Alignment (SWA), a game-theoretic framework that modifies inference-time decision making by interpolating between an agent's private objective and an estimate of group welfare via a social weight

λ\in[0,1]

. In a shared-resource congestion game with

n

agents and congestion severity

β

, we show that SWA induces a critical threshold

λ^*=(n-β)/(n-1)

above which agents no longer have marginal incentive to increase demand under overload, yielding a phase transition from persistent congestion to stable operation near capacity. We further provide an inference-time algorithmic instantiation of SWA that does not require parameter updates or multi-agent reinforcement learning, and use a multi-agent simulation to empirically validate the predicted threshold behavior.

Furkan Mumcu, Yasin Yilmaz

University of South Florida

Congestion Games Multi-Agent LLM Systems LLM Alignment Multi-Agent Coordination Game Theory

Feb 16, 2026

RoboSolver: A Multi-Agent Large Language Model Framework for Solving Robotic Arm Problems

This study proposes an intelligent multi-agent framework built on LLMs and VLMs and specifically tailored to robotics. The goal is to integrate the strengths of LLMs and VLMs with computational tools to automatically analyze and solve problems related to robotic manipulators. Our developed framework accepts both textual and visual inputs and can automatically perform forward and inverse kinematics, compute velocities and accelerations of key points, generate 3D simulations of the robot, and ultimately execute motion control within the simulated environment, all according to the user's query. To evaluate the framework, three benchmark tests were designed, each consisting of ten questions. In the first benchmark test, the framework was evaluated while connected to GPT-4o, DeepSeek-V3.2, and Claude-Sonnet-4.5, as well as their corresponding raw models. The objective was to extract the forward kinematics of robots directly from textual descriptions. The results showed that the framework integrated with GPT-4o achieved the highest accuracy, reaching 0.97 in computing the final solution, whereas the raw model alone attained an accuracy of only 0.30 for the same task. Similarly, for the other two models, the framework consistently outperformed the corresponding raw models in terms of accuracy. The second benchmark test was identical to the first, except that the input was provided in visual form. In this test, the GPT-4o LLM was used alongside the Gemini 2.5 Pro VLM. The results showed that the framework achieved an accuracy of 0.93 in obtaining the final answer, which is approximately 20% higher than that of the corresponding raw model. The third benchmark test encompassed a range of robotic tasks, including simulation, control, velocity and acceleration computation, as well as inverse kinematics and Jacobian calculation, for which the framework achieved an accuracy of 0.97.

Hamid Khabazi, Ali F. Meghdari, Alireza Taheri

Social & Cognitive Robotics Laboratory, Center of Excellence in Design, Robotics, and Automation (CEDRA), Sharif University of Technology, Tehran, Iran · Chancellor, Fereshtegaan International Branch, Islamic Azad University, Tehran, Iran · Artificial Intelligence in Design and Complex Systems (AIDACS) Group, Sharif University of Technology, Tehran, Iran

Robot Kinematics Robotics Multi-Agent LLM Systems Robotic Control VLMs for Robotics Robotics Simulation

Feb 14, 2026

MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems

Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation and lack adaptability after deployment. We study in-context structural adaptation, where structured experience conditions both query-dependent system generation and execution-time reconfiguration without updating LLM parameters. We introduce MASFly, which realizes this adaptation through two complementary mechanisms. First, a retrieval-augmented SOP instantiation mechanism retrieves and adapts successful collaboration patterns to construct a query-specific MAS. Second, an experience-enhanced process supervision mechanism uses a dedicated Watcher agent to monitor execution against prior failure experience and reconfigure the system upon abnormal behavior. Experiments demonstrate that MASFly achieves state-ofthe-art performance, including a 61.7% success rate on TravelPlanner, with strong task adaptability and robustness.

Guangyi Liu, Haojun Lin, Huan Zeng +2

Department of Electronic Engineering, Tsinghua University · Ant Group

Multi-Agent LLM Systems Multi-Agent Orchestration In-Context Learning Multi-Agent Systems

Feb 10, 2026

PeroMAS: A Multi-agent System of Perovskite Material Discovery

As a pioneer of the third-generation photovoltaic revolution, Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic performance and cost potential. The development process of PSCs is precise and complex, involving a series of closed-loop workflows such as literature retrieval, data integration, experimental design, and synthesis. However, existing AI perovskite approaches focus predominantly on discrete models, including material design, process optimization,and property prediction. These models fail to propagate physical constraints across the workflow, hindering end-to-end optimization. In this paper, we propose a multi-agent system for perovskite material discovery, named PeroMAS. We first encapsulated a series of perovskite-specific tools into Model Context Protocols (MCPs). By planning and invoking these tools, PeroMAS can design perovskite materials under multi-objective constraints, covering the entire process from literature retrieval and data extraction to property prediction and mechanism analysis. Furthermore, we construct an evaluation benchmark by perovskite human experts to assess this multi-agent system. Results demonstrate that, compared to single Large Language Model (LLM) or traditional search strategies, our system significantly enhances discovery efficiency. It successfully identified candidate materials satisfying multi-objective constraints. Notably, we verify PeroMAS's effectiveness in the physical world through real synthesis experiments.

Yishu Wang, Wei Liu, Yifan Li +8

Southeast University Nanjing, China · Sun Yat-Sen University Zhuhai, China · The Hong Kong University of Science and Technology Hong Kong, China +2

Multi-Agent LLM Systems AI Agents for Scientific Discovery Materials Science

Feb 9, 2026

CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support

Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume centralized data access and rely on prompt-based assignment, limiting their applicability in privacy-sensitive clinical settings. We propose Contribution-Aware Medical Multi-Agents (CoMMa), a decentralized LLM-agent framework where specialists operate on partitioned clinical data streams. Unlike prior approaches that share inputs across agents, CoMMa enforces data decentralization to include stronger role specialization and further enhances this via agent-specific finetuning. To enable reliable and interpretable coordination, we introduce a contribution-aware aggregation mechanism that replaces stochastic, narrative-based reasoning with deterministic embedding projections to approximate each agent's marginal utility. This yields explicit credit assignment over agents, providing a stable and interpretable decision pathway aligned with clinical requirements. We evaluate CoMMa on multiple oncology benchmarks, including real-world multidisciplinary tumor board datasets from large academic hospitals in North America and East Asia, as well as public datasets, demonstrating strong performance and generalization across heterogeneous clinical settings.

Yichen Wu, Kailong Fan, Sangjoon Park +9

Harvard Medical School/MGH · Yonesei University · MBZUAI +1

Multi-Agent LLM Systems Clinical Decision Support Multi-Agent Systems

Feb 9, 2026

Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems

Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. In this work, we theoretically pinpoint a key reason for training instability when extending group-based RL to multi-agent LLM systems. We show that under GRPO-style optimization, a global normalization baseline may deviate from diverse agents' reward distributions, which ultimately leads to gradient-norm instability. Based on this finding, we propose Dr. MAS, a simple and stable RL training recipe for multi-agent LLM systems. Dr. MAS uses an agent-wise remedy: normalizing advantages per agent using each agent's own reward statistics, which calibrates gradient scales and dramatically stabilizes training, both theoretically and empirically. Beyond the algorithm, Dr. MAS provides an end-to-end RL training framework for multi-agent LLM systems, supporting scalable orchestration, flexible per-agent LLM serving and optimization configs, and shared resource scheduling of LLM actor backends. We evaluate Dr. MAS on multi-agent math reasoning and multi-turn search benchmarks using Qwen2.5 and Qwen3 series models. Dr. MAS achieves clear gains over vanilla GRPO (e.g., +5.6% avg@16 and +4.6% pass@16 on math, and +15.2% avg@16 and +13.1% pass@16 on search) while largely eliminating gradient spikes. Moreover, it remains highly effective under heterogeneous agent-model assignments while improving efficiency.

Lang Feng, Longtao Zheng, Shuo He +2

Nanyang Technological University, Singapore

Multi-Agent LLM Systems Multi-Agent System Optimization Group Relative Policy Optimization RL for LLM Agents Multi-Agent Reinforcement Learning

Feb 3, 2026

Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance

Multi-agent LLM frameworks are data-intensive systems that govern how agents orchestrate tasks, manage state, and coordinate decisions. These architectural choices control execution overhead, memory behavior, planning effectiveness, and coordination scalability. Their impact on system performance remains poorly understood. Existing benchmarks evaluate individual agent capabilities in isolation and lack standardized framework-level comparison. We make four contributions. We introduce an architectural taxonomy that decomposes multi-agent LLM frameworks along five dimensions: orchestration, memory, planning interfaces, specialization, and communication topology. We develop MAFBench, a unified evaluation suite that integrates existing benchmarks within a standardized execution pipeline. We conduct a controlled empirical study across nine frameworks, fixing the underlying LLM and varying only architectural design choices. We distill the results into six evidence-based design principles. Architectural design, not only model intelligence, governs performance. Orchestration alone increases latency by over 60x, and a minimal implementation of the same paradigm isolates that cost as implementation rather than paradigm. Schema-constrained planning interfaces reduce accuracy by up to 32 points through formatting failures, not reasoning errors. Communication topology drops coordination success from above 90% to below 30% under mismatched structure. Memory architecture controls recall and scalability independent of context window size, and no evaluated framework natively supports controlled knowledge revision.

Abdelghny Orogat, Ana Rostam, Essam Mansour

Concordia University

Multi-Agent LLM Systems Multi-Agent Orchestration LLM Agent Evaluation AI Agent Benchmarks Software Architecture Design

Feb 3, 2026

MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning settings, and has been suggested as a potential tool for guiding coordination of MAS; however, its actual effectiveness in MAS remains unclear. To fill this gap, we present MAS-ProVe, a systematic empirical study of process verification for multi-agent systems (MAS). Our study spans three verification paradigms (LLM-as-a-Judge, reward models, and process reward models), evaluated across two levels of verification granularity (agent-level and iteration-level). We further examine five representative verifiers and four context management strategies, and conduct experiments over six diverse MAS frameworks on multiple reasoning benchmarks. We find that process-level verification does not consistently improve performance and frequently exhibits high variance, highlighting the difficulty of reliably evaluating partial multi-agent trajectories. Among the methods studied, LLM-as-a-Judge generally outperforms reward-based approaches, with trained judges surpassing general-purpose LLMs. We further observe a small performance gap between LLMs acting as judges and as single agents, and identify a context-length-performance trade-off in verification. Overall, our results suggest that effective and robust process verification for MAS remains an open challenge, requiring further advances beyond current paradigms. Code is available at https://github.com/Wang-ML-Lab/MAS-ProVe.

Vishal Venkataramani, Haizhou Shi, Zixuan Ke +6

1Rutgers University · 2Salesforce AI Research

Multi-Agent LLM Systems LLM-as-a-Judge Process Reward Models LLM Agent Evaluation Multi-Agent Systems

Feb 1, 2026

A-MapReduce: Executing Wide Search via Agentic MapReduce

Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information seeking. However, when confronted with wide search tasks characterized by large-scale, breadth-oriented retrieval, existing agentic frameworks, primarily designed around sequential, vertically structured reasoning, remain stuck in expansive search objectives and inefficient long-horizon execution. To bridge this gap, we propose A-MapReduce, a MapReduce paradigm-inspired multi-agent execution framework that recasts wide search as a horizontally structured retrieval problem. Concretely, A-MapReduce implements parallel processing of massive retrieval targets through task-adaptive decomposition and structured result aggregation. Meanwhile, it leverages experiential memory to drive the continual evolution of query-conditioned task allocation and recomposition, enabling progressive improvement in large-scale wide-search regimes. Extensive experiments on five agentic benchmarks demonstrate that A-MapReduce is (i) high-performing, achieving state-of-the-art performance on WideSearch and DeepWideSearch, and delivering 5.11% - 17.50% average Item F1 improvements compared with strong baselines with OpenAI o3 or Gemini 2.5 Pro backbones; (ii) cost-effective and efficient, delivering superior cost-performance trade-offs and reducing running time by 45.8% compared to representative multi-agent baselines. The code is available at https://github.com/mingju-c/AMapReduce.

Mingju Chen, Guibin Zhang, Heng Chang +2

Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University · National University of Singapore · Tsinghua University

Multi-Agent LLM Systems Agentic Retrieval

Jan 30, 2026

Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning

Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generation is highly sequential, and long CoTs lead to a high latency. We propose to train Divide-and-Conquer CoT (DC-CoT) to reduce the latency. With DC-CoT, the model can act as a director that identifies distinct subtasks that can be performed in parallel in its reasoning process, and then spawns workers to execute the subtasks. Our goal is to achieve high accuracy, with a low longest path length, which is a theoretical measure of the latency needed for the response. We start with a long CoT base model (DeepScaleR-1.5B-Preview), and first use SFT with a small curated demonstration set to initialize its ability to spawn workers in a certain format. Because SFT degrades the accuracy significantly, we design a multi-stage RL algorithm, with various data filtering strategies, to recover the accuracy while decreasing the longest path length. Across several benchmarks including AIME 2024 and HMMT 2025, DC-CoT achieves similar accuracy as DeepScaleR-1.5B-Preview while decreasing longest path length by 35-40%. Our code, SFT dataset and models are publicly available at https://github.com/amahankali10/DC_CoT_RL_for_Low_Latency_CoT_with_Parallel_Reasoning.

Arvind Mahankali, Kaiyue Wen, Tengyu Ma

Stanford University

Multi-Agent LLM Systems CoT Reasoning RL for Language Model Reasoning LLM Inference Acceleration

Jan 20, 2026

MASCOT: Multi-Agent Socio-Collaborative Companion Systems

Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from persona collapse, where agents revert to generic, homogenized assistant behaviors, and social sycophancy, where agents produce redundant, non-constructive dialogue. We propose MASCOT, a multi-agent framework for multi-perspective socio-collaborative companions. MASCOT introduces a novel bi-level optimization strategy to harmonize individual and collective behaviors: 1) Persona-Aware Behavioral Alignment, an RLAIF-driven pipeline that finetunes individual agents for agent-specific identities; and 2) Collaborative Dialogue Optimization, a group-level adaptation process that promotes complementary, diverse, and productive discourse. We evaluate MASCOT using human-grounded contexts drawn across both in-domain and out-of-domain (OOD) settings against state-of-the-art baselines. MASCOT improves persona consistency by up to +14.1 and social contribution by up to +10.6. A broad evaluation suite, including human evaluation, multiple LLM judges, three-way comparisons, and automatic metrics, further shows that MASCOT produces more role-consistent and less redundant multi-agent dialogue.

Yiyang Wang, Yiqiao Jin, Alex Cabral +1

Georgia Institute of Technology · Massachusetts Institute of Technology

Multi-Agent LLM Systems Multi-Agent System Optimization Persona Consistency Multi-Agent Collaboration

Jan 20, 2026

Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details. Current solutions typically treat this as a direct-to-text generation problem, suffering from hallucination, overlooked critiques, and a lack of verifiable grounding. To address these limitations, we introduce

\textbf{RebuttalAgent}

, the first multi-agents framework that reframes rebuttal generation as an evidence-centric planning task. Our system decomposes complex feedback into atomic concerns and dynamically constructs hybrid contexts by synthesizing compressed summaries with high-fidelity text while integrating an autonomous and on-demand external search module to resolve concerns requiring outside literature. By generating an inspectable response plan before drafting,

\textbf{RebuttalAgent}

ensures that every argument is explicitly anchored in internal or external evidence. We validate our approach on the proposed

\textbf{RebuttalBench}

and demonstrate that our pipeline outperforms strong baselines in coverage, faithfulness, and strategic coherence, offering a transparent and controllable assistant for the peer review process.

Qianli Ma, Chang Guo, Zhiheng Tian +4

AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University

Multi-Agent LLM Systems LLM Hallucination Mitigation Scholarly Peer Review Agentic RAG Text Generation