Multi-Agent LLMs

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 144% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 211

Oct 8, 2026cs.CV

Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?

A single multimodal large language model (MLLM) struggles to excel simultaneously at detection, localization, description, and reasoning in multimodal industrial anomaly understanding (MM-IAU). We show that in-domain training does not close this gap. On MMAD, a widely adopted MM-IAU benchmark, trained specialists reach at most 75.5% accuracy in defect localization, against 92.3% for human experts, and even detect anomalies less accurately than their untrained base model. Meanwhile, different MLLMs offer complementary strengths but share this weakness in fine-grained perception, so combining them alone cannot remove it. We therefore propose SiGMA, a spatially grounded multi-agent framework that divides labor between heterogeneous MLLM agents and a dedicated visual defect expert. A multimodal searcher supplies industrial knowledge and normal references, the defect expert turns query-reference comparison into calibrated anomaly evidence, and a label-free reliability controller weighs each source by task-wise competence and query-level evidence quality. SiGMA reaches 85.2% average accuracy on MMAD, 4.0% above the strongest trained specialist and Gemini-2.5-Pro and within 1.5% of human experts. Even with three agents of at most 9B parameters, it reaches 84.4%, and new MLLMs join without retraining.

Xingwu Zhang, Duanyang Du, Huiling Zhu +5

Hunan University · University of Aberdeen · South China Normal University +1

Industrial Anomaly Detection Multimodal Anomaly Detection Anomaly Localization Multi-Agent LLMs

Oct 7, 2026cs.AI

From Expert-Guided Proof Search to Automated Open-Problem Solving

Large language models are increasingly contributing to mathematical research, where progress often depends on efficient proof search, incremental improvements and careful verification. We describe Bolzano, a multi-agent open-source system that uses parallel prover agents with a verifier agent and maintains a human-readable research state. Initial manual use on expert-selected problems yielded 8 results whose proofs were checked by domain experts. Motivated by these case studies, we ran Bolzano without problem-specific human guidance on about 3,800 open problems extracted from four sets of papers, solving about 200 open problems. One experiment used papers accepted to STOC 2026, a top conference in theoretical computer science. There, we answered four questions raised in the papers, as confirmed by their authors.

Adrián Zámečník, Matěj Kripner, Martin Koutecký +5

Computer Science Institute, Charles University · Institute of Formal and Applied Linguistics, Charles University · Department of Applied Mathematics, Charles University +1

Automated Theorem Proving AI Agents for Scientific Discovery LLM Mathematical Reasoning Multi-Agent LLMs

Oct 6, 2026cs.MA

Disentangling Models from Personas in Heterogeneous LLM Simulations

Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model. This overlooks the inter-model effects which may dominate engagement dynamics in real-world deployments. To show this, we simulate a heterogeneous social network powered by several different base models and show that the amount of engagement an agent receives depends more on its base model than on its assigned persona. The attraction or repulsion effects of a base model strengthen dramatically when more models are added in the mix, suggesting that networks dynamics may converge to base model effects at scale. To help explain this effect, we conduct a series of content-mediating analyses, showing the predictability of base models across contexts as well as the relationship between a model's lexical patterns and an engagement-maximizing style. In light of recent developments in mass multi-agent interaction, this work underscores the relevance of heterogeneous compositions in driving the outcomes of those networks

Dani Roytburg, Daphne Ippolito

Carnegie Mellon University

Large Language Model-Based Social Simulation Multi-Agent LLMs

Oct 4, 2026cs.MA

templar: agentic induction and evolution of standardized radiology reporting templates from large-scale clinical corpora

Structured radiology reporting mitigates the heterogeneity of free-text reports, yet its benefits depend on high-quality reporting templates. In practice, such templates are conventionally built through labor-intensive expert consensus and therefore vary across institutions and lag behind evolving clinical practice. Large language models (LLMs) enable automated template induction, but existing approaches remain limited: single-LLM induction is constrained by context length, and the corpus-scale method ASTAR produces a static, closed-corpus template without external grounding or downstream adaptation. To address these limitations, we propose TEMPLAR, a TEMPLate-centric Agentic framework for inducing and evolving standardized Radiology reporting templates from large-scale clinical corpora. TEMPLAR treats the template as a persistent central state maintained alongside two provenance-aware knowledge graphs, namely an anatomical graph that constrains template construction and a diagnostic graph that supports finding-to-diagnosis reasoning. Three agents operate on this state. The Induction Agent derives canonical clinical slots from anatomy-constrained Span-Triple atoms via dual-view similarity clustering; the Evolution Agent then assembles these slots into a hierarchical template and revises it under consistency constraints, external clinical evidence, and downstream structuring feedback; and the Clinical Agent applies the evolved template to report structuring, reconstruction, and diagnostic reasoning. Across four datasets, TEMPLAR outperforms ASTAR, three medical LLMs, and six general-purpose LLMs in coverage, information fidelity, and diagnostic fidelity, while achieving the highest or tied-highest LLM-rated template quality. Its fidelity advantages over ASTAR persist under cross-dataset transfer, and cumulative ablations support complementary contributions of its key components.

Xiaotian Hu, Mingxuan Liu, Zhonghan Wang +9

Tsinghua University · University of Hong Kong · University of California, San Diego

Radiology Report Generation Multi-Agent LLMs

Sep 30, 2026cs.MA

Consensus and Factual Dynamics in Large Populations of Interacting Language Models

Large Language Model (LLM) agents are increasingly deployed as populations of interacting entities, in which consensus --agreement on a shared answer-- emerges as a collective, unengineered behaviour. Prior work on LLM consensus shows that agents can cross-verify their answers and converge towards more factual responses, treating agreement as a proxy for correctness. However, these studies usually fix a single interaction structure, leaving open how consensus depends on how agents interact. We address this gap by introducing RHEON, a physics-inspired framework that recasts a population drawn from a single frozen model as an evolving

O(n)

spin system on a ladder of interaction geometries of increasing effective dimension --from a 1D ring to a full-coupling mean-field graph-- with the sampling temperature

T

as the tunable source of thermal disorder, evolved through a Glauber-like asynchronous dynamics. Sweeping RHEON across

432

configurations of prompt, population size, communication topology, and sampling temperature yields Eraclitus-4.7M, a tagged evolutionary corpus of

4.7

million responses. We find that agents reach their strongest consensus gain within the first few update sweeps and that increasing the number of neighbours per agent accelerates convergence on average. We further show that whether a configuration settles on factually correct or hallucinated consensus is not predictable from its initial state alone, and that the hallucination-minimising temperature depends on how the agents are coupled, so the common near-greedy default is not automatically the safest. Finally, semantic agreement correlates positively with factual convergence, and interaction strengthens the association, yet never enough for unanimity to certify correctness.

Emanuele Ricco, Elia Onofri, Vincenzo Sammartino +1

Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST) Thuwal 23955, Saudi Arabia · Dipartimento di Informatica, Universit`a di Pisa Pisa, Italy

Hallucination in Language Models Multi-Agent Consensus Multi-Agent LLMs

Sep 29, 2026cs.MA

From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs

Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work together on complex problems. However, self-improvement methods typically optimize one system at a time, and multi-agent frameworks often have every model work toward a shared goal. We ask a different question. When each agent pursues its own reward, can self-improving LLMs learn from one another well enough to improve the whole population? We call this capability recursive social improvement. We study populations that revise skill files and choose whether, when, and whom to copy from. Independent search, learning from peers, and acting all share one token budget. In controlled environments, established social-learning algorithms benefit from peers, but three LLMs do not. They earn less reward per token than solo learners, and explore too narrowly or run out of tokens before acting. We then let the models write and revise their own skills. Observing peers changes how they improve, helping one model find useful skills sooner and another spend less on private search. Neither, however, outperforms independent learners at the same cost. Skills are copied, revised, and passed on, so one discovery can seed further search. Yet these exchanges concentrate the population around fewer independent discoveries. Together, these results show that LLMs can make learning more efficient by copying from peers, but not yet more effective.

Kunal Jha, Max Kleiman-Weiner, Natasha Jaques

Department of Computer Science, University of Washington, Seattle, WA 98195, USA.

LLM Agent Self-Improvement LLM Agent Skill Learning Multi-Agent LLMs

Sep 29, 2026cs.MA

Absorbing State Phase Transitions in Multi-Agent Search

Nontrivial dynamics can emerge in large language model (LLM)-based multi-agent systems, and preliminary evidence exists that formalisms from statistical mechanics can be effective at modeling and predicting such behaviors. In parallel, designing multi-agent communication topology for optimal task-solving is an active research question. In this paper, we focus on predicting the success of multi-agent search tasks using the formalism of absorbing state phase transitions. We first taxonomize search tasks into four types, informed by classical results in combinatorial search. We then theoretically derive a critical communication degree

d_c

, the minimum number of agents each agent can communicate with, above which incorrect hypotheses do not proliferate uncontrollably and the search enters the solved state. Finally, we evaluate frontier LLM-based multi-agent systems on real-world search and discovery tasks, software configuration debugging and physical mechanism discovery, and find that agreement with theory is mixed. LLM agents may not communicate with their neighbors and can develop strategies that are individually beneficial but limits the benefits of collaboration.

Wenwen Zheng, Yuzhe Yang, Helen Qu +2

Flatiron Institute

Phase Transitions Multi-Agent Systems Multi-Agent Communication Multi-Agent LLMs

Sep 29, 2026cs.AI

MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems

Recent studies report that LLM-based multi-agent systems (MAS) fail at rates of 41%-87%, yet to our knowledge, no benchmark to date supports systematic anomaly detection (AD) for them. Building MAS AD benchmarks is hard because they must remain fresh as LLM systems evolve: tasks may leak into training data and thus be memorized by LLMs, traces and anomaly patterns expire as backbones evolve, and labels must be provided reliably for each refresh. To address these challenges, we present MAADBench (MA: multi-agent; AD: anomaly detection), the first refreshable MAS AD benchmark designed for diverse, evolving LLM backbones underlying the agents. MAADBench combines (1) sampled-and-coupled generative tasks over an approximately 10^37-task space to mitigate task leakage, (2) refreshable trace generation under configurable LLM backbones, and (3) automated provision of cost-free, deterministic step-level labels for fine-grained AD evaluation. Beyond offering the paradigm itself, we run MAADBench with five state-of-the-art LLM backbones and release the MAADBench-Full dataset with 5,200 step-labeled traces. Benchmarking 25 AD methods on the MAADBench dataset reveals substantial limitations in current approaches: they rely heavily on supervision, struggle with subtle MAS-specific anomalies, and lack robustness across LLM backbones. These gaps point to a rich research agenda for MAS-specific anomaly detection, with MAADBench providing a systematic and refreshable testbed for method development and evaluation. We open-source MAADBench-Full at https://huggingface.co/datasets/hww123/MAADBench-full.

Lei Ma, Dennis Hofmann, Haowen Xu +4

Worcester Polytechnic Institute · University of Arizona

AI Agent Benchmarks Multi-Agent LLMs Anomaly Detection

Sep 28, 2026cs.AI

Principled Thoughts for Latent Recursive LLM Systems

Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while training supervises only the Cross-Entropy (CE) of the final decoded answer and does not constrain the thought. Theoretical and empirical analyses establish and confirm four failures of CE-only training that lead to a lower probability of the correct answer such as collapsing thoughts across distinct questions and retaining irrelevant information. We introduce REST (REpresentation-Supervised Thoughts), a training objective that turns four properties of a valid thought representation (causality, minimality, separability, and stability) into differentiable losses added to CE. We instantiate it in latent single-agent and multi-agent systems, without architectural changes or added parameters at inference. Across 7 benchmarks spanning mathematics, science, medicine, and code generation, with the same training data, compute, and latent budget, REST increases accuracy over CE-only training across agent settings and model sizes by up to 7.5 percentage points and convergence on a final answer by 30%. Furthermore, REST thoughts encode more of what is required to achieve the correct answer, and decoding them better recovers the intended output of the agent, which makes latent communication easier to interpret. Project Website: https://fard-lab.github.io/REST

Fahd Seddik, Fatemeh Fard

FARD Lab, University of British Columbia, Okanagan, Canada

Continuous Latent Reasoning Multi-Agent LLMs LLM Training Latent Reasoning Recursive Language Models

Sep 28, 2026cs.AI

LongCat-DeepResearch Technical Report

We present LongCat-DeepResearch, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded reports. The workflow separates global planning from detailed investigation and coordinates revision at the section level. Multiple planning agents first explore external sources and refine an actionable research plan, termed ResearchSpec. Research agents then investigate and draft their assigned sections in parallel, gathering additional evidence in separate contexts as their analyses develop. Once the sections are assembled, global review guides targeted local revisions, reducing reliance on repeated full-report rewriting. This workflow also supports the construction of research tasks and trajectories for the mid-training and post-training of LongCat's general-purpose models. LongCat-DeepResearch achieves 55.25 on DeepResearchBench, 51.35 on DeepResearchBench II, and 79.83 on ResearchRubrics. On an in-house benchmark, it scores 76.04, ranking second among four compared systems. Development-set analyses show benefits from combining planning perspectives, while further planning refinement has mixed effects. Additional editing improves average automatic readability preference across two benchmarks, with different trends on each.

Meituan LongCat Team, He Zhu, Yue Xu +28

Meituan LongCat Team

Deep Research Agents Multi-Agent Planning Multi-Agent LLMs

Sep 28, 2026cs.AI

Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents

Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and create persistent artifacts. As these artifacts are shared between users, they form an indirect communication channel between otherwise independent assistants. We study a failure mode in which this channel enables self-propagating attacks. We introduce artifact-mediated propagation, where adversarial content introduced through an artifact (e.g. a report), is stored in an assistant's persistent memory, reproduced in a subsequently created artifact, and acquired by another assistant that later reads it. We evaluate this process in temporal human-agent universes that model artifact exchange between independently operated assistants over time, measuring whether an attack survives successive hand-offs, how many hops it reaches, and how broadly it spreads. We find that attacks can propagate across multiple independent assistants and persist over extended interaction sequences. In larger simulated environments, even GPT-5.6 Luna exhibits substantial spread, reaching 60-80% of agents with propagation chains extending to eight hops. These results show that persistent artifacts can act as durable carriers of adversarial state, allowing attacks to outlive individual interactions and spread across isolated assistants.

Sidharth Pulipaka, Ansh Sharma, Stanislau Hlebik +4

SPAR · University of Cambridge · APTA AI +1

AI Agent Security Agent Memory Poisoning Prompt Injection Attacks on AI Agents Multi-Agent LLMs Memory-Augmented Language Model Agents

Sep 27, 2026cs.CL

LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems

Large language models (LLMs) are increasingly deployed in multi-agent settings, where agents observe and influence one another, making social influence a key dimension of AI behavior and safety. We investigate whether LLMs' responses depend on the social identity of other agents, beyond the effect of their consensus. We construct judgment tasks with a single correct answer, and place models in a multi-agent setting where they receive incorrect answers from other agents whose social identities (AI or human, model family, or an arbitrary minimal group) are either shared with or distinct from their own. Across 12 open-weights models and nine tasks, we find a bidirectional effect of group identity on conformity to incorrect answers: in-group consensus increases conformity (in-group favoritism), whereas out-group consensus decreases it (out-group divergence). Unlike humans, for whom one ally breaking the consensus sharply reduces conformity, models are unmoved by an ally from the majority's group. Worse, a correct ally from the opposing group intensifies this bidirectional effect. Chain-of-Thought reasoning suppresses most of these effects, yet an in-group ally still reduces conformity to an incorrect out-group majority. Labeling peers as safety-aligned shifts overall conformity but leaves in-group favoritism and out-group divergence intact. These results show that group identity shapes how LLMs aggregate information across agents, independently of its correctness, and identify a manipulation surface for multi-agent AI systems.

Liron Soffer, Ravid Shwartz-Ziv, Chen Shani

Tel-Aviv University · New York University

Normative Conformity in Language Models Social Bias in Language Models Belief Updating in LLMs Multi-Agent Consensus Multi-Agent LLMs

Sep 22, 2026cs.AI

AgenticSizing: A Large Language Model-based Multi-Agent Framework for Analog Circuit Sizing

Analog circuit sizing remains a challenging and time-consuming task due to the large design space, strong performance trade-offs, and increasing circuit complexity in scaled technologies. Although recent large language model (LLM)-based methods show promise in improving sample efficiency and interpretability, existing approaches often lack explicit circuit-topology understanding and are mainly evaluated on relatively simple analog building blocks. This paper presents a multi-agent LLM-based framework for complex analog circuit sizing. The proposed framework first analyzes the circuit topology and decomposes the netlist into functional blocks and substructures. It also extracts lightweight design knowledge for reuse. Based on the extracted topology and knowledge, a planner coordinates multiple role-specialized sizing agents to update design variables and achieve global performance specifications. This workflow mimics the collaborative process of an expert analog design team and provides a structured, interpretable, and simulation-driven optimization procedure. The framework was validated on eight circuits, with the largest design containing up to 55 transistors and 60 sizing variables. Notably, for the LDO benchmark, the proposed method achieved a 60% success rate with an average of 83 iterations, where classical optimizers failed to find feasible solutions. Further, ablation studies demonstrate that topology understanding, design-knowledge infusion, and agent specialization provide complementary benefits. The source code is available to support reproducibility.

Yijia Hao, Pratibha Verma, Dongxu Guo +4

Centre for Electronics Frontiers, Institute for Integrated Micro and Nano Systems, School of Engineering, The University of Edinburgh, UK · Department of Electrical Engineering, Indian Institute of Technology Indore, India · School of Informatics, The University of Edinburgh, UK +1

Large Language Model-Guided Optimization Electronic Design Automation Multi-Agent LLMs LLM Agent Planning

Sep 20, 2026cs.AI

Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows

Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected tokens are billed as input tokens at the same per-token price as the system prompt and the user query. Production observability tools report total token cost but do not separate the tokens a node generates from the tokens it is handed, so this component of the bill is invisible to the teams paying it. We introduce the Total Cost of Agency (TCA), a decomposition of multi-agent workflow cost into base prompt, inference, memory injection, miss penalty and context-accumulation components, and an exact attribution method: a two-pass, non-billable token count that measures injected tokens directly rather than estimating them from word-count proxies. On a 200-task enterprise benchmark executed against real model APIs, memory injection accounts for 13.6 percent of the variable cost a compile-time optimizer can act on, about 12 percent of the full billed cost, and its share rises from a structural zero at workflow depth one to 27.6 percent at depth six. Injected tokens grow linearly with depth over the measured range (R^2 = 0.9974, depths two through six); a quadratic fit yields a negative leading coefficient, so the data do not exhibit convex growth at these depths. We show the component is controllable at fixed model tier: reducing the retrieval window capacity from 32 to 2 entries lowers injected tokens by 28.7 percent with an accuracy change within seed-level variation. We report in full that our graph-rewriting transforms are approximately cost-neutral in isolation, that two of the five decomposition terms are zero by construction in this harness, and that total workflow cost is dominated by model tier assignment, which we hold fixed and treat as prior work. Prompt caching is not evaluated; all figures are for the uncached case.

Vivek Kumar Singh, Preeti Priyam, Gautam Bhowmick

Independent Researcher McKinney, TX, USA · Independent Researcher Chicago, IL, USA

LLM Agent Memory Cost-Aware Inference LLM Agent Workflow Optimization Multi-Agent LLMs

Sep 17, 2026cs.LG

Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks

The study of opinion dynamics in social networks is one of the key challenges in computational social science with direct relevance to understanding political polarization, misinformation, and health responses. Current approaches focus on simplified mathematical models that ignore linguistic and contextual factors related to belief updates or use Large Language Model (LLM)-based simulations that have not been validated against real data. We present a framework based on the concept of a digital twin to simulate opinion dynamics in social networks. The approach fills the gap by cloning a real-world Twitter network, assigns a set of attributes for agents (such as persona, emotions, centrality, stubbornness, and influence), and employs Mistral-7B to perform opinion update based on memory and social exposure. To evaluate the proposed approach, we validate it against two real Twitter datasets (COVID-19 discourse and U.S elections 2020). The results show that the capability of the proposed framework reproduces opinion trajectories and reduces individual prediction error by more than 50% compared to the best-performing classical baseline (Mistral-7B achieves Mean Absolute Error (MAE) = 0.150 and 0.121 on the COVID-19 and US Election 2020 datasets, respectively). We observe similar improvements in structural alignment (Delta_r = 0.120 and 0.180) and polarization dynamics (Delta_Var = 0.106 and 0.115) on the two datasets, respectively. Additionally, the ablation studies confirm that agent attributes, memory, and social exposure all contribute to the framework's predictive fidelity in reproducing opinion trajectories, with agent attributes being the most critical contributor. Overall, our results demonstrate that grounding Mistral-7B within empirically cloned interaction networks produces a realistic simulation framework capable of reproducing complex social dynamics.

Omran Berjawi, Giuseppe Fenza, Rida Khatoun +1

Information Processing and Communication Laboratory (LTCI) Institut Polytechnique de Paris, T´el´ecom Paris Palaiseau, France · Management & Information Systems (DISA-MIS) University of Salerno Fisciano, Italy · College of Communication and Information, University of Kentucky +1

Opinion Dynamics Human Behavior Simulation Computational Social Science Agent-Based Modeling Large Language Model-Based Social Simulation Digital Twins+1

Sep 16, 2026cs.CL

Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry

We evaluate six frontier language models on the two-agent

\log_2 N

-Questions game (Potash et al., 2019) to measure self-communication across an information asymmetry. A questioner with access to

N

candidate Wikipedia lead paragraphs (

N = 4

to

1024

) must identify a secret target using exactly

\log_2 N

binary questions answered by an agent from the same provider that sees only the target. Across 408 games, win rate decays cleanly as a geometric power of horizon length,

p^{\log_2 N}

(

p \approx 0.93

). Per-round failure rates are flat across the horizon, indicating that errors compound because more rounds must succeed rather than because individual rounds grow harder. Adjudication across three independent judges shows that losses divide between single-agent answer errors and discrimination failures, which become undetectable and unrecoverable under the two-agent structure rather than from channel breakdown. Claude Opus 5 lags behind due to systematic false-negative answers (82% answer errors), whereas the five leading models (GLM-5.3, GPT-5.6 Sol, Grok 4.6, Gemini 3.8 Flash, and Kimi K3) are closely clustered. Maximizing information gain requires structural partitioning (e.g., splitting on document titles), and neither reasoning-token expenditure nor API cost correlates with success (

r = -0.05

), highlighting communicative reliability as a distinct bottleneck from inference compute.

Peter Potash

LLM Evaluation Pragmatic Reasoning in Language Models LLM Reliability Multi-Agent LLMs

Sep 16, 2026cs.AI

Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents

Large language model (LLM) pricing agents may respond to how market data is presented, even when its numerical values remain unchanged. We introduce market signal injection (MSI), an attack that manipulates numerical formatting, competitor ordering, or qualitative market commentary without issuing explicit instructions. We evaluate nine open-weight models in simulated Bertrand duopoly and triopoly markets and three proprietary models in duopoly markets. Sentiment-based attacks produce the largest behavioral shifts, which propagate to other firms and alter profits and consumer surplus. Susceptibility varies across model families, and larger models are not consistently more robust. Matched neutral-text controls and a rule-based agent support a framing-based account of these shifts under the fixed demand parameters of our simulation. Episode-held-out probes distinguish baseline from attacked activations in all eleven re-evaluated model--condition pairs: linear AUC is 1.00 and MLP AUC ranges from 0.93 to 0.99. This separability does not by itself identify harmful pricing decisions. Input canonicalization removes the tested sentiment attacks, while decision boundary anchoring, which combines prompt constraints with output projection, provides partial mitigation under the tested adaptive attacks. These results identify data presentation as an attack surface for LLM pricing agents and motivate defenses that account for interactions among agents.

Dohun Lee, Hyunwoo Park

Graduate School of Data Science, Seoul National University

Adversarial Attacks on LLMs AI Agent Security Adversarial Robustness of Language Models Multi-Agent LLMs

Sep 16, 2026cs.LG

Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric

Large language models (LLMs) are increasingly deployed in applications involving interaction between agents, where their output plays a role in collective reasoning and decision-making processes. Despite significant research into the functioning of LLMs in such multi-agent systems, the processes of bias propagation in such systems are still a challenge. This work studies how biased opinions are propagated in the form of textual interaction in an environment of LLMs, in which a minority of agents maintain persistent extreme opinions, while the remaining agents iteratively update their beliefs through structured textual interactions. The findings show that even the presence of a small percentage of biased agents in such a system leads to significant shifts in the opinions of non-biased agents. It suggests that for the same percentage of biased agents, the shifts occur more quickly for the Llama~3.2 model when compared to a classical Friedkin-Johnsen (FJ) model. Further semantic analysis demonstrates that rhetorical consistency in textual explanations increases systematically with biased exposure and, importantly, is partially decoupled from numerical convergenumericalutral agents adopt the vocabulary employed by the biased agents even in configurations where their numerical opinion shifts remain moderate. The research helps explain how bias and language develop together in multi-agent language model ecosystems.

Omran Berjawi, Giuseppe Fenza, Rida Khatoun

Institut Polytechnique de Paris, Télécom Paris, Palaiseau, France · University of Salerno, Fisciano, Italy

Opinion Dynamics Social Bias in Language Models Belief Updating in LLMs Multi-Agent LLMs

Sep 15, 2026cs.MA

ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures

LLM-based multi-agent systems can fail even when communication succeeds because agents do not correctly track their peers' roles, knowledge, or intentions. We investigate whether such inter-agent misalignment cases, labelled FC2 in MAST-Data, can be converted into functional partner-state reasoning items. ToMAS applies four explicit convertibility criteria to diagnosed execution traces. A full conversion pass over 242 eligible non-AG2 training traces produced 39 CLEAN items. In an 18-trace reliability pilot, two annotators achieved 94.4% raw agreement and Cohen's kappa = 0.92. We then used the converted items as binary rewards in a small-scale GRPO feasibility experiment with Qwen2.5-1.5B. On a 28-item held-out Magentic GAIA diagnostic, every evaluated condition exceeded the ROUGE-L threshold on the same 2 of 28 items. Post-hoc adapter checks show why: under the learning rate used, the LoRA update remained numerically negligible (max abs Delta W about 7e-6), so all conditions decode identically to the untrained checkpoint. The experiment therefore does not show a training effect and cannot establish one; it reports an executable pipeline together with two limitations that any conclusive study must address: a provenance gap between the training and evaluation items, and lexical-overlap scoring. ToMAS provides a preliminary rubric and pipeline for converting diagnosed coordination failures into trainable partner-state reasoning items and identifies the requirements for a conclusive matched-domain evaluation.

Muhammad Ashar Ishfaq, Glaucia Melo

The Islamia University of Bahawalpur, Pakistan · Toronto Metropolitan University, Toronto, Canada

Theory of Mind LLM Agent Evaluation AI Agent Benchmarks Multi-Agent Reasoning Multi-Agent LLMs

Sep 14, 2026cs.MA

Cheap Talk Stabilizes Strategic Interaction in LLM Agents

Large language models are increasingly deployed as interacting agents, making the persistence of their action policies across repeated interaction critical for reliable multi-agent operation. We investigate whether and how agent-generated, non-binding pre-play communication ("cheap talk") increases such persistence in four open-weight 7-9B-parameter LLMs. Our experiments span four repeated two-player games -- Prisoner's Dilemma, Snowdrift, Stag Hunt, and Harmony -- with incentive structures ranging from strategic conflict to alignment, each presented in six contexts. We observe unstable trajectories in all four games, although their prevalence and magnitude depend strongly on model and context. Across models, games, and contexts, cheap talk is predominantly stabilizing, with five corrected reversals concentrated in social or team framings; effects vary substantially by model and context. Controlled current-message interventions identify two separable output-level channels in Qwen: reduced action uncertainty and less between-round drift in action probabilities. Matched history-by-message counterfactuals further show that recent partner behavior conditions how mutual-benefit versus self-prioritizing language affects policy persistence. Finally, in Prisoner's Dilemma, we identify in Qwen and Falcon a history-balanced policy-content direction in late transformer layers; projecting out this direction increases realized switching during closed-loop play, demonstrating that complete trajectories are causally sensitive to this component. Together, these findings show that cheap talk can make individual trajectories more persistent across diverse incentive structures, while revealing that the magnitude and mechanisms of stabilization are model- and history-dependent.

Nunzio Lorè, Hongan Zhu, Babak Heydari

Multi-Agent Intelligent Complex Systems (MAGICS) Lab, Northeastern University, Boston, MA, USA

Repeated Games LLM Agents Multi-Agent Communication Multi-Agent LLMs

Sep 12, 2026cs.MA

Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training

Clinical education must prepare medical students to conduct safe and coherent patient interviews under conditions of uncertainty. Traditional standardized patient (SP) training is resource-intensive and difficult to scale. We developed a scaffolding-oriented multi-agent Large Language Model (LLM) AI Standardized Patient (AI-SP) training platform1. The system includes a patient agent for simulated dialog, a tutor agent providing Socratic prompts without disclosing diagnostic information, and a turn-level evaluator agent that monitors clinical progress without revealing summative scores. In a randomized controlled study (N = 100 medical students), participants were assigned to either a multi-agent (MA) scaffolding condition or a control condition. All students completed two learning sessions under their assigned condition followed by an examination conducted in a patient only environment. Performance was assessed using a standardized Objective Structured Clinical Examination (OSCE) based rubric. While no significant difference was observed in final diagnostic accuracy between groups, the multi-agent AI standardized patient system improved final examination scores compared to the control group utilizing structured progressive information disclosure; the most substantial and consistent improvements were observed in communication, the expression of empathy, and specific history-taking behaviors. These findings suggest that specialized LLM agents enhance the process quality of simulated clinical interviews without artificially inflating examination outcomes. To support future research, we release a multi-expert annotated dataset comprising transcripts, checklist annotations, turn-level evaluations, and OSCE-aligned scoring outcomes. This resource aims to facilitate the development of pedagogically grounded AI-SP systems and advance research on AI-supported clinical reasoning training.

Luming Yang, Haoxian Liu, Siqing Li +4

Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA · Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Department of Statistics and Data Science, Southern University of Science and Technology, Shenzhen, China +3

Educational Technology LLM Agent Evaluation Multi-Agent LLMs

Sep 10, 2026cs.AI

A Voice-Interactive Multi-Agent System for Smart Operating Rooms: Architecture Design and Key Technologies

This paper presents SurgicalRoomAgent, a voice-interactive multi-agent system for smart operating rooms based on large language models (LLMs). The system achieves natural language understanding, device control, intraoperative recording, and surgical report generation through a layered architecture comprising a voice interaction pipeline (wake, ASR, turn detection, agent reasoning, TTS) and an agent core (skill registry, task planner, device manager). Three key technologies are investigated: (1) KV Cache prefix warming for low-latency inference, reducing recomputation overhead from approximately 500 ms to tens of milliseconds via byte-level Longest Common Prefix reuse; (2) streaming partial JSON parsing with early parallel task execution, reducing end-to-end latency by approximately 30%; and (3) progressive skill prompt disclosure, which dynamically filters system prompts based on user role, connected devices, and surgical phase to maximize information density within limited context windows. The system is implemented using the Qwen3-27B model with llama.cpp/sglang inference engines. Experimental analysis demonstrates effective operation within a 16,384-token context limit and multi-device parallel control response times meeting OR real-time requirements.

Tianxiang Zhou

Wuhan United Imaging Surgical Co., Ltd. (UIS) Wuhan, China

Language Model-Based Control LLM Agent Orchestration LLM Inference Acceleration LLM Agents Multi-Agent LLMs

Sep 10, 2026cs.AI

Multi-Agent Agentic Graph Learning via Structural Signatures

Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existing methods either employ a single agent or orchestrate multiple role-based agents to reason and learn over the entire graph, but both essentially rely on a shared reasoning policy across different graph regions, which can be suboptimal for graphs with heterogeneous structural and semantic patterns. Inspired by the progress of multi-agent collaboration on complex reasoning tasks, a natural remedy is to let multiple agents own different memory and collaborate; however, applying this paradigm to graphs directly faces two challenges. First, existing AGL methods typically verbalize graph structures into natural-language descriptions for LLM agents, making the reasoning process sensitive to the ordering of structural information and thereby breaking the permutation-invariant nature of graphs. Second, incorporating increasingly large sampled neighborhoods leads to rapidly growing contexts. To address these challenges, this paper introduces a multi-agent agentic graph learning (i.e., MAAGL) framework. MAAGL partitions the graph into communities and assigns an independent agent to each community for region-specific specialization. MAAGL represents structural and semantic evidence separately. Structural evidence is summarized by a dynamically updated structural signature that is permutation-invariant and fixed in size, while semantic evidence is filtered to the top-k nodes ranked by relevance. Based on historical trajectories with similar signatures, agents estimate their confidence and trigger debate-style collaboration when needed. Extensive experiments on four benchmark datasets show that MAAGL outperforms SOTA AGL methods.

Liang Qu, Jianxin Li, Hua Wang

Edith Cowan University, Perth, Australia. · Victoria University, Melbourne, Australia.

Graph Representation Learning LLM Reasoning with Graphs Graph-Based Agent Memory Multi-Agent LLMs

Sep 7, 2026cs.MA

Scaling Multi-Agent Systems with Prospect-State Propagation

Current LLM-based multi-agent systems (MAS) periodically compress intermediate states to reduce inference-time token consumption, thereby attempting to incorporate more agents. However, naive scaling strategies face challenges. For example, in economic simulations, large-scale MAS typically discard semantically rich economic states, i.e., agent behavioral trajectories, which are key drivers of macroeconomic fluctuations. In this paper, we reveal a phenomenon in which agent heterogeneity gradually decreases during simulation, and propose Prospect-State Propagation for Multi-Agent Systems (PspMAS). Inspired by prospect theory, PspMAS decouples each agent's micro state into a compact Prospect State and an expressive Semantic State. The former records psychological traces through a lightweight, parallelizable propagator and continuously injects heterogeneity into the system. The latter leverages the strong perception, reasoning, planning, and decision-making abilities of LLMs. These two components work complementarily, providing a scalable LLM-based multi-agent simulation solution.

Zhimei Chen, Mu Chen, Fakhri Karray

1Independent Researcher · 2Mohamed bin Zayed University of Artificial Intelligence · University of Waterloo

Agent-Based Modeling Multi-Agent Systems Multi-Agent LLMs

Sep 7, 2026cs.AI

ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies

Large language model (LLM) agents are increasingly proposed for enterprise workflows, yet existing evaluations rarely test whether business-decision conclusions transfer across competitive market ecologies. We introduce ERPBench, an execution-instrumented benchmark for enterprise decision agents in a six-round Enterprise Resource Planning (ERP) simulation with coupled pricing, production, procurement, inventory, finance, and shared-market competition. ERPBench evaluates the same 100 fixed problems in two matched competitive market ecologies: Solo, where each evaluated LLM agent competes against fixed rule-based opponents, and Arena, where six evaluated LLM agents compete in a shared market. Across six model families, this yields 1,200 model-level trajectories spanning 7,200 decision rounds. Under the observed service configuration, the leading model differs between ecologies: DeepSeek leads in Solo (252.29M mean valuation; mean rank 1.67), whereas Gemini leads in Arena (263.95M; 1.76). The two ecologies identify the same task-level winner on only 21 of 100 problems, and Gemini's bottom-rank rate falls from 22 % to 0 % in Arena. ERPBench supports paired evaluation of whether enterprise-agent rankings transfer across competitive market ecologies, supplemented by aggregate execution-intervention analysis. Code and benchmark resources are available in our https://github.com/GAIR-NLP/erp-bench.

Xinran Zhang, Pengrui Lu, Lyumanshan Ye +1

1Shanghai Innovation Institute · 2Beijing Institute of Technology · 4GAIR Lab +1

AI-Assisted Decision Making LLM Agent Evaluation AI Agent Benchmarks Multi-Agent LLMs

Sep 1, 2026cs.CL

GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions

The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implications for safety and monitorability as well as for linguistic accounts of LLMs. To address these questions, we introduce GlossoGen, a novel platform for studying multi-agent language evolution in complex scenarios. Within GlossoGen, we build the SaveVeyru scenario, which requires agents with partial information to communicate under pressure. We find that language evolution does occur between LLM agents, that the resulting languages are compositional and morphologically productive, and that they deviate from the LLMs' English prior in ways that render them incomprehensible to humans. Moreover, we identify several qualities essential to this evolution: pressure towards efficiency; the strength of the models backing the agents; and access to a "postmortem" stage in which agents can agree on linguistic conventions. Importantly, we observe that different conditions govern the transmission of language to new agents. Specifically, we find that agents learn new languages from usage alone, take an active role in this learning, and that while stronger models are required for novel language emergence, weaker models can learn an existing language once it has emerged. Taken together, our results indicate that current LLMs have the potential for cumulative cultural evolution -- previously attested only in humans -- with mixed populations of agents developing capacities that go beyond their lowest common denominator.

Elias Stengel-Eskin, Newton Sander, Carlos Bonetti +4

University of Texas at Austin · AE Studio · Schmidt Sciences +1

Multi-Agent LLMs Emergent Communication

Sep 1, 2026cs.AI

ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything

Large language model (LLM)-based multi-agent systems (MAS) have shown strong potential for solving complex tasks, yet their development forces a tradeoff: code frameworks are expressive but engineering-intensive, while no-code builders simplify authoring but constrain agent interactions to author-defined workflows. We present ChatDev 2.0: DevAll (hereafter DevAll), a no-code platform for building, executing, and inspecting heterogeneous MAS that delivers both high expressiveness and ease of use. In terms of expressiveness, DevAll pairs a declarative executable graph abstraction with a cycle-aware execution engine, so that heterogeneous agents and dynamic and cyclic interactions can be represented and executed within a single framework. For ease of use, an integrated visual interface lets users author, run, monitor, and inspect MAS, including human-in-the-loop steps, entirely without writing code. Experiments demonstrate that DevAll reproduces state-of-the-art MAS across three representative tasks at competitive performance and without task-specific orchestration code, highlighting its effectiveness as a general-purpose platform for LLM-based MAS. DevAll is available at https://github.com/OpenBMB/ChatDev.

Yufan Dang, Shu Yao, Bowen Lai +6

Tsinghua University · Shanghai Innovation Institute · Shanghai Jiao Tong University +3

Multi-Agent Orchestration Multi-Agent Systems Multi-Agent LLMs

Sep 1, 2026cs.AI

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code relies. As a result, a prompt edit intended to improve content generation can inadvertently corrupt the protocol and cause the entire agent pipeline to fail. Our key observation is that these two roles have different representations: execution protocols are typically structured, while task-relevant content is usually expressed in unstructured language. Based on this, we propose control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant language remains the optimizable data flow for agent communication. This design allows optimizers to improve multi-agent behavior without exposing the routing or formatting interface to prompt drift. Across synthetic reasoning, collaborative review generation, and insurance rating workflows, our framework empirically achieves 100% eventual protocol validity while consistently improving task performance.

Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti +4

University of Waterloo · Manulife

LLM Agent Orchestration LLM Agent Workflow Optimization Prompt Optimization Multi-Agent Communication Multi-Agent LLMs

Sep 1, 2026cs.CR

SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems

Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-agent setting can easily be mistaken for evidence of a genuinely multi-agent security effect. We thus systematize MAS security through an execution-centered analysis of 197 works, covering six interaction interfaces, four adversary positions, seven system-level risks, and eight recurring attack paths. We introduce an A-I-R framework that organizes attacks by adversary position, interaction interface, and resulting system-level risk, unifying otherwise fragmented attack mechanisms across MAS. We organize defenses through a five-part contract covering path target, observation, intervention, trust boundary, and recovery, and identify path closure and recovery as key challenges. We audit 44 evaluation and benchmark works and identify open challenges in isolating interaction effects, designing comparable and diagnostic metrics, supporting reuse across MAS designs, and evaluating open-system operation. Together, these findings motivate an interaction-aware view of MAS security: trace attacks end to end, test whether defenses close those paths, and evaluate system-level effects with appropriate counterfactuals.

Rui Yang, Junjie Xu, Zhengyu Liu +4

Johns Hopkins University · Nanyang Technological University

AI Agent Security Benchmarks Multi-Agent System Security Multi-Agent LLMs

Aug 31, 2026cs.CL

SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?

Large language model-based multi-agent systems are evolving from fixed interaction topologies toward dynamically orchestrated Agent Swarms. However, existing benchmarks are still largely based on single-agent or general-purpose agent tasks, making it difficult to systematically evaluate key orchestration capabilities. We propose SwarmBench, a benchmark that evaluates model performance from multiple perspectives, including accuracy, efficiency, cost, and process quality. Experimental results show that current models exhibit substantial differences in orchestration capability. These differences are reflected not only in final accuracy, efficiency, and cost, but also in the overall quality of the orchestration process itself. Based on these findings, we further propose SwarmExp, a simple yet effective method based on experience extraction and experience replay, which consistently improves the orchestration performance of large language models.

Jinshan Gao, Zhuoran Jin, Tianyi Men +2

The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

LLM Agent Orchestration AI Agent Benchmarks Multi-Agent LLMs