Multi-Agent LLMs

Ensuring that AI agents behave safely and beneficially when interacting with other parties has emerged as one of the central challenges of modern AI safety. While mechanism design, as the theory of designing rules to align individual and collective objectives, can incentivize cooperative behavior, it is still an open question whether it alone is sufficient to maximize LLM agents' social welfare. This work proves that the answer is negative: drawing from incomplete contract theory, we formally show that when contracts cannot distinguish all relevant future contingencies, there is a strictly positive welfare loss that no realistic mechanism can eliminate. We show that prosocial agents, who weigh others' welfare alongside their own, can close this gap and achieve outcomes that are socially superior and individually beneficial. Experimentally, we show that in multi-agent resource-allocation environments and canonical social dilemmas where agents are powered by large language models, prosociality is beneficial. The implication for AI safety is clear: to enable cooperative interactions at scale, designing adequate mechanisms is not sufficient; agents must be built to be intrinsically prosocial.

Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and game-theoretic environments. Existing approaches often entangle opponent modeling with prediction, relying on implicit contextual reasoning and limiting adaptability in dynamic interactions. To this end, we propose Structured Opponent Modeling (SOM), a two-stage opponent modeling framework that distinctly separates opponent model construction and opponent prediction. At the construction stage, SOM employs a Structural Causal Model (SCM), a graph-based formalism for representing dependencies among variables, to capture directed links between opponents' observations and actions, yielding an explicit and structured opponent representation. At the prediction stage, the LLM performs structured reasoning along clear pathways derived from the SCM, improving both prediction accuracy and stability. Extensive experiments on diverse multi-agent benchmarks demonstrate that SOM consistently outperforms state-of-the-art LLM-based reasoning baselines, enabling more accurate and adaptable strategic decision-making in complex and dynamic multi-agent interactions.

Large Language Models (LLMs) demonstrate strong capabilities for solving scientific and mathematical problems, yet they struggle to produce valid, challenging, and novel problems - an essential component for advancing LLM training and enabling autonomous scientific research. Existing problem generation approaches either depend on expensive human expert involvement or adopt naive self-play paradigms, which frequently yield invalid problems due to reward hacking. This work introduces VHG, a verifier-enhanced hard problem generation framework built upon three-party self-play. By integrating an independent verifier into the conventional setter-solver duality, our design constrains the setter's reward to be jointly determined by problem validity (evaluated by the verifier) and difficulty (assessed by the solver). We instantiate two verifier variants: a Hard symbolic verifier and a Soft LLM-based verifier, with evaluations conducted on indefinite integral tasks and general mathematical reasoning tasks. Experimental results show that VHG substantially outperforms all baseline methods by a clear margin.

Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In contrast, fully unstructured teams enable adaptability and exploration but suffer from inefficiencies such as error propagation, inter-agent conflicts, and wasted resources (measured in time, tokens, or file operations). We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems, where processors must operate under partial observability and communication constraints. In LATTE, a team of agents collaboratively construct and maintain a shared, evolving coordination graph which encodes sub-task dependencies, individual agent assignment, and the current state of sub-task progress. This protocol maintains consistency while empowering agents to dynamically allocate work, adapt coordination, and discover new tasks. Across multiple collaborative tasks and a variety of base models, we demonstrate how LATTE reduces token usage, wall-clock time, communication, and coordination failures (e.g. file conflicts and redundant outputs) while matching or exceeding the accuracy of standard designs including MetaGPT, decentralized teams, top-down Leader-Worker hierarchies, and static decompositions.

Static capabilities benchmarks suffer from saturation and contamination, making it difficult to track capabilities progress over time. We introduce Agent Island, a multiplayer simulation environment in which language-model agents compete in a game of interagent cooperation, conflict, and persuasion. The environment yields a dynamic benchmark designed to mitigate both saturation and contamination; new models can always outperform the current leading player in this winner-take-all game, and agents compete against other adaptive agents rather than face a fixed task set. We rank players with a Bayesian Plackett-Luce model, allowing us to quantify uncertainty in player skill. In 999 games involving 49 unique models, openai/gpt-5.5 dominates its peers with a posterior mean skill of 5.64, compared with 3.10 for the second-ranked model, openai/gpt-5.2, and 2.86 for the third-ranked model, openai/gpt-5.3-codex. We release the game logs as a dataset for analyses of model behavior. As an example, we investigate same-provider preference in final-round votes and find that models are 8.3 p.p. more likely to support a same-provider finalist than finalists from other providers. This preference is not uniform across providers: among separately estimated providers, the effect is strongest for OpenAI models and weakest for Anthropic models.

Discharge summaries require extracting critical information from lengthy electronic health records (EHRs), a process that is labor-intensive when performed manually. Large language models (LLMs) can improve generation efficiency; however, they are prone to producing faithfulness hallucinations, statements that contradict source records, posing direct risks to patient safety. To address this, we present CuraView, a multi-agent framework for sentence-level detection and evidence-grounded explanation of faithfulness hallucinations in discharge summaries. CuraView constructs a GraphRAG-based knowledge graph from patient-level EHRs and implements a closed-loop generation-detection pipeline with sentence-level evidence retrieval and classification spanning four evidence grades from strong support to direct contradiction (E1-E4), yielding structured and interpretable evidence chains. We evaluate CuraView on a subset of 250 patients from the Discharge-Me benchmark, with 50 patients held out for testing. Our fine-tuned Qwen3-14B detection model achieves an F1 of 0.831 on the safety-critical E4 metric (90.9% recall, 76.5% precision) and an F1 of 0.823 on E3+E4, representing a 50.0% relative improvement over the base model and outperforming RAGTruth-style and QAGS-style baselines. These results demonstrate that evidence-chain-based graph retrieval verification substantially improves the factual reliability of clinical documentation, while simultaneously producing reusable annotated datasets for downstream model training and distillation.

Language models (LMs) are increasingly used in high-stakes, multi-agent settings, where following instructions and maintaining value alignment are critical. Most alignment research focuses on interactions between a single LM and a single user, failing to address the risk of misaligned behavior spreading between multiple LMs in multi-turn interactions. We find evidence of this phenomenon, which we call misalignment contagion, across multiple LMs as they engage multi-turn conversational social dilemma games. Specifically, we find that LMs become more anti-social after gameplay and that this effect is intensified when other players are steered to act maliciously. We explore different steering techniques to mitigate such misalignment contagion and find that reinforcing an LM's system prompt is insufficient and often harmful. Instead, we propose steering with implicit traits: a technique that intermittently injects system prompts with statements that reinforce an LMs initial traits and is more effective than system prompt repetition at keeping models in line with their initial pro-social behaviors. Importantly, this method does not require access to model parameters or internal model states, making it suitable for increasingly common use cases where complex multi-agent workflows are being designed with black box models.

Grounding is the collaborative process of establishing mutual belief sufficient for a communicative goal. While static grounding maps language to a shared context, dynamic grounding requires agents to negotiate meaning across turns. Current multi-agent Large Language Model (LLM) benchmarks largely emphasize static, one-shot tasks, overlooking whether agents can repair grounding breakdowns through interaction. We introduce an iterated multi-turn negotiation game where two agents allocate shared resources to private projects with verifiable jointly optimal outcomes. Although individual agents can identify Pareto-optimal allocations in isolation, agent dyads consistently fail to reach them across models. We identify four failure modes: (1) loss of shared interaction history, (2) stubborn anchoring to early proposals, (3) defaulting to equal splits over reward-maximizing coordination, and (4) referential binding errors across turns. Our baselines show that the coordination gap is not explained by individual reasoning limits or insufficient information exchange alone. Instead, the bottleneck lies in dynamic grounding: joint plan formation, commitment, and execution.

Sixth-generation (6G) networks are increasingly envisioned as AI-native infrastructures integrating communication, sensing, and computing into a unified fabric. However, existing approaches remain largely optimization-centric, relying on closed-loop control with limited reasoning capability. In this paper, we argue for a paradigm shift toward Agentic AI-Native 6G, in which Large Language Model (LLM)-based agents operate as bounded, policy-governed reasoning entities within a semantic control plane layered above deterministic 3GPP infrastructure. We propose a four-layer architecture that integrates deterministic network infrastructure, semantic abstraction of intent and context, hierarchical reasoning, and a distributed multi-agent fabric spanning device, edge, and core domains. To assess feasibility, we develop a proof-of-concept agentic reasoning and orchestration framework and conduct an extensive empirical study using a domain-specific 6G benchmark under realistic deployment constraints. Our results reveal a fundamental tradeoff between reasoning capability and system efficiency, showing that no single model simultaneously satisfies latency, throughput, and accuracy requirements. Instead, heterogeneous deployment of LLM agents across the device--edge--core continuum is necessary to balance these constraints. We further demonstrate that quantization introduces non-uniform effects across models, reinforcing the need for system-level optimization rather than model-level compression alone. These findings establish agentic intelligence as a viable architectural direction for 6G and highlight key challenges in achieving scalable, trustworthy, and self-reasoning networks. All experimental results and evaluation scripts are publicly available to support reproducibility.

The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy. Traditional content moderation systems rely on centralised, top-down rules, often failing to accommodate the subjective nature of harm perception. This paper proposes an LLM-based multi-agent personalised inference framework that filters content based on unique sensitivity profiles of individual users. Our architecture combines domain-specific Expert Agents, a Manager Agent for orchestrating content analysis and agent selection, and a Ghost Profile Agent for simulating user perspectives, to inform moderation decisions. Evaluated against a range of non-personalised baselines, the system demonstrates up to a 32% improvement in accuracy, showing increased alignment with individual user sensitivities. Beyond technical performance, our framework provides policy-relevant insights for platform governance, providing a scalable way to reconcile moderation policies with societal and individual digital rights

Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines. We identify a structural failure mode in sequential fine-tuning of shared-context teams: updating one agent shifts the team's context distribution, and when subsequent updates are evaluated on cached rollouts, this mismatch compounds. We formalize this as the compounding occupancy shift and prove that stale-occupancy evaluation incurs a penalty that scales quadratically with the number of agents. In contrast, intermediate-occupancy evaluation reduces this to linear scaling. We propose TeamTR, a trust-region framework that resamples trajectories after each component update and enforces per-agent divergence control, yielding rigorous per-update and per-stage improvement lower bounds. Experiments show that TeamTR outperforms single-agent and sequential baselines with 7.1% on average, mitigates coordination regressions, and supports plug-and-play component replacement. Code is available at https://github.com/Yydc/TeamTR.

As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper argues that this assumption is fundamentally mistaken. In agentic AI, safety is determined by interaction topology, not model weights. When agents deliberate sequentially or aggregate via parallel voting with a judge, the structure of information flow and decision coupling dominates outcomes. Evidence across model families and scales reveals three persistent topology-driven pathologies: ordering instability, where system behavior depends primarily on agent sequence; information cascades, where early judgments propagate regardless of correctness; and functional collapse, where systems satisfy fairness metrics while abandoning meaningful risk discrimination. Contrary to intuition, scaling to more capable models strengthens these effects by increasing consensus formation and reducing the challenge of initial decisions. These failure modes are invisible to model-centric evaluation and alignment procedures. We argue that agentic AI must be treated as a dynamical system rather than a collection of aligned components. Interaction topology must become a primary target of safety evaluation and regulation, with systems required to demonstrate robustness across architectural variations before deployment.

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious agents can propagate misinformation and manipulate group decisions, undermining MAS safety. Existing embedding-based defenses aim to detect and prune suspicious agents, but their effectiveness depends on a clear separation between the text embeddings of malicious and benign messages. Attackers can circumvent such defenses by crafting messages whose embeddings lie close to benign ones. We analyze this failure mode theoretically and validate it empirically with three attacks, Slow Drift, Benign Wrapper, and Chaos Seeding. Our analysis further reveals a fundamental limitation of embedding-based defenses: because they rely solely on the text embeddings, they ignore token-level confidence signals such as logits, which can remain informative when embeddings are not distinguishable under attack. We propose using confidence scores to prune or down-weight messages during MAS communication. Experiments show improved robustness across models, datasets, and communication topologies. Moreover, we find that the effectiveness of confidence signals decays over communication rounds, highlighting the importance of early intervention. This insights can inform and inspire future work on MAS attacks and defenses.

Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an agentic AI framework that replaces the traditional signal then execute paradigm with a fully autonomous deliberative loop in which multiple specialized Large Language Model agents reason, negotiate, and act in concert - without any offline training or human intervention. The framework proposes four architectural contributions: (i) an Adaptive Z-Score Trigger Engine that acts as a cognitive resource allocator, gating LLM inference exclusively on statistically anomalous market conditions; (ii) a Sequential Deliberative Pipeline - the core agentic contribution - in which an Analyst agent, a Risk Manager agent, and an Executor agent form a structured reasoning chain governed by typed JSON contracts and a deterministic hard-gate safety layer; (iii) an Inference Gating Protocol, a mutex-based cognitive resource scheduler that serializes concurrent agent activations and ensures fully reproducible audit trails; and (iv) a Correlation-Break Diversification composite score that operationalizes portfolio-level idiosyncratic signal prioritization within individual agent reasoning. Validated over a five-day autonomous dry-run session under live market conditions, the framework demonstrates operational correctness of the deliberative pipeline, achieving 157 zero-intervention invocations across 76 assets with an 11.5% agentic friction rate that confirms non-trivial inter-agent negotiation. This preliminary proof-of-concept establishes the feasibility of training-free, deterministic safety-constrained multi-agent orchestration in financial decision loops, with statistically robust performance evaluation and execution cost modeling deferred to extended live deployment.

Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded perception context budgets. Existing agentic methods mitigate this via rule-based preprocessing, yet often suffer from information loss, high cost, and reliance on textual intermediates. We propose MACF, an end-to-end Multi-Agent Collaboration Framework that decouples per-agent perception budgets from global video complexity, enabling scalable video understanding while preserving visual fidelity. MACF partitions videos into segments for locally budgeted agents and enables holistic reasoning via an agent-native latent communication protocol. Each agent encodes partial observations into compact, task-sufficient tokens in a shared embedding space, allowing efficient and information-preserving collaboration by a central coordinator. We introduce a curriculum training strategy that progressively enforces semantic alignment, evidence summarization, and cross-agent coordination. Extensive experiments on diverse video understanding benchmarks show that MACF consistently outperforms state-of-the-art MLLMs and multi-agent systems under identical budget constraints, demonstrating the effectiveness of our latent collaboration for scalable video understanding.

LLM agents are known to deviate from Nash equilibria in strategic interactions, but nobody has looked inside the model to understand why, or asked whether the deviation can be reversed. We do both. Working with four open-source models (Llama-3 and Qwen2.5, 8B to 72B parameters) playing four canonical two-player games, we establish the behavioral picture through self-play and cross-play experiments, then open up the 32-layer Llama-3-8B model and examine what actually happens during a strategic decision. The mechanistic findings are clear. Opponent history is encoded with near-perfect fidelity at the first layer (96% probe accuracy) and consumed progressively, while Nash action encoding is weak throughout, never exceeding 56%. There is no dedicated Nash module. Instead, the model privately favors the Nash action through most of its forward pass, but a prosocial override rooted in pretraining on human text concentrated in the final layers reverses this, reaching 84% probability of cooperation at layer 30. Injecting a learned Nash direction into the residual stream shifts behavior bidirectionally and causally, confirmed through concept clamping. The behavioral experiments surface six scale- and architecture-dependent findings, the most notable being that chain-of-thought reasoning worsens Nash play in small models but achieves near-perfect Nash play above 70B parameters. The cross-play experiments reveal three phenomena invisible in self-play: a small model can unravel any partner's cooperation by defecting early; two large models reinforce each other's cooperative instincts indefinitely; and who moves first determines which Nash equilibrium the system reaches. LLMs do not lack Nash-playing competence. They compute it, then suppress it.

The purpose of our paper is to develop a unified multi-agent architecture that automates end-to-end machine learning (ML) pipeline generation from datasets and natural-language (NL) goals, improving efficiency, robustness and explainability. A five-agent system is proposed to handle profiling, intent parsing, microservice recommendation, Directed Acyclic Graph (DAG) construction and execution. It integrates code-grounded Retrieval-Augmented Generation (RAG) for microservice understanding, an explainable hybrid recommender combining multiple criteria, a self-healing mechanism using Large Language Model (LLM)-based error interpretation and adaptive learning from execution history. The approach is evaluated on 150 ML tasks across diverse scenarios. The system achieves an 84.7% end-to-end pipeline success rate, outperforming baseline methods. It demonstrates improved robustness through self-healing and reduces workflow development time compared to manual construction. The study introduces a novel integration of code-grounded RAG, explainable recommendation, self-healing execution and adaptive learning within a single architecture, showing that tightly coupled intelligent components can outperform isolated solutions.

Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requirements remains challenging for current large language models (LLMs). In this paper, we propose \emph{Agora-Opt}, a modular agentic framework for optimization modeling that combines decentralized debate with a read-write memory bank. Agora-Opt allows multiple agent teams to independently produce end-to-end solutions and reconcile them through an outcome-grounded debate protocol, while memory stores solver-verified artifacts and past disagreement resolutions to support training-free improvement over time. This design is flexible across both backbones and methods: it reduces base-model lock-in, transfers across different LLM families, and can be layered onto existing pipelines with minimal coupling. Across public benchmarks, Agora-Opt achieves the strongest overall performance among all compared methods, outperforming strong zero-shot LLMs, training-centric approaches, and prior agentic baselines. Further analyses show robust gains across backbone choices and component variants, and demonstrate that decentralized debate offers a structural advantage over centralized selection by enabling agents to refine candidate solutions through interaction and even recover correct formulations when all initial candidates are flawed. These results suggest that reliable optimization modeling benefits from combining collaborative cross-checking with reusable experience, and position Agora-Opt as a practical and extensible foundation for trustworthy optimization modeling assistance. Our code and data are available at https://github.com/CHIANGEL/Agora-Opt.

Language Model (LM)-based agents remain largely untested in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a multi-agent environment where players can engage in private negotiations while competing to be the first to achieve their secret objective. Players have asymmetric objectives and negotiations are non-binding, allowing alliances to form and break as players' short-term interests align and diverge. We run AI only games and conduct a user study pitting human players against AI opponents. We identify significant differences between human and AI negotiation behaviors, finding that humans favor lower-complexity deals and are significantly less reliable partners compared to LM-based agents. We also find that humans are more aggressive negotiators, accepting deals without a counteroffer only 56.3% of the time compared to 67.6% for LM-based agents. Through targeted prompting inspired by these findings, we modify agents' negotiation behavior and improve win rates from 22.2% to 32.7%. We run over 1,100 games with over 16,000 private conversations totaling 15.2 million tokens and over 150,000 player actions. Our results establish C2C as a testbed for studying and building LM-based agents that can navigate the sophisticated coordination required for real-world deployments. The game, code, and dataset may be found at https://negotiationgame.io/c2c.

As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models (typically written in SystemC) for early architecture exploration and verification. While Large Language Models (LLMs) show promise in code generation, their application to hardware modeling faces unique challenges: (1) Rigid, static workflows fail to adapt to varying design complexity, causing inefficiency; (2) Context window overflow in multi-turn interactions leads to catastrophic forgetting of critical specifications; and (3) the Coupled Validation Failure problem--where generated Testbenches (TBs) incorrectly validate flawed models due to correlated hallucinations--severely undermines reliability. To address these limitations, we introduce RefEvo, a dynamic multi-agent framework designed for agile and reliable reference modeling. RefEvo features three key innovations: (1) A Dynamic Design Planner that autonomously decomposes design specifications and constructs tailored execution workflows based on semantic complexity; (2) A Co-Evolutionary Verification Mechanism, which employs a Dialectical Arbiter to simultaneously rectify the model and verification logic against the specification (Spec) oracle, effectively mitigating false positives; and (3) A Spec Anchoring Strategy for lossless context compression. Evaluated on a diverse benchmark of 20 hardware modules, RefEvo achieves a 95% pass rate, outperforming static baselines by a large margin. Furthermore, our context optimization reduces token consumption by an average of 71.04%, achieving absolute savings of over 70,000 tokens per session for complex designs while maintaining 100% specification recall.

Efficient and fair spectrum allocation is a central challenge in 6G networks, where massive connectivity and heterogeneous services continuously compete for limited radio resources. We investigate the use of Large Language Models (LLMs) as bidding agents in repeated 6G spectrum auctions with budget constraints in vehicular networks. Each user equipment (UE) acts as a rational player optimizing its long-term utility through repeated interactions. Using the Vickrey-Clarke-Groves (VCG) mechanism as a benchmark for incentive-compatible, dominant-strategy truthfulness, we compare LLM-guided bidding against truthful and heuristic strategies. Unlike heuristics, LLMs leverage historical outcomes and prompt-based reasoning to adapt their bidding behavior dynamically. Results show that when the theoretical assumptions guaranteeing truthfulness hold, LLM bidders recover near-equilibrium outcomes consistent with VCG predictions. However, when these assumptions break -- such as under static budget constraints -- LLMs sustain longer participation and achieve higher utilities, revealing their ability to approximate adaptive equilibria beyond static mechanism design. This work provides the first systematic evaluation of LLM bidders in repeated spectrum auctions, offering new insights into how AI-driven agents can interact strategically and reshape market dynamics in future 6G networks.

Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that limit generalization. In contrast, large language models (LLMs) offer a flexible modeling interface that can naturally accommodate heterogeneous observations and actions. Motivated by this, we propose the Decision Language Model (DLM), which formulates multi-agent decision making as a dialogue-style sequence prediction problem under the centralized training with decentralized execution paradigm. DLM is trained in two stages: a supervised fine-tuning phase, which leverages dialogue-style datasets for centralized training with inter-agent context and generates executable actions from offline trajectories, followed by a group relative policy optimization phase to enhance robustness to out-of-distribution actions through lightweight reward functions. Experiments on multiple benchmarks show that a unified DLM outperforms strong offline MARL baselines and LLM-based conversational decision-making methods, while demonstrating strong zero-shot generalization to unseen scenarios across tasks.

As software systems grow in complexity, they must satisfy an increasing number of competing quality attributes, making it essential to balance them in a principled manner -- for example, a safety requirement for sensor-fusion verification may conflict with a tight planning-cycle budget. Multi-agent large language model frameworks support this balancing process by assigning specialized agents to different objectives. However, their conflict resolution is typically heuristic. Requirements are aggregated implicitly without explicit acceptance or rejection, limiting auditability in regulated domains. We present ArgRE, a multi-agent requirements negotiation system that embeds Dung-style abstract argumentation into the negotiation stage. Each proposal, critique, and refinement is modeled as an argument, conflicts are represented as directed attack relations, and the accepted set of arguments is computed under grounded and preferred semantics. The pipeline further integrates KAOS goal modeling, multi-layer verification, and standards-oriented artifact generation. Evaluation across five case studies spanning safety-critical, financial, and information-system domains shows that ArgRE provides argument-level traceability absent from existing frameworks. Independent evaluators rated its decision justifications significantly higher than those of heuristic synthesis (4.32 vs. 3.07, p < 0.001), indicating improved auditability, while semantic intent preservation remains comparable (94.9% BERTScore F1) and compliance coverage reaches 84.7% versus 47.6%--47.8% for baselines. Structural analysis further confirms that the default pairwise protocol yields acyclic graphs in which grounded and preferred semantics coincide, whereas cross-pair arbitration introduces controlled cyclicity, leading to predictable divergence between the two semantics.

The TRUST democratic discourse analysis pipeline exposes its large language model (LLM) components to peer model identity through multiple structural channels -- a design feature whose bias implications have not previously been empirically tested. We provide the first systematic measurement of identity-dependent scoring bias across all active identity exposure channels in TRUST, crossing four model families with two anonymization scopes across 30 political statements. The central finding is that single-channel anonymization produces near-zero bias effects, because individual channels act in opposite directions and cancel each other out -- a result that would lead an evaluator to conclude that identity bias is absent when it is not. Only full-pipeline anonymization reveals the true pattern: homogeneous ensembles amplify identity-driven sycophancy when model identity is fully visible, while the heterogeneous production configuration shows the reverse. Model choice matters independently: one tested model exhibits baseline sycophancy two to three times higher than the others and near-zero deliberative conflict on ideological topics, making it structurally unsuitable for pipelines where genuine inter-role disagreement is the intended quality mechanism. Three practical conclusions follow. First, heterogeneous model ensembles are structurally more robust than homogeneous ones, achieving higher consensus rates and lower identity amplification. Second, full-pipeline anonymization is required for valid bias measurement -- partial anonymization is insufficient and actively misleading. Third, these findings have direct implications for the validation of multi-agent LLM systems in quality-critical applications: a system validated under partial anonymization or with a homogeneous ensemble may pass validation while retaining structural identity bias invisible to single-channel measurement.

Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent communication through internal representations such as key-value caches offers a promising alternative to text-based protocols, but existing approaches do not jointly optimize communication with multi-agent reasoning. Therefore we propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems. DiffMAS performs parameter-efficient supervised training over multi-agent latent trajectories, enabling agents to jointly learn how information should be encoded and interpreted across interactions. Experiments on mathematical reasoning, scientific QA, code generation, and commonsense benchmarks show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods, achieving 26.7% on AIME24, 20.2% on GPQA-Diamond, and consistent gains across reasoning benchmarks.

We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the International Actuarial Association (IAA) Education Syllabus. The pipeline separates four LLM roles by adapter: one agent drafts items, one constructs distractors, a third independently verifies both stages and drives bounded one-shot repair loops, and a cost-optimized auxiliary agent handles Wikipedia-note summarization and topic labelling. The items, per-model responses and complete leaderboard are published as a browsable web interface at https://actubench.de/en/, allowing readers and practitioners to inspect individual items without a repository checkout. We evaluate 50 language models from eight providers on two complementary benchmarks -- 100 empirically hardest multiple-choice items and 100 open-ended items scored by an LLM judge -- and report three headline findings. First, multi-agent verification is load-bearing: the independent verifier flags a majority of drafted items on first pass, most of which the one-shot repair loop resolves. Second, locally-hosted open-weights inference sits on the cost-performance Pareto front: a Gemma~4 model running on consumer hardware and a Cerebras-hosted 120B open-weights model dominate the near-zero-cost region, with the latter within one item of the top of the leaderboard. Third, MCQ and LLM-as-Judge rankings differ meaningfully: the MCQ scaffold inflates the performance ceiling, and Judge-mode evaluation is needed to discriminate at the frontier.

Automated feature generation extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable machine learning. Traditional methods rely on predefined operator libraries and cannot leverage task semantics, limiting their ability to produce diverse, high-value features for complex tasks. Recent Large Language Model (LLM)-based approaches introduce richer semantic signals, but still suffer from a restricted feature space due to fixed generation patterns and from the absence of feedback from the learning objective. To address these challenges, we propose a Memory-Augmented LLM-based Multi-Agent System (\textbf{MALMAS}) for automated feature generation. MALMAS decomposes the generation process into agents with distinct responsibilities, and a Router Agent activates an appropriate subset of agents per iteration, further broadening exploration of the feature space. We further integrate a memory module comprising procedural memory, feedback memory, and conceptual memory, enabling iterative refinement that adaptively guides subsequent feature generation and improves feature quality and diversity. Extensive experiments on multiple public datasets against state-of-the-art baselines demonstrate the effectiveness of our approach. The code is available at https://github.com/fxdong24/MALMAS

Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing price movements? We conduct a controlled experiment where AI agents trade in a prediction market after receiving private signals, measuring information aggregation by the log error of the last price. We find that although the median market is effective at aggregating information in the easy information structures, increasing the complexity has a significant and negative impact, suggesting that AI agents may suffer from similar limitations as humans when reasoning about others. Consistent with our theoretical predictions, information aggregation remains unaffected by allowing cheap talk communication, changing the duration of the market or initial price, and strategic prompting, thus demonstrating that prediction markets are robust. We establish that "smarter" AI agents perform better at aggregation and they are more profitable. Surprisingly, giving them feedback about past performance has no impact on aggregation.

Team-level failure in nuclear control rooms arises not from isolated operator error, but from emergent interaction dynamics, delayed diagnosis, suppressed dissent, and authority-driven error propagation, that conventional human reliability analysis methods are structurally unable to model. This study introduces TEAM-SimHRA, a multi-agent large language model simulation framework that reconceptualizes human reliability as an interaction-driven emergent property of control room teams rather than a static individual attribute. Unlike existing approaches that assign fixed error probabilities to predefined tasks, TEAM-SimHRA reproduces collective cognition, role-conditioned authority dynamics, and real-time communication suppression across temporally evolving accident progressions. Validated against the Three Mile Island (1979) and Chernobyl (1986) accidents, the two most extensively documented nuclear team failures , the framework achieves face-validity pass rates of 43.5% and 52.6% respectively, reproducing near-historical decision delay (134.8 vs. 138 min), perfect communication suppression stability, and full authority pressure cascade at historically accurate propagation depth. These results demonstrate that multi-agent simulation can extract quantitative team-level reliability indicators that are inaccessible to traditional methods, opening a viable path toward simulation-based dynamic probabilistic risk assessment for safety-critical sociotechnical systems.

With the rapid advancement of artificial intelligence, multi-agent systems (MASs) are evolving from classical paradigms toward architectures built upon large foundation models (LFMs). This survey provides a systematic review and comparative analysis of classical MASs (CMASs) and LFM-based MASs (LMASs). First, within a closed-loop coordination framework, CMASs are reviewed across four fundamental dimensions: perception, communication, decision-making, and control. Beyond this framework, LMASs integrate LFMs to lift collaboration from low-level state exchanges to semantic-level reasoning, enabling more flexible coordination and improved adaptability across diverse scenarios. Then, a comparative analysis is conducted to contrast CMASs and LMASs across architecture, operating mechanism, adaptability, and application. Finally, future perspectives on MASs are presented, summarizing open challenges and potential research opportunities.