Papers

Histology and transcriptomics provide complementary views of tissue biology, capturing spatial morphology and molecular activity, respectively. Pathology foundation models (PFMs) learn rich morphological representations from H&E images, yet strong downstream performance alone does not establish whether these representations encode biologically meaningful and robust molecular information. We present a **training-free framework for auditing biological alignment in frozen PFMs** using spatially paired histology and transcriptomics from HEST-1k, evaluated on **240 samples spanning three organs**. Multiple frozen PFMs are used to extract H&E representations, while gene expression is aggregated into biologically interpretable pathway-level programs. We use TabPFN as a pretrained probe to quantify the extent to which these molecular programs can be decoded from frozen image representations without task-specific gradient updates. Beyond predictive performance, our audit examines whether pathway decodability generalizes across tissue sections, patient groups, and tissue types; whether representations exhibit section-level or other shortcut dependencies; and whether predictions remain stable under small image perturbations and context resampling. This multi-tissue evaluation distinguishes molecular programs that are consistently encoded from those that are tissue-specific, unstable, or shortcut-sensitive. Our framework therefore provides a systematic approach for assessing not only **what biological information pathology foundation models encode, but also how reliably that information persists under clinically relevant sources of variation**.

Social dynamical networks significantly influence contemporary digital landscapes, affecting realms from social activism to public policy formulation. This paper investigates the use of multi-agent systems (MAS) to monitor and analyze these networks. Firstly, we propose a single-time-scale distributed inference model designed to effectively manage challenges such as latency and agent failure. Secondly, we provide sufficient conditions that ensure the stability of the proposed scheme. Notably, the observer gain design remains effective regardless of time delays. Thirdly, we develop a computationally efficient recovery mechanism for agent failures that relies on employing graph-theoretic approaches to restore network observability by replacing failed agents (due to sensing failure or unbounded delays, i.e., packet drops) by implementing computationally efficient graph-theoretic methods to assign observationally equivalent agent counterparts. Lastly, we illustrate the proposed scheme through a pedagogical example and real-world network applications.

Cooperation is a cornerstone of human societies, enabling collective progress in dynamic and uncertain environments. With the advent of AI systems acting autonomously, it becomes crucial to understand not only human-AI cooperation but also AI-AI interactions in adaptive networks. In this work, we examine the interactions of AI using Large Language Models – Mistral, Llama3, Gemma3, and Phi3 – in a public goods game within dynamic network structures. Our experiments were conducted under single-model and mixed-model conditions across Watts-Strogatz (WS), Barabasi-Albert (BA), and Erdos-Renyi (ER) networks. We analyzed the impact of model architecture, network topology, and prompt design on cooperative behavior. Results show that Mistral and Llama3 offer high cooperation rates, while Phi3 shows defective tendencies. Additionally, the random structure of Erdos-Renyi networks dramatically improves cooperation. Prompt design also plays a key role; a society-benefits prompt leads to a higher cooperation level. These findings offer a preliminary framework for LLM-based simulations in adaptive social networks.

Artificial intelligence is transforming personalized healthcare, yet fragmented clinical, self reported, and wearable evidence remains difficult to interpret and trace. We present CareGraph, an auditable hybrid AI framework that converts heterogeneous records into prioritized trends, missing context indicators, bounded next steps, discussion questions, and provenance linked explanations. CareGraph organizes evidence without diagnosing, predicting outcomes, selecting treatment, or making autonomous clinical decisions. Its pipeline covers deterministic analysis, context detection, graph construction, constrained language model synthesis, evidence validation, safety controls, and release gating. Tests used synthetic cohorts of 400 patients each for development, validation, and holdout. On holdout data, a frozen ordinary least squares trend rule with a sufficiency gate achieved 0.827 accuracy, 0.837 macro F1 with a 95 percent confidence interval of 0.819 to 0.854, and 0.974 insufficient data F1. Missing context detection achieved 0.815 strict micro F1 versus 0.318 for the legacy detector. On an authored holdout benchmark, safety ruleset version 1.2 achieved 1.000 precision, 0.950 recall, and 0.974 F1. An audit requiring graph retrieval across 80 patients yielded 79 syntheses and 78 presentations without fallback; one output was blocked and one failed closed because of an invalid evidence key. Against monolithic GPT 5.6 on 56 matched patients, CareGraph was faster at 40.15 versus 49.62 seconds, shorter at 661 versus 1,163 words, and showed better exploratory lexical alignment with longitudinal targets; the baseline used fewer tokens and cited more raw evidence. Graph auditing verified provenance and deterministic retrieval; incremental graph effects on generation require paired evaluation. CareGraph offers a safety bounded foundation for intelligent personalized health systems.

Natural language driven autonomous co-scientist workflows involve a fundamental trade-off between flexibility and reasoning at the expense of determinism, reproducibility, and observability. Such agents increasingly must communicate across institutional boundaries, where federation topology can shape latency and cost. We systematically evaluated these tradeoffs using a controlled ablation on a production agentic platform for science. We use a verifiable task: given a protein sequence, we ask an agent to confidently characterize its function by routing across common tools. We compare federation topology, classic RL vs LLM-driven harnesses, language model, and prompt expertise. We also stratify results by protein novelty. We find that the choice of LLM dominated prediction quality far more than topology or prompting (Opus ~92%-94% vs o4-mini ~40%-50%). The PPO policy was nearly as accurate as the best LLM (88%) at zero token cost, fastest latency, and perfect consistency, but yields no reasoning trace. Expert prompted LLMs reached the highest accuracy but were high-cost and less consistent; prompt dependence was largest when the task was hardest. Federation imposed a negligible penalty on performance. These results offer actionable guidance for deploying agents for scientific workflows: for routine, verifiable tasks, a cheap deterministic policy delivers near-frontier accuracy with complete reproducibility, while flexible LLM reasoning is best reserved for open-ended discovery.

The increasing heterogeneity of multi-agent systems poses significant challenges for jointly training a global model across agents. At the same time, cooperative inference between agents has long been recognized as a powerful mechanism for distributed decision making over networks. Motivated by these observations, we propose a collaboration framework for distributed binary classification over multi-agent networks, where a set of independently trained agents, potentially differing in architecture, feature space, or modality, coordinate their actions during test time to form collective predictions. This coordination is achieved by exchanging local decision statistics through a distributed learning protocol. We develop a theoretical and experimental study of this independent training and cooperative inference paradigm, and examine its performance under different communication budgets and distributed learning rules. We establish classification error guarantees under sufficient, finite-round, and finite-precision communication, together with PAC-style generalization bounds. These results capture the influence of model heterogeneity, network topology, combination policy, and communication constraints on prediction accuracy. Taken together with the experimental results, they reveal both the price of independent training and the benefit of collective prediction for the proposed distributed decision making framework with models learned from data.

Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts. These records let a downstream agent continue without revisiting the complete upstream context. We uncover a hidden loss in this process: handoffs can carry tasks forward while eroding judgments already established upstream. A requirement that must be satisfied before action becomes a caveat that the next agent may acknowledge and set aside. The issue remains visible, but its role has changed. We define operational state preservation as retaining an established judgment's role in constraining downstream action. Safety blockers provide a concrete instance: an unresolved prerequisite restricts the admissible actions until the condition is resolved. In our experiments, we confirm correct upstream detection, hold source permissions fixed, and vary the handoff supplied to a local-view executor. Direct-state controls preserve every blocker, whereas compression, plan assimilation, convergence, ownership deferral, and precedent substitution repeatedly weaken them. Ownership deferral produces 76.7% blocker deactivation; multihop compression produces 97.2%. Measuring the transmitted state separately from endpoint action exposes two routes to behavioral recovery. In fixed-artifact replays, restoring the full blocker description raises recognition from 6.2% to 99.2% and reduces forbidden action from 85.2% to 0.0%. An authorization-check prompt instead reduces forbidden action to 1.6% while leaving artifact deactivation at 95.3%. A successful endpoint can therefore conceal a damaged handoff. These findings make maintaining earlier judgments a core capability of reliable collaboration: each stage must carry forward both what earlier work established and what it requires of subsequent action. Semantic availability does not guarantee operational preservation.

Prehospital stroke assessment aims to accurately identify stroke symptoms and make rapid decisions through standardized procedures within an extremely narrow time window, thereby saving valuable time for subsequent treatment. In clinical practice, FAST-based scales are widely used for prehospital stroke assessment by issuing instructions that guide subjects to perform specific actions to screen facial, arm, and speech functions. However, in home and community settings, non-clinical users often encounter challenges such as inaccurate descriptions, incomplete symptom observation, and difficult operational procedures, which may lead to inaccurate or biased assessment results. To address these challenges, this paper presents StrokeGuard: a multi-agent guided system designed for prehospital stroke assessment that makes mobile FAST screening more standardized and executable. Specifically, to overcome the limitations of traditional single-agent systems in terms of procedural fault tolerance and user guidance capability, StrokeGuard adopts a dual-channel agent mechanism that separates formal assessment (i.e., facial palsy, arm weakness, speech impairment) from procedural support (e.g., step prompts, error correction, and real-time feedback). It guides the assessment process through multi-agent collaboration, dual-channel interaction, state-machine control, and stage-local fallback recovery mechanisms. Stage-specific scoring is delegated to constrained pretrained video assessment modules, while evidence source records are integrated with structured report generation. The user evaluation uses MATES-9, an exploratory scale for measuring user experience in multistep AI-guided tasks. In a simulated prehospital scenario, StrokeGuard improves the MATES-9 total score over a paper FAST-style form by 10.83 points, corresponding to a 23.8% relative increase.

Parliamentary systems pass more bills than presidential systems at baseline, but collapse to near-zero passage under party-system fragmentation. The literature offers three competing micro-explanations: coalition-formation failure, party discipline, and committee gatekeeping. These operate simultaneously in any real legislature, so observational studies struggle to separate their contributions. We present an agent-based model that compares four democratic institutions: pure parliamentary, pure republican/presidential, premier-presidential (France), and president-parliamentary (Russia). Across four scenarios and N=200 seeds per cell we report bootstrap confidence intervals, Morris screening, Sobol variance decomposition, mechanism ablations, and a hung-parliament variant comparison. Three findings emerge. First, government formation failure alone does not halt legislation: when a fragmented parliament reverts to personal voting, parliamentary passage (46.4%) is statistically indistinguishable from the presidential benchmark (44.8%); collapse requires cohesive opposition obstruction, which drives passage to 0.05%. Second, disabling discipline restores fragmented passage to 46.7%, and the rescue magnitude is monotone across the four institutions in a pattern that survives varying the common discipline level. Third, the passage-representation tradeoff is a single spectrum: parliamentary maximises throughput at the cost of representational fidelity; republican maximises fidelity via the presidential veto; semi-presidential variants split the difference.

We study multilevel fair resource allocation with tree-structured hierarchical relations among agents. At each level, the problem can be viewed locally as allocating an agent's bundle to its children, the overall allocation being a trace of this process iterated down to the leaves. Assuming that internal nodes' utilities are the utilitarian welfare of their children, and the leaves have classical additive utilities over items, we first propose multilevel adaptations of usual envy-based fairness notions (e.g., WEF1). We present three adaptations and show that the choice among them is not neutral. We prove that, under identical preferences, the three adapted envy-based notions coincide, and that the Multilevel extension of Weighted Round Robin (Chakraborty et al., 2021) (MWRR) guarantees them. We then show that under general preferences, MWRR may guarantee some notions while failing others. Finally, through experiments, we show that MWRR may still perform well even for adaptations it does not formally guarantee.

Large language model (LLM)-based multi-agent social simulation has demonstrated compelling results, but Agentopia was evaluated with 100 agents over 10 simulated years using Qwen3.5-397B-A17B, leaving the behavior of reduced-scale deployments on consumer hardware unclear. In this paper, we implement and evaluate a reduced-scale Agentopia port on a single NVIDIA RTX 5070 Ti(12 GB VRAM) using Qwen3-8B-AWQ, a 4-bit quantized model. We introduce three structural adaptations for this setting: (1) system-managed layered memory compression, (2) four activity blocks per simulated day, and (3) explicit physical- and mental-health state variables. Across three independent stochastic runs, two runs completed 52 weeks and the third completed 50 weeks before reaching the context limit, totaling 154 system-weeks (770 agent-weeks). No agent died,and no threshold-based health warning was logged; activity records containing at least one NO_RESPONSE field occurred at rates of 10.15-10.29% across runs. A 52-week memory-off run tied L2/L3 artifact production to layered memory; a separate 10-week comparison associated four daily time blocks with 2.72 times more finalized records and lower lexical duplication, but a higher missing-field rate. These comparisons do not support causal behavioral claims. We release validated configurations, derived audits, analysis scripts, aggregate figure data, and our implementation changes in a public fork; raw runs and initial persona data are excluded because their redistribution provenance is not fully resolved.

LLM-based multi-agent trading systems, in which specialized agents collaborate through structured communication to produce trading decisions, are moving rapidly from research prototypes to live deployments that control real assets. The same inter-agent communication that makes them effective also exposes them: a corrupted signal can propagate to the final decision and translate into realized financial loss. Unlike prior attacks that presume privileged access to system internals, we restrict the adversary to what is practically reachable—the source data and prompts agents consume—yielding a low-barrier, and thus democratized threat model instantiated as role-specific adversaries. We present the first systematic empirical study in the financial domain to characterize how an adversarial signal enters a multi-agent trading system and how far it survives toward the decision. Along the role axis, we decompose a widely-used trading pipeline into four functional roles—Analyst, Researcher, Trader, and Risk Manager—and pair each with an attack matched to its interface. Along the structural axis, we evaluate four communication topologies under data- and agent-level attacks, using the Adversarial Signal Preservation Score (APS) as a post-hoc lens on why some designs are more robust than others. We conduct experiments across five assets, two backbones, and two target directions. A central finding is that no architecture is inherently robust. These findings provide insights for the future design of safer and more robust agentic trading systems.

In a deliberative poll, once submissions outnumber what anyone will read, some mechanism chooses which arguments each voter sees, acquiring much of the decision; practice delegates it to opaque learned rankers, so a voter cannot recompute or contest the exposure that shaped their vote. We ask whether it can be a published rule over publicly recomputable evidence with parameters held by the voter, treating legibility as an admissibility condition on usable mechanisms, not an objective traded against accuracy. We formalise a poll over bipolar justification sets, judging a slate by reason coverage, the order it arrives in, and captured endorsement mass; we give seven checkable criteria for a civic recommender and a rule meeting them: a one-hop reversed endorsement flow parameterised by a relation-weight function. An agentic simulator records every slate at every vote, over about 17,000 seed-paired runs. Served slates fall 0.035 short of a label-reading ceiling upper-bounding every selection procedure, opaque ones included: any unconstrained ranker's advantage is bounded and small. On coverage alone, with non-degenerate authoring, the rule is indistinguishable from a random slate, a null due to an order-blind, charity-blind instrument; on the other two it leads at every prefix by a margin widening with adversarial pressure and dominates on mass by a factor of 3.3. Once a realistic fraction of submissions carries no reasons, the coverage margin returns and grows. Label-homogeneous flooding collapses completeness from 0.81 to 0.34 under a flat weight policy, only to 0.44 under author-count normalisation, making the weight function a security control worth 10% of completeness. The choice between ranking arms is a position on a coverage-versus-mass frontier, not a fact, the kind of choice only a legible rule can hand to the person it affects. It maps onto an open-source peer-to-peer platform.

Multi-agent quorums are widely used to authorize high-stakes infrastructure and policy mutations, yet distinct reviewers often share upstream telemetry, documents, or tool backends. When upstream inputs fail, multiple votes collapse onto a single corrupted cause: replication does not imply epistemic redundancy. We introduce Epistemic Fault Domains (EFDs) and the Structural Epistemic Cut \kappa_E, which quantifies the minimum number of modeled root faults whose exposure covers an authorizing coalition relative to an explicit Epistemic Fault Basis. Under closed causal accounting, conservative exposure, and authorization alignment, \kappa_E lower-bounds the number of roots required for semantic compromise (\kappa_S). We prove that arbitrarily large quorums can retain \kappa_E=1, that recognizing shared ancestry never increases credited resilience, and that adding voters at a fixed threshold cannot increase the cut under compatible exposure extensions. Finally, we design the Dependency-Aware Quorum Controller (DAQC) to enforce structural cuts at runtime admission, evaluate its mechanics via analytical derivations and simulations, and provide a frozen 120-task external benchmark suite.

Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate the choice of algorithmic technique to the backbone alone. We present MARS (Multi-Agent Relay of Specialized LLMs), a prompt-only framework in which each agent is a topic specialist—dynamic programming, graphs, strings, geometry, and so on—grounded by retrieval-augmented generation over an algorithm-theory corpus. Given a problem, retrieval selects a small team of relevant specialists; a starter writes an initial C++17 solution, and each subsequent turn runs the candidate against public examples in a sandbox, lets the active specialist keep, repair, or hand off the draft, and forwards a structured packet to the next specialist. A single infrastructure-fixer pass normalizes boilerplate at the end. On the CodeContests test split with Gemma 4, MARS reaches $0.624 \pm 0.006$ pass rate at $2.3$ recorded pipeline stages per task ($+14.4$ percentage points over direct prompting), closing most of the gap to CodeSIM ($0.731$) at $3.3{\times}$ lower wall-clock cost and substantially smaller variance in per-task token spend. The source code is available on GitHub: https://github.com/fckand/mars.

As LLM agents proliferate, built by different parties and with different capabilities and costs, orchestrating them is more like assembling labor across the economy than a computer calling a subroutine. Existing orchestration is typically centralized, with a single planner assigning every task, but this creates a bottleneck as agent pools grow, requires private information (e.g., agents' execution costs), and can easily be manipulated, such that a single inserted preference nearly doubles a favored agent's task share under a centralized LLM allocator. We introduce AgentLance, a repeated labor market in which agents bid on tasks using their private costs and self-maintained strategy notes, an allocator selects winners from bids and public reputation records, and a VCG-style payment rule rewards cost-aware bidding. Complex tasks are handled by hierarchical delegation: winning agents can decompose work and subcontract it through the same mechanism. Across mathematical reasoning, code generation, knowledge-intensive QA, and agentic tasks, AgentLance matches agents to their specializations, shifts work toward cheaper agents as cost sensitivity rises, and consistently outperforms single-model, centralized-orchestration, and market baselines. Diagnosing market failures, including inaccurate cost self-estimation and sub-optimal bidding, then correcting them in controlled experiments yields further gains, charting a path toward more efficient agent economies.

We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline. Agents choose their own research directions, conduct experiments, collaborate and publish papers. These papers accumulate into a shared body of knowledge that later agents can read, cite and extend. We evaluated the Station on 12 mathematical construction problems from the AlphaEvolve study and two additional case studies. Five of the 12 problems yielded results novel relative to the prior literature: a new infinite family of finite field Kakeya sets, new exact 604-point kissing configurations in eleven dimensions, improved bounds for the discretized Kakeya needle and sign uncertainty problems, and a substantially improved lower bound for Erdős's minimum overlap problem. Agents also discovered novel infinite families for Book Ramsey numbers. Their research extended beyond searching for high-scoring constructions: agents developed explanations of their findings and proved theorems outside the assigned tasks. These explanations guided further discoveries and were preserved in the agents' papers, making the underlying insights easier for external researchers to understand and build upon. All presented discoveries are supported by exact constructions or proofs formally verified in Lean. We release the source code, full agent dialogues, papers and verification code, providing a transparent record of how these discoveries emerged.

Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture-of-agents synthesis (Wang et al., 2025), while other work finds that interaction adds cost without improving quality under equal budgets (Tran & Kiela, 2026; Xu et al., 2026; Jarrett et al., 2025), or that independent sampling already captures multi-agent gains (Li et al., 2024). We argue this contradiction partly reflects a missing distinction, because not all multi-agent communication is equal. Different model families find structurally different solutions, but when agents read each other's complete outputs, their proposals converge within one round, erasing the diversity that motivates using multiple models. We call this the interaction tax. We test 11 verifier-scored optimization tasks under matched budgets and find that full-solution interaction is a weak default. Independent proposal generation avoids this collapse. Full-solution interaction mainly makes agents stay close to the first solution they see instead of trying different approaches, and critique helps only if the violated rule is easy for the LLM to find and fix. These results suggest that multi-agent performance depends less on the number of agents than on the information they exchange, and interaction helps only when agents share the right information at the right time.

Recent LLM-agent systems make conflicting design bets: decompose work across many narrow agents, or use one strong tool-using agent. This pilot studies that choice on bounded cross-border VAT determination with reverse charge, where every case has an oracle label and each intermediate decision is independently scoreable. We hold the activity surface fixed (subtasks, tools, I/O schemas, validation checks, orchestrator, base model, and merge policy) and vary only the assignment of subtasks to workers across four orchestrated configurations, from one wide worker to five narrow ones, against S0, a tuned no-orchestrator single agent, with a deterministic rule engine as oracle. The program spans 4,400 runs: a 40-case, five-repeat main sweep, matched-token arms separating prompt-budget from agent-count effects, and three failure-injection arms, all judged against pre-registered falsification criteria. The two intermediate configurations lead on accuracy (0.830, against endpoints at 0.720 and 0.770) but miss the pre-stated bar against the fine endpoint, so the intermediate-optimum hypothesis remains unsupported at pilot scale. The single agent does not Pareto-dominate the orchestrated set. The matched-token criterion fires: the budget-matched single agent lands 6.5 points below the leader, but the interval includes zero, so any advantage is consistent with a prompt-budget explanation. Under injection, availability faults are absorbed at every granularity, with wide-scope restart over-recovering its baseline by +0.160, while one schema-conforming hallucinated record degrades every configuration and inverts the ordering, hitting fragmented configurations hardest. The contribution is a bounded, preregistered pilot heuristic for right-sizing decomposition (place one partition boundary at the dependency-layer midpoint), released with oracle, dataset, harness, raw traces, and analysis pipeline.

We present the first LLM-powered multi-agent system for autonomous fault management across millions of optical links in production AIDCs. Refined via SFT and continuous memory evolution, it achieves 97.7% F1 and over 60% fault-incident reduction, outperforming SOTA LLMs on a ten-week field data evaluation.

LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure. Although external harnesses can substantially improve robustness, harness design remains a manual and expensive process that requires searching over a large space of prompts, tool configurations, and control logic. We propose AutoSaddler, an automatic harness optimization framework that formulates harness improvement as an offline learning problem and iteratively updates the harness using failure signals from mini-batches. AutoSaddler combines failure-trace diagnosis, structured patch generation that treats the harness as code, and validation-based update selection. Experiments on GAIA2, SWE-Bench Pro, and Terminal-Bench 2.0 show that AutoSaddler substantially improves agent performance over the corresponding base harnesses, achieving gains of 9.0, 9.6, and 10.0 percentage points, respectively. Ablation studies further suggest that effective harness optimization benefits from three ingredients: deep debugging rather than shallow reflection, targeted modifications rather than unconstrained editing, and generalization-aware selection rather than trajectory-specific repair. Together, these results suggest that automatic harness optimization is a promising path toward more performant and reliable agent systems.

Societies of interacting language-model agents offer a controllable and repeatable way to study collective behaviour at scales that would be difficult to test with people. Their scientific value, however, depends on whether a social mechanism that works in a small group still operates when thousands of agents interact, and testing this directly requires costly large-scale runs. Here we introduce an audit that predicts a mechanism's fate as a population grows. It asks how often the mechanism can act, whether agents use the information it supplies, and whether the measurement itself creates apparent scale effects. Controlled experiments show that a single structural term can decide whether reciprocity, consensus or punishment survives scaling. For gossip, the population at which the mechanism fails is set by the reach and lifetime of its messages. In language-model societies, agents respond not only to social information but to how it is expressed: counts and percentages led to different scale behaviour. Predictions made before execution held on third-party code and a second model family, while a failed prediction exposed the boundary of the finding. The audit provides a prospective way to decide which social mechanisms can be interpreted across population scales.

Large language models (LLMs) and vision-language models (VLMs) are expanding the range of behaviors that can be represented in agent-based simulations, but many contemporary platforms are difficult to study, modify, or run on ordinary computers. We present two intentionally minimal simulation foundations for education and rapid prototyping. SD-AgentFoundry-2D provides a two-dimensional multi-agent environment in which locally hosted LLM agents move, communicate, respond to place occupancy, and encounter spatially localized fire events. SD-AgentFoundry-3D provides a three-dimensional digital-twin environment in which a locally hosted VLM receives first-person images and produces natural-language movement instructions. Both codebases are designed to run locally on macOS, Windows, and Linux and are deliberately left open to modification rather than developed as finished applications. Together, they offer accessible starting points for learning about generative social simulation and for building domain-specific extensions.

When can an agent failure be caught? A weak audit score alone cannot identify whether the record or the method is limiting. CatchBench therefore puts one auditor's question to three information states: the declared configuration before a run (PRE), a growing prefix of its trace (LIVE), and the finished trace (POST). Prior benchmarks fix one of these states or vary the telemetry; to our knowledge none scores all three under one task-method interface. Each state admits different questions, so seven task contracts carry their own labels and metrics rather than one leaderboard. Four are evidential; three are Gold-derived mechanism diagnostics. The release scores 72 entrants, from rule scanners and structural models to eleven LLM judges across nine model families (GPT, Claude, Gemini, Gemma, Llama, Qwen, DeepSeek, Mistral, Nova), over 1187 declared configurations and 1162 recorded runs. Every recorded comparison is published as a measured difference with its interval, uncorrected, and no board declares a winner it cannot show. The three sharpest results cut against our own data. One rule reads declaration order alone and reaches a perfect F1 on one of six configuration sources, so a score there measures how the corpus was built. Our admissibility bar then rejected one injected substrate and withheld evidential status from the other. A published structural gain also turns on which size reference it is measured against. A benchmark number is therefore not interpretable until the process behind its labels is published and tested for the shortcut it may leave. We report all three, and regenerate every ordering from released predictions with no model call.

Developing innovative system architectures increasingly relies on advanced modeling and optimization techniques to frame the architecting process and define the corresponding computational problems. For complex System-of-Systems (SoS), high-fidelity multiphysics and multidisciplinary simulations are essential for capturing detailed behaviors. However, their computational expense and the risk of evaluation failures make direct optimization challenging. To overcome these limitations, surrogate-based approaches, like Bayesian optimization, have emerged as effective tools for managing expensive, black-box simulation tasks. This work introduces a hierarchical Bayesian optimization framework that leverages Gaussian process meta-modeling to handle discrete architectural choices, conditional dependencies, and heterogeneous design variables inherent to SoS problems. Results show that the hierarchical formulation improves search efficiency and robustness compared to conventional surrogate-based methods, enabling the exploration of large and structurally diverse design spaces with limited simulation budgets. We apply the approach to an aircraft-based multi-agent system for wildfire suppression, a use case developed within the EU-funded COLOSSUS project that illustrates how SoS principles can coordinate heterogeneous aerial platforms with complementary roles, supporting both sustainable mobility and emergency response missions. Our framework provides a scalable methodology for SoS architecting and model exploration, offering transferable insights for applications in aviation, sustainable mobility, and resilience-oriented system design. By combining hierarchical representations with surrogate-based optimization, this work is among the first practical demonstrations of hierarchical Bayesian optimization applied to real-world SoS problems, advancing both methodology and practice.

Clinical diagnosis relies on consistent multimodal data collected from the same patient throughout the disease course, yet such data are difficult to acquire at scale because of collection costs, missing modalities, fragmented systems, and longitudinal follow-ups. Existing synthetic-data approaches largely focus on individual modalities or vision-language dual modalities at report-level generation. Little work has been done to construct synthetic data with consistent patient backgrounds, coherent disease trajectories, and interrelated modality-specific evidence at a complete clinical case level. We introduce CaseWeaver, a multi-agent framework built around a timeline-anchored Latent Clinical Case Graph (LCCG). The LCCG organizes patient context, latent disease states, clinical events, and expected observations in a shared patient-level representation. Modality-agents use scoped observation subgraphs and clinical protocols to generate evidence including clinical records, laboratory results, physiological signals, and medical images. We evaluate clinical inferability using a calibrated AgentClinic protocol and case diversity using Virtual Case Diversity (VCD) score. CaseWeaver outperformed general-model and agentic-workflow baselines on both metrics, producing more diverse and coherent multimodal virtual clinical cases.

Agentic AI frameworks interpret open-ended task goals and decompose them into multi-step plans. Richer information about embodiment-specific capabilities, physical preconditions, and cross-robot coordination improves grounding, but does not eliminate infeasible, mistimed, or unsafe physical actions. Physical robot crews therefore require an explicit architectural interface between semantic planning and execution, where every planned action is verified against robot capabilities, system state, and workflow constraints before actuation. This paper introduces Physical Agentic AI, a framework for skill-grounded robot agent orchestration, in which each robot exposes a typed library of executable skills while a foundation model planner decomposes a task into phases and assigns each phase to a robot-skill pair. A Robot Orchestration layer exposes the skill library, robot state, named locations, and workflow contracts to a non-actuating Mission Planner, while a deterministic Robot Orchestrator validates and authorizes one skill at a time. We evaluate on a drone-UGV search-and-dispatch mission, where every mission in every condition is executed live in Gazebo, and on a humanoid-quadruped transportation task using hardware-equivalent skill interfaces plus two physical trials on a Unitree G1 and Go2. Varying planner knowledge and runtime enforcement independently, we find that retrieval raises skill grounding from 51% to 96% yet leaves informed planners dispatching 23-29% of faulted steps. Per-dispatch enforcement reduces false dispatch to 0% with no false blocks, and a held-plan ablation confirms that the gate, not plan variation, is responsible. Live execution makes the difference physical: without enforcement all eight injected faults crossed the orchestration boundary and six produced robot motion; with enforcement all eight were refused before motion.

Powder X-ray diffraction (PXRD) is the routine probe of crystalline matter, yet its analysis is the rate-limiting step as laboratories automate acquisition. Deep-learning analyzers excel on simulated patterns and degrade on measured ones. This simulation-to-real gap is structural, not additive: synthetic denoising gives no measurable lift on real spectra, whereas correcting a small peak-position drift more than doubles median retrieval correlation. Real-spectrum fine-tuning, peak-aligned reranking, and recalibration narrow what remains and restore the coverage synthetic anchors lose. Xtalyst integrates these in an agent-orchestrated system spanning phase identification, refinement, and calibrated property prediction. On a frozen held-out partition (n=534) each module measured on both splits reproduces its development finding – including the synthetic-anchor under-coverage, whose magnitude differs between the two pools – while held-out refinement converges and preserves symmetry without reaching profile-quality fits, and on a diffractometer its wet-dry recommend-rescan-reanalyze loop flips a blinded silicon standard to a gated PASS and changes which minor phase is resolved on a multi-metal alloy.

Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding how a system responds to intervention, which in practice depends on controlled experimentation. In this work, we propose a multi-agent framework that enables LLM agents to conduct controlled experiments with scientific simulation models for pharmaceutical process design. Given a user query and a baseline configuration, the system constructs a structured task representation, designs experiments, executes comparative simulation, interprets the resulting outcomes, and synthesizes evidence-based recommendations for process parameter optimization. By coupling language models with high-fidelity simulation models in an interactive agent framework, the proposed system supports reasoning through intervention, comparison, and observation. As a result, it produces more specific and actionable outputs than language-only reasoning. In an industrial application setting, this advantage is reflected in higher output specificity as well as improved user-rated correctness and helpfulness. Ablation studies and visualized case analyses further demonstrate the effectiveness and practical utility of simulation-integrated experimental reasoning.

LLM-based multi-agent systems (MAS) solve complex tasks through communication among role-specialized agents. However, inter-agent dependencies introduce reliability risks beyond isolated agent failures. For instance, errors in intermediate messages could be inherited and amplified by downstream agents. Existing uncertainty quantification (UQ) methods mainly target isolated responses or single-agent reasoning, and therefore fail to capture uncertainty propagation in MAS. To this end, we propose PropUQ-MAS, an error propagation-aware UQ framework that represents MAS execution as a communication-structured graph and estimates each step's reliability by combining local uncertainty with uncertainty inherited from upstream messages. Extensive experiments demonstrate that PropUQ-MAS consistently improves UQ in MAS, with average relative gains of +6.10% in AUROC and +47.58% in PRR.