Papers

In a decentralized multi-robot team under partial observability, the fact that decides a robot's next action is often visible only to a teammate. Existing decentralized methods communicate kinematic information, such as position or planned trajectory, which cannot convey what the teammate perceives. Learned communication in multi-agent reinforcement learning (MARL) can carry perceptual content, but the resulting messages are task-coupled and opaque. We propose Latent Telepathy. Each robot broadcasts the perceptual latent vector it already computes for its own use, the output of an encoder trained with a self-supervised joint-embedding predictive objective, frozen, and shared across the team. A teammate learns to act on it from task reward alone. Because the encoder already runs for perception, the message costs no additional computation and a single compact vector of bandwidth. Because the encoder is frozen before any policy is trained, the message means the same thing to every robot, and the receiving robot is never told what it means. We evaluate Latent Telepathy with a content-controlled protocol in which bandwidth, latency, topology and receiver are held fixed and only the message content varies. Broadcasting the latent lets a navigator avoid an occluded hazard in 99.7% of episodes, matching a noiseless hand-designed message. Position and trajectory messages remain at chance, and the raw camera image, 186 times wider, is less reliable than the compressed latent. The result holds from a discrete gridworld to rendered pixels under continuous velocity control, and the encoder decodes the hazard from a physical robot's camera in 102 of 102 live decisions. We also identify a requirement for porting MARL communication results to continuous control, that the decision a message informs must remain reachable by exploration, and show how to restore it.

Large language models are increasingly used as interacting agents, but it remains unclear how robust their coordination is when public communication is unreliable. We study this question in iterated $N$-player Stag Hunt games played by homogeneous LLM groups under controlled programmatic action inversion, which changes both the public transcript and the actions used for execution. Across an experimental grid spanning group sizes, coordination thresholds, corruption levels, and seven LLMs, we observe three main patterns. First, honest agents' pre-flip Stag choices decline as corruption increases, but the sharp fall in public success is primarily mechanical. In the focal $N=5,M=3$ setting, pre-flip success remains 78% at 80% corruption, while public success falls to 12%. Second, honest choices are associated with the public history available at decision time, particularly under high corruption. Third, three threshold-style public-report benchmarks yield similar action-match rates to the LLM agents, showing substantial descriptive agreement between LLM decisions and these benchmarks. Overall, our results show that original choices, public actions, and executed outcomes must be separated when evaluating multi-agent robustness, as corrupted communication can severely and predictably degrade mutually beneficial cooperation.

Large scale warehouse automation relies on efficient multi agent path finding (MAPF) to coordinate thousands of robots in structured environments. Existing MAPF algorithms primarily improve conflict resolution while representing warehouses as generic navigation graphs, overlooking their inherent geometric structure and traffic patterns. This paper presents TRACS (Traffic aware Routing and Aisle Coordination System), a geometry aware planning framework that exploits warehouse layout to simplify planning rather than introducing another conflict-resolution algorithm. TRACS constructs a directed routing graph with alternating one way aisles that eliminates head on and edge swap conflicts by design, decoupling spatial routing from temporal traffic coordination. Independent hybrid graph grid routing is combined with lightweight edge based scheduling to avoid joint space time search while ensuring collision free execution. Experimental evaluation on warehouse benchmarks against representative priority based, iterative repair, and search based MAPF planners shows that TRACS consistently achieves a 100% empirical success rate while substantially improving planning scalability. On fixed scene benchmarks with up to 1000 robots, TRACS reduces planning time by up to 14.7X while maintaining competitive makespan, lower flowtime, and near optimal path quality. Under a fixed 10 minute planning budget, TRACS routes up to 5120 robots, roughly twice the largest fleet reached by the strongest baselines, while sustaining a 100% success rate, demonstrating the effectiveness of exploiting warehouse geometry for scalable robotic warehouse systems.

Coding assistants raise task performance, but learners plan and monitor less. Giving less away, the usual fix, conflates two things: how much work a system carries (cognitive load) and what the learner must decide before help arrives (metacognitive demand). Our principle, preserved metacognitive demand, holds the second constant and lets the first vary. CoMeT implements it: support rises when a learner fails at a decision point and fades on take-up. Within subjects, 131 adult learners used CoMeT, an unrestricted assistant and a question-only tutor on three Python tasks. CoMeT matched the question-only tutor's demand, delivered artifacts twice as often as the assistant, and frustrated learners less than the question-only tutor, with delegation and load unchanged. Learners often did not answer. Fading held when their turn addressed the decision under support, and CoMeT surrendered the full answer in one session in sixteen, against one in six for the question-only tutor.

Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic workflows: subtask complexity varies widely within a single trajectory. A planning step may require frontier-class reasoning while a subsequent formatting step needs only a 7B model. We formalize step-level model routing as a sequential assignment problem over agent trajectories and propose AgentRouter, a lightweight classifier (12M parameters, <5ms overhead per step on an A100 GPU) that maps each trajectory step to one of four model tiers using five features extractable at routing time. Trained on 50,000 annotated agent trajectory steps spanning planning, coding, research, and data analysis tasks, AgentRouter achieves 72% cost reduction relative to frontier-only baselines, retaining 97.3% of frontier-only quality (less than 3% degradation in end-to-end task completion); per-step routing accuracy reaches 91% on minimal-complexity steps and 85% on efficient-tier steps, with 76-82% on the harder mid-range and frontier tiers. On the same benchmarks, RouteLLM and FrugalGPT (applied per-step) achieve only 31% and 44% cost reduction respectively, because their single-turn training signal misses trajectory-level quality dependencies.

Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent systems amplify this threat through three mechanisms absent from single-model settings: inter-agent message passing creates injection channels invisible to perimeter defenses, shared tool access enables privilege escalation across agent boundaries, and trust propagation allows a compromised agent to influence upstream orchestrators. We construct a threat model enumerating 14 attack vectors across four categories: direct injection via user input (3 vectors), indirect injection via tool outputs (4 vectors), inter-agent injection via message passing (4 vectors), and cascading injection through orchestrator manipulation (3 vectors). Testing all 14 vectors against a 6-agent production-representative system, we find that 67% of agents are vulnerable to at least one scope violation even with system-prompt-level guardrails, and indirect injection via tool outputs succeeds in 43% of attempts. Four architectural defenses reduce overall injection success from 31.2% to 4.2%: message signing with provenance tracking (inter-agent injection down 91%), input/output sanitization at agent boundaries (indirect injection down 78%), privilege-scoped tool access per agent role (privilege escalation eliminated entirely), and anomaly detection on inter-agent communication patterns (84% of cascading attempts caught).

Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subtasks to other agents, and pay for metered resources. Deploying such agents safely requires five capabilities that today live in separate systems: persistent identity, scoped delegation, peer trust, discovery, and payment. Existing approaches root these in centralized authorities or cover only subsets, so authority, trust, and payment fracture exactly where autonomy needs continuity: when a key rotates or a delegation must be revoked. We present NostrAgent, a decentralized architecture that unifies all five over Nostr relays using three custom event kinds: Kind 38100 identity declarations authenticated by BIP340 Schnorr signatures with pre-rotation commitments, Kind 38101 scoped delegation chains whose every hop verifiably narrows granted capabilities, and Kind 38102 peer attestations forming a Sybil-deterrent trust graph, with Lightning HTTP 402 (L402) binding payment to agent identity. Identity remains operator-sovereign without any registration authority; relays are substitutable transport rather than a trust root; and every authorization decision is replayable offline from signed events. We evaluate a Python prototype with a mixed-method design: ATAM quality analysis with a two-round mini-Delphi panel, STRIDE threat modeling across three trust boundaries, eleven benchmarks with non-parametric statistics, and 19 failure modes. Results show sub-millisecond offline verification, linear delegation-chain scaling, and Lightning-settled L402 at 157 ms median on regtest. 17 of 19 failure modes pass empirically, one is bounded analytically, and one is disclosed as an architectural limitation. NostrAgent demonstrates an auditable prototype substrate for trustworthy agentic systems without centralized trust roots.

We study personalized federated reinforcement learning, in which $n$ agents, each acting in its own Markov decision process, collaborate through a server to learn a shared MAML-style policy initialization that becomes effective for an individual agent once that agent adapts it with a single local policy-gradient step. We propose Per-FedAvg-PG, in which agents take $\tau$ local stochastic meta-policy-gradient steps between communication rounds, and prove that it reaches an $\varepsilon$-approximate first-order stationary point of the personalized objective in $K=\mathcal O(\varepsilon^{-3/2})$ rounds with $\tau=\Theta(\varepsilon^{-1/2})$ local steps. The analysis rests on a structural feature of the reinforcement learning setting: under standard policy-class regularity, the per-agent objectives have uniformly bounded gradients and Hessians with explicit constants, so the bounded-gradient and bounded-heterogeneity conditions imposed by the supervised theory hold automatically and no separate heterogeneity assumption is needed. The exact meta-gradient requires the inner-loop policy Hessian, which our experiments identify as the practical bottleneck. We therefore analyze the Hessian-free variant, bound its bias, and exhibit fixed points at which the meta-gradient is nonzero and of order $\alpha$, showing that the resulting stationarity floor is a property of the method rather than of the bound. Experiments on tabular and neural navigation confirm the predicted behavior and show transfer to unseen agents at an order of magnitude lower sample cost than independent training. Together these results identify the adaptation step size as a tunable personalization knob and the curvature estimate as the quantity that governs whether exact meta-gradients are affordable.

Efficient coordination under limited communication remains a key challenge in decentralized multi-robot exploration. While centralized approaches benefit from global information sharing, they are often impractical in large-scale or communication-constrained environments. Existing Monte Carlo Tree Search (MCTS)-based approaches, such as Decentralized Monte Carlo Exploration (DMCE), enable decentralized planning by taking peer intent into account. This peer intent is obtained by communicating sequences of planned waypoints with robots within direct communication range. In this work, we extend this idea by introducing Probabilistic Peer Intent (PPI), which converts peer trajectories into a continuous spatial representation of predicted intent and incorporates it into local MCTS action evaluation. We additionally study the effects of sharing peer intent beyond direct communication range by propagating plans over multiple hops. Experiments across multiple simulated environments and team sizes show that PPI and Multi-hop propagation can each improve decentralized exploration, with their relative benefits depending on environment structure and team size. We also demonstrate the real-world deployment of our method on three robots operating in different environment types.

Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and divisions of labor cannot be specified in advance; teams must learn from experience how to organize reasoning as it unfolds. Human teams routinely adapt this way, while existing AI agent teams rely on fixed protocols, explicit task decomposition, or routing. We introduce Self-Organizing Agent Teams (SAT), fixed teams of AI agents that learn reusable strategies from prior collaborations to organize roles, conversational phases, participation, and information flow. These strategies enable what we call collaborative computation: agents exchange, challenge, repair, and synthesize partial reasoning into solutions no member produced independently. In two independent settings, we learn teamwork strategies that transfer unchanged to unseen benchmarks, using only 15 mathematics and 25 graduate-level knowledge problems. Across five mathematics and physics benchmarks, self-organizing teams average 66.7% accuracy, versus 48.8% for their strongest member, 58.7% for compute-matched inference by that agent, and 59.0% for a perfect router over members' independent answers; on AIME 2026, they exceed this router by 13.4 points. Because gains vary across benchmarks, we ask when self-organizing collaboration helps. Across eight benchmarks, demonstrability (the organizational-psychology construct of whether a team can distinguish correct from incorrect reasoning) strongly tracks improvement over the strongest member (Spearman $\rho=0.90$, $p=0.005$): teams benefit most when correct reasoning can be recognized once it appears. More broadly, these results suggest that organization itself can become an agent capability: agent teams can learn how to reason together and produce solutions their members could not reach independently.

Density-Driven Optimal Control (D2OC) provides an effective framework for steering multi-agent systems toward prescribed spatial distributions. However, existing D2OC formulations are primarily developed for Euclidean domains and do not directly account for intrinsic manifold geometry. This paper extends D2OC to second-order multi-agent systems evolving on Riemannian manifolds. The proposed Riemannian D2OC (R-D2OC) constructs a local distribution objective in the tangent space of each agent through logarithmic maps and uses its weighted center as the reference for a finite-horizon LQR. The resulting control is executed on the manifold through intrinsic second-order dynamics and parallel transport within a receding-horizon scheme. We establish local curvature-dependent bounds that quantify the approximation introduced by the tangent-space reduction and characterize the resulting target bias. Furthermore, we derive a conditional discrete-descent result showing that the closed-loop objective decreases when a local velocity-alignment condition is satisfied. Numerical simulations on a 3D ellipsoidal manifold demonstrate distribution-level control and empirically support the proposed approximation and descent results.

Density-Driven Optimal Control (D2OC) provides a principled approach to distributing multi-robot teams over non-uniform spatial distributions. Applying D2OC to nonholonomic robots, however, creates a gap between safety constraints imposed on a reference motion and the physical inputs that determine the actual robot motion. We address this issue by enforcing the safety constraint directly on the robot's physical inputs while preserving the density-driven coverage objective. The proposed framework combines D2OC with a control barrier function safety filter through a feedback-linearizing look-ahead point, allowing safety and actuator limits to be considered together during control. We further derive a safety margin that accounts for the look-ahead geometry, robot footprint, and motion during each control interval. Simulation results show that the proposed method maintains the required physical separation while achieving coverage performance comparable to a conventional reference-tracking approach, which can satisfy safety on the reference motion yet violate the corresponding physical clearance. Experiments on multiple nonholonomic robots in the Robotarium further demonstrate safe execution while driving the robots toward the desired spatial distribution. These results show that enforcing safety directly on the physical inputs can eliminate the mismatch between safety certification and physical robot motion in density-driven multi-robot coverage.

LLM agents are beginning to write the rules they live under: policies, contracts and code that other agents review and approve. What happens when those rules must decide who is sacrificed from a group? We built GovSim-SelfGovern, a commons in which agents legislate in executable Python, test each law in a sandbox, vote on it, and live with the result. When the fishery is abundant, self-rule helps, raising the chance that the community survives without anyone starving from 52.5% to 75.0%. When it cannot feed everyone though, adding governance is not enough to save the commons. We trace much of this to the vote: agents readily draft laws that remove members, but then frequently vote them down, thereby dooming the commons. In a controlled replay, the same exile law passes 8% of the time when the sandbox preview names its victim at once and 55% when the removal is deferred until a future crisis. Showing voters the full source code does not close the gap, though most describe the removal in their own words. Nor is sacrifice a fixed trait. A single sentence of framing can swing self-removal from 2.5% to 91%, and due process deters agents more than considering the potential death of a peer. In contrast, give the community a treasury and the question of who must go almost disappears. Our work shows that what our collectives legislate is decided more by the form in which a choice is put to them as compared to their ethical beliefs.

Training agents with reinforcement learning requires a gym, comprising a task, an executable environment in which the task can be attempted, and a verifier that reliably distinguishes success from failure. Constructing such gyms remains manual, expensive, and static. Task sets saturate as models improve and are increasingly exposed to contamination. Synthetic generation offers scale, but single-pass synthesis produces tasks whose difficulty is largely cosmetic. Models comparable in capability solve them despite convoluted phrasing, and correctness must be adjudicated post-hoc by unreliable LLM judges. We present AutoGym, a framework that generates complete gyms (tasks, executable environments, and verifiers) from a minimal domain seed or prior model trajectories. AutoGym introduces three mechanisms. (1) Blueprint-first generation specifies the valid solution space, environment requirements, and verification criteria before the environment is materialized, making solvability a construction prerequisite rather than a property verified after the fact. (2) Explicit generation parameters control task topology, interaction depth, capability axes, question obfuscation, and distractor composition, enabling fine-grained difficulty steering. (3) Active curriculum synthesis uses performance-informed calibration to adjust the distribution over these parameters as model capabilities evolve. Across productivity and temporal-reasoning settings, AutoGym generates gyms spanning the capability spectrum, including instances that challenge frontier models.

LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified, and collective outcomes inherit the model's training prior. We introduce Bayesian Chronicle Agents (BCA), a minimal belief layer separating what an agent believes from how it speaks. Each stance is a probability, updated by one Bayesian step per utterance heard. A single prior-strength parameter $\kappa$ encodes stubbornness, modeled after its role in Friedkin–Johnsen (FJ) opinion dynamics. We then sweep this parameter to yield three canonical regimes of opinion dynamics on demand (consensus, persistent disagreement, committed-minority influence), with persistent disagreement matching the FJ closed-form fixed points at $R^2\!=\!0.93$–$0.99$. We further show that prescribed $\kappa$ remains recoverable after the language round-trip, with perfect rank-order recovery across all four models. Explicit belief also makes simulation auditable: the layer surfaces systematic per-model stance biases that end-to-end simulation would silently absorb.

In recent years, quantum game theory has gained significant attention as a framework for studying decision-making in multi-agent systems using quantum principles. However, computing equilibrium strategies is challenging because the dimension of the joint Hilbert space grows as the product of the players' local dimensions. In this paper, we consider an extended Gutoski-Watrous (EGW) game in which each player's quantum strategy is represented by a local density matrix. We derive tensor-contraction expressions for the payoff functions and their gradients, thereby avoiding the explicit construction of the full joint density matrix and its computationally expensive multiplication by the payoff operators. Building on the resulting effective Hamiltonians, we propose the Matrix Exponential Fixed-Point Iteration with Annealing (MEFPIA) algorithm to search for equilibrium points in EGW games. We compare MEFPIA with the Matrix Multiplicative Weights Update (MMWU) algorithm in terms of convergence. For the tested instances and parameter settings, both algorithms approach the same strategy profiles and payoffs, while MEFPIA achieves lower relative error in fewer iterations. These results indicate that MEFPIA is a promising numerical method for equilibrium search in multi-agent quantum games. Our findings provide important insights into the quantum game theory's potential for addressing complex decision-making processes, as well as opening up new paths for future research and exploration in multi-agent quantum systems.

Renewable energy communities (RECs) coordinate buildings, photovoltaic generation, batteries, electric vehicles and flexible loads. Controller studies often simplify changing participation, equipment availability, service deadlines and data quality, so lower cost or peak demand can conceal missed services or infeasible power requests. This paper presents CityLearn v3, a configurable simulation and evaluation framework for REC control studies under these conditions. It represents changing members and assets, flexible-load deadlines, demand-response requests, local energy sharing, and data or equipment failures within one simulation environment. Building and phase power limits constrain controllable requests, while a declared timestep preserves consistent power-to-energy accounting. The framework records controller inputs and distinguishes requested actions from those applied to the simulated equipment. Reference controllers, service- and constraint-aware performance indicators, and trajectory exports support comparisons within and across communities. Software checks and application examples examine service delivery, electrical constraints, settlement and changing scenarios; a synthetic high-frequency trace replay illustrates how aggregation can conceal short peaks without changing annual energy. Together, these records allow aggregate performance to be interpreted alongside service failures, action reductions and participant-level outcomes.

Organizations deploying agentic artificial intelligence must determine more than whether a model is trustworthy; they must establish what to validate, control, and observe for a use case to deliver its intended outcome while meeting applicable obligations. This paper proposes AI-GRACE (Agentic Intelligence-Governance, Risk, Assurance, Controls, and Evidence) as a use-case operationalization framework connecting organizational governance with technical implementation. The proposal draws on professional observations and a purposive synthesis of standards and literature, using design science to frame the method contribution and situational method engineering to guide contextual tailoring and reuse. The framework establishes objectives and obligations and then assesses risks in seven proposed domains, including mission and value realization. It derives requirements for assurance before deployment, runtime controls, and evidence, which guide capability qualification, gap assessment, and a logical architecture. An Agent Operating Envelope specifies permitted actions and escalation conditions, while Risk-Aligned Independence Levels (RAIL) summarize the authorized independence. A fictional retail banking application illustrates the method. The contribution is a traceable basis for deciding what an organization must implement, what it already supports, and what remains unresolved. Empirical evaluation must establish whether it improves deployment decisions, efficiency, and reuse.

Human approval is often treated as the last security boundary before an agent executes a consequential operation. That boundary is only meaningful if the operation presented for review is the operation later authorized or released. We call failures of this binding Loopjacking: a human approves what they understand as operation A, while the implementation uses that decision for a materially different operation B. We distinguish two variants. In a representation-based attack, B is already encoded but omitted or misrepresented at approval time; in a post-approval state-substitution attack, the human sees the correct A and mutable workflow state later replaces it with B. We evaluate a purposive set of released agent products. We reproduce post-approval substitution in seven tested Agno AgentOS releases ending at 3.0.9 and in 12 tested versions of a conditional in-memory LangGraph Agent Server composition ending at 0.14.0. We reproduce representation mismatch in OpenClaw 2026.2.23 and its rejection in 2026.2.24. OpenAI Agents SDK 0.22.0 and 0.22.2 provide a negative control: serialized continuation preserves exact per-call binding and rejects mutated B. These results do not estimate ecosystem prevalence. They show that complete canonical approval rendering and exact use-time comparison, or preventing unauthorized pending-state mutation, block the tested attacks while preserving legitimate execution. We separate this contribution from established work on misleading dialogs, session smuggling, action binding, and authorization continuity.

In this paper, we tackle the problem of jointly estimating the system states and partially unknown dynamics within distributed sensor-equipped networks, particularly in scenarios where only partial state observations are available. To address this issue, we propose an observer-based dynamic cooperative learning framework incorporating online distributed Gaussian Process (GP) regression, which enables accurate estimation despite incomplete in measurements and deficient GP models. In addition, a novel data collection strategy is introduced, with theoretical conditions ensuring feasible data acquisition. Moreover, we also derive an error upper bound encompassing state estimation and model estimation, leveraging the deterministic error bounds of GPs. Empirical simulations demonstrate the superiority of our approach compared to existing distributed GP-based methods.

Connected-vehicle safety evaluations rely on coupled traffic and network simulations, but standard channel models ignore radio resource competition in 5G NR sidelink Mode-2, reporting unrealistically high message delivery in dense traffic. This study introduces resource-competition losses without requiring full protocol reimplementation. We labeled 10.5 million reception outcomes from ns-3 5G-LENA traces (calibrated on 3GPP scenarios and driven by SUMO trajectories) to fit NS3Learn - a closed-form model capturing half-duplex loss, scheduling collisions, receiver capture, and decoding. Evaluation spanned two signalized urban networks, six penetration levels (1-100%), and five random seeds per condition. NS3Learn achieved a mean absolute deviation of 0.06 in per-instant delivery compared to ns-3 5G-LENA, outperforming alternative models (0.44 and 0.55 deviation). Fitted parameters transferred to a distinct intersection with only 20% additional error. Crucially, using realistic communication models reversed simulated traffic speed trends and more than doubled predicted hard-braking events. The framework transfers reception realism between simulators via model distillation instead of full reimplementation. Every stage maps directly to an explicit physical mechanism. Researchers and transportation agencies can maintain existing simulation pipelines while accurately accounting for dense-traffic packet loss and denial-of-service impacts. Adapting to new radio configurations requires only offline refitting rather than code modification.

The goal-oriented communication paradigm is poised to enable novel real-time applications by easing the burden on communication networks while still delivering task-relevant information. However, efforts so far have focused on the encoding problem, while the design of medium access schemes is still in the early stages of development, especially when connectivity is to be provided to a massive number of devices, e.g., for remote monitoring. In this respect, existing goal-oriented approaches are often centralized or based on simplified underlying mechanisms, requiring unrealistic assumptions. In this work, we present the Goal-oriented Irregular Repetition Slotted ALOHA (GO-IRSA) scheme, which combines modern random access techniques with belief-based policies. GO-IRSA does not impose significant computing loads on the sensors or require frequent feedback, and it can reduce the average and worst-case error of the estimate of a distributed Wiener process by over 30% with respect to the optimal centralized solution in a network with thousands of sensors, and is robust to imperfect interference cancellation and inaccurate process knowledge.

Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We replayed 100 held-out human Wason groups with matched large language model (LLM) agent groups, seeding one belief-anchored agent per participant's pre-discussion answer and scoring agents and people with the same code. Across human scoring definitions, estimates ranged from 24.0% to 57.0%; about one fifth of participants never posted, whereas agents almost always did. Agent groups remained more consensual in two post-unblinding sensitivity analyses: the submit-based comparison (n = 98) yielded gaps of 34.0 and 43.9 percentage points for chat and reasoning modes, and the participation-matched comparison (n = 45) yielded gaps of 34.1 and 44.4 points. These complementary routes reduced different measurement asymmetries yet converged within 0.5 percentage points. The gap persisted without early stopping and under a reparameterization removing the memorizable answer; reasoning-mode groups then agreed nearly unanimously, mostly on incorrect answers. Simulated consensus did not track collective accuracy, and belief-anchored agent groups were biased estimators of the human group-outcome distribution in this setting. These analyses provide a scoring-explicit basis for assessing simulated-group estimates of human deliberative outcomes.

The growing complexity of multi-domain operational environments (land, aerospace, naval, cyber, and electromagnetic spectrum) has increased the volume and velocity of data reaching command-and-control (C2) centers, straining the observe-orient-decide-act (OODA) decision cycle. Artificial Intelligence (AI) systems currently employed in defense are, in general, reactive and isolated tools that still rely heavily on human operators to integrate information, assess scenarios, and formulate courses of action. This paper proposes a conceptual Agentic AI architecture for AI systems that can plan, access data sources, execute tools, and act autonomously and audibly, aimed at supporting decision-making across the three Brazilian Armed Forces (Navy, Army, and Air Force). Four application fronts are discussed (decision support, situational analysis, feasibility studies, and countermeasure suggestion), as well as the data and sensor access requirements and the security and permission safeguards necessary for responsible employment across administrative, strategic, operational, and tactical contexts.

The widespread adoption of LLMs has led to escalating content compliance risks. Prior works have contributed to addressing these risks in the English context, downplaying the complexity of Chinese language content. This paper follows China's current AI-Generated content compliance requirements and provides evaluation results on 20 notable LLMs, offering insight into China's regulatory landscape. We design a novel framework to assess the compliance and refusal rates with 2303 questions spanning six distinct dimensions, including 203 self-constructed constitutional questions. The framework employs several judges to generate verdicts independently based on their hierarchical alignment memory. Our findings show that international models also exhibit high levels of compliance despite the use of standard Chinese questions, and the main differences may stem from dimensions closely related to ideological alignment. We establish a regulatory benchmark that enables the global AI community to evaluate both Chinese and non-Chinese LLMs under a unified set of legally grounded compliance requirements.

Clinical coding agents repeatedly encounter the same failure modes, including unsupported codes, missed documented conditions, specificity errors, and procedure-coding convention mismatches. We introduce Learn-Then-Act, an inference-time adaptation framework that converts errors from a small labeled LEARN batch into a structured Mistake Knowledge Database (MistakeKDB). False-negative lessons are routed to a recall-oriented Coder, while false-positive lessons are routed to a precision-oriented Judge. We instantiate the framework in LearnActCoder, a Coder-Judge clinical coding pipeline with lookup-table grounding where available. On 150 matched MIMIC-III notes, structured MistakeKDB improves CPT F1 by 5.9 percentage points, while raw-example and reflection-style memories remain near the no-memory baseline; the ICD-9 improvement is not significant. On a matched MIMIC-IV cohort, memory shifts ICD-10 coding toward higher precision at a recall cost, leaving F1 statistically unchanged. Applying the same memory to 1,000 held-out MIMIC-III notes maintains a stable ICD operating point, providing scale/stability evidence. Overall, the results are consistent with structured, feedback-derived error memory being useful for adapting clinical coding behavior across cases without weight updates or changes to the underlying workflow. Absolute CPT/HCPCS performance remains low, and the system is evaluated retrospectively rather than in clinical deployment.

Large language model (LLM) agents already trade with real capital, yet agent-security research has mostly treated them as generic agents. Trading changes the threat: a compromised agent's orders move prices that other participants act on, and an attacker who profits from a crash can trigger the shock that a non-robust agent mishandles. We present FARSIGHT (Financial Agent Robustness and Security Investigation and Global Holistic Taxonomy), a systematization that rates trading agents on robustness to market stress and on security against source manipulation, agent compromise, and agents acting as attackers. It also checks paper-level ratings against released code. Across 15 academic schemes, none earns full credit on any robustness metric, no paper describes a way to halt trading without waiting for LLM inference, and none combines source provenance with cross-source corroboration. In the code of the 7 open-source schemes, no release enforces a stop-loss or position limit outside the LLM, 4 lack a component that their paper or documentation describes, and 2 run model-written code on the host. The same gaps appear beyond finance. Restating FARSIGHT as a domain-independent threat model, we map them onto agents in healthcare, law, software, and crypto. We then trace how compromised agents spread harm, as worms and as cascades that need no further compromise. At published injection rates per hop, a channel read by ten agents lets one compromised agent start an outbreak. We derive 14 open problems and urge deployers to corroborate sources, keep interrupts that bypass the model, and enforce loss limits outside it.

Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In practice, new SEC-filing questions repeatedly expose heterogeneous errors in period, entity, evidence use, and calculation. Existing self-improvement methods can turn failures into new behaviors, but offer limited control over where a correction should apply or which previously correct answers it may break. We therefore frame post-deployment improvement as controlled behavioral maintenance: recurring failures should become scoped skill patches, and each patch should earn deployment with- out introducing regressions. We instantiate this view in FINSKILLOPS, a multi-agent system for SEC filing QA. FINSKILLOPS derives reusable skills from evidence-grounded, typed failure diagnoses and governs them through targeted validation, protected-case regression checks, negative controls, and versioned replacement or retirement. Across six financial QA benchmarks, a single frozen skill registry achieves the highest verdict-weighted correctness and reference consistency among the evaluated systems. Evolved skills raise correctness from 3.70 to 4.55 on our enhanced benchmark. In a separate 12-round operational study, only six of 33 proposed skills are promoted, while the monitoring non-correct rate falls from 20.0% to 12.5%. These results establish controlled skill scope, admission, and lifecycle management as the foundation for reliable self-improvement.

Travel-planning agents generate itineraries that may become infeasible after acceptance because of flight cancellations, hotel unavailability, or attraction closures. Revising these itineraries involves full replanning, classical plan repair, and LLM-based travel-agent revision, whose differing task formulations and evaluation protocols hinder comparison. We conduct a systematic empirical study using two TREK-derived benchmark sets: 500 single-disruption cases, including feasible and infeasible instances, and 200 feasible simultaneous compound-disruption cases. We compare LLM-Z3 full replanning, IPyHOPPER hierarchical repair, and an iTIMO local-revision adapter across effectiveness, plan stability, and computational cost. LLM-Z3 with Gemini achieved the highest observed compound-disruption success. IPyHOPPER nearly matched that configuration's single-disruption overall success, while preserving substantially more of the accepted itinerary on successful repairs. Successful hierarchical and local repairs made fewer edits and retained more accepted commitments than full replanning. Computational profiles differed: IPyHOPPER used no LLM inference, the evaluated LLM-Z3 adapter used compact one-call inference, and the iTIMO adapter consumed substantially more tokens. The study provides practical guidelines for balancing feasibility recovery, commitment preservation, and computational cost within evaluated settings.

Low-altitude wireless networks (LAWNs) are emerging as a key infrastructure for heterogeneous unmanned aerial systems that support concurrent services within a shared three-dimensional airspace. Their coexistence creates strong coupling among mobility, connectivity, and shared network resources, while heterogeneous services impose distinct and time-varying requirements. These interactions naturally form a dynamic non-cooperative game in which both operating conditions and coordination objectives evolve over time. Conventional optimization and learning-based controllers typically rely on predefined objectives, limiting their ability to adapt autonomously to changing service requirements and resource priorities. To address this challenge, we propose a hierarchical hybrid large language model (LLM)- multi-agent reinforcement learning (MARL) architecture organized as a dual-loop structure. Specifically, an outer adaptation loop employs LLM-assisted game orchestration to interpret service requirements and operator intent, and reconfigure objectives and resource priorities, while an inner loop executes decentralized, parameter-conditioned MARL policies under the configured game. A logistics-monitoring case study illustrates how the proposed framework facilitates coordinated coexistence among heterogeneous services, adapting to evolving operating conditions without retraining the underlying MARL policies. Finally, we discuss key challenges and research directions toward scalable, trustworthy, and adaptive agentic LAWNs.