arXiv:2603.03655v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where early-stage hallucinations multiplicatively compound into downstream failures. To overcome this, we present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology. Layer A (Control Plane) establishes a governed supervisor--worker hierarchy that enforces role-based tool isolation, limits execution to constrained action spaces, and drives reflection-based replanning. Layer B (Workflow Plane) operationalizes canonical drug discovery stages -- from Target Identification to Lead Optimization -- as stateful, composable skill graphs. This layer integrates strict data contracts and strategic human-in-the-loop (HITL) checkpoints to safeguard scientific validity at high-uncertainty decision boundaries. Operating on the design principle of ``free-form reasoning for safe tasks, structured execution for long-horizon pipelines,'' Mozi provides built-in robustness mechanisms and trace-level audibility to completely mitigate error accumulation. We evaluate Mozi on PharmaBench, a curated benchmark for biomedical agents, demonstrating superior orchestration accuracy over existing baselines. Furthermore, through end-to-end therapeutic case studies, we demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates, effectively transforming the LLM from a fragile conversationalist into a reliable, governed co-scientist.

arXiv:2603.03761v1 Announce Type: new Abstract: LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configurations. Existing LLM leaderboards and tool/agent benchmarks evaluate components in isolation and remain fragmented across tasks, metrics, and candidate pools, leaving a critical research gap: there is little query-conditioned supervision for learning to recommend end-to-end agent configurations that couple a backbone model with a toolkit. We address this gap with AgentSelect, a benchmark that reframes agent selection as narrative query-to-agent recommendation over capability profiles and systematically converts heterogeneous evaluation artifacts into unified, positive-only interaction data. AgentSelectcomprises 111,179 queries, 107,721 deployable agents, and 251,103 interaction records aggregated from 40+ sources, spanning LLM-only, toolkit-only, and compositional agents. Our analyses reveal a regime shift from dense head reuse to long-tail, near one-off supervision, where popularity-based CF/GNN methods become fragile and content-aware capability matching is essential. We further show that Part~III synthesized compositional interactions are learnable, induce capability-sensitive behavior under controlled counterfactual edits, and improve coverage over realistic compositions; models trained on AgentSelect also transfer to a public agent marketplace (MuleRun), yielding consistent gains on an unseen catalog. Overall, AgentSelect provides the first unified data and evaluation infrastructure for agent recommendation, which establishes a reproducible foundation to study and accelerate the emerging agent ecosystem.

arXiv:2603.03781v1 Announce Type: new Abstract: Long-term memory is fundamental for personalized agents capable of accumulating knowledge, reasoning over user experiences, and adapting across time. However, existing memory benchmarks primarily target declarative memory, specifically semantic and episodic types, where all information is explicitly presented in dialogues. In contrast, real-world actions are also governed by non-declarative memory, including habitual and procedural types, and need to be inferred from diverse digital traces. To bridge this gap, we introduce Lifebench, which features densely connected, long-horizon event simulation. It pushes AI agents beyond simple recall, requiring the integration of declarative and non-declarative memory reasoning across diverse and temporally extended contexts. Building such a benchmark presents two key challenges: ensuring data quality and scalability. We maintain data quality by employing real-world priors, including anonymized social surveys, map APIs, and holiday-integrated calendars, thus enforcing fidelity, diversity and behavioral rationality within the dataset. Towards scalability, we draw inspiration from cognitive science and structure events according to their partonomic hierarchy; enabling efficient parallel generation while maintaining global coherence. Performance results show that top-tier, state-of-the-art memory systems reach just 55.2\% accuracy, highlighting the inherent difficulty of long-horizon retrieval and multi-source integration within our proposed benchmark. The dataset and data synthesis code are available at https://github.com/1754955896/LifeBench.

arXiv:2603.03911v1 Announce Type: new Abstract: Web security demands rapid response capabilities to evolving cyber threats. Agentic Artificial Intelligence (AI) promises automation, but the need for trustworthy security responses is of the utmost importance. This work investigates the role of semantic relations in extracting information for sensitive operational tasks, such as configuring security controls for mitigating threats. To this end, it proposes to leverage hypernym-hyponym textual relations to extract relevant information from Cyber Threat Intelligence (CTI) reports. By leveraging a neuro-symbolic approach, the multi-agent system automatically generates CLIPS code for an expert system creating firewall rules to block malicious network traffic. Experimental results show the superior performance of the hypernym-hyponym retrieval strategy compared to various baselines and the higher effectiveness of the agentic approach in mitigating threats.

arXiv:2603.04149v1 Announce Type: new Abstract: Structural and functional heterogeneity are hallmarks of cortical circuits, from broad degree distributions in the mouse connectome to diverse intrinsic neuronal timescales. Yet a mechanistic link between connectivity heterogeneity and functional diversity is lacking. To bridge this gap, we introduce a random recurrent network in which connectivity is generated by a configuration model with tunable degree heterogeneity and synaptic weights exhibiting varying levels of correlation. Using generating-functional methods, we derive a heterogeneous dynamical mean-field theory (hDMFT) with degree-conditioned stochastic dynamics. The theory shows that the interaction of partial symmetry in the weights and degree heterogeneity induces a non-Markovian memory term in the form of an emergent self-coupling whose strength scales with degree and produces a broad distribution of activity timescales. We obtain analytic stability criteria demonstrating that degree heterogeneity lowers the critical gain and localizes unstable modes onto hubs. The resulting rich dynamical landscape includes silent, chaotic, and multistable regimes, which we uncover via spectral, replica, and Lyapunov exponent analyses. We highlight the computational benefits of the observed timescale heterogeneity by revealing that, under an external input drive featuring a broadband spectrum, slow hub neurons act as integrators, demixing slow input components. Finally, instantiating the model with the empirically measured topology from the MICrONS cubic-millimeter mouse connectome explains the broad range of single-neuron timescales and their positive correlation with in-degree observed in resting-state recordings. Our results provide a mechanistic link between connectome topology, neural dynamics, and computation, identifying hubs in partially symmetric networks as a natural substrate for multiplexed processing across timescales.

arXiv:2603.03290v1 Announce Type: cross Abstract: Long-horizon LLM agents require memory systems that remain accurate under fixed context budgets. However, existing systems struggle with two persistent challenges in long-term dialogue: (i) \textbf{disconnected evidence}, where multi-hop answers require linking facts distributed across time, and (ii) \textbf{state updates}, where evolving information (e.g., schedule changes) creates conflicts with older static logs. We propose AriadneMem, a structured memory system that addresses these failure modes via a decoupled two-phase pipeline. In the \textbf{offline construction phase}, AriadneMem employs \emph{entropy-aware gating} to filter noise and low-information message before LLM extraction and applies \emph{conflict-aware coarsening} to merge static duplicates while preserving state transitions as temporal edges. In the \textbf{online reasoning phase}, rather than relying on expensive iterative planning, AriadneMem executes \emph{algorithmic bridge discovery} to reconstruct missing logical paths between retrieved facts, followed by \emph{single-call topology-aware synthesis}. On LoCoMo experiments with GPT-4o, AriadneMem improves \textbf{Multi-Hop F1 by 15.2\%} and \textbf{Average F1 by 9.0\%} over strong baselines. Crucially, by offloading reasoning to the graph layer, AriadneMem reduces \textbf{total runtime by 77.8\%} using only \textbf{497} context tokens. The code is available at https://github.com/LLM-VLM-GSL/AriadneMem.

arXiv:2603.03314v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable and steadily improving performance across a wide range of tasks. However, LLM performance may be highly sensitive to prompt variations especially in scenarios with limited openness or strict output formatting requirements, indicating insufficient robustness. In real-world applications, user prompts provided to LLMs often contain imperfections, which may undermine the quality of the model's responses. To address this issue, previous work has primarily focused on preprocessing prompts, employing external tools or even LLMs to refine prompt formulations in advance. However, these approaches overlook the intrinsic robustness of LLMs, and their reliance on external components introduces additional computational overhead and uncertainty. In this work, we propose a Contrastive Learning-based Inverse Direct Preference Optimization (CoIPO) method that minimizes the discrepancy between the label-aligned logits produced by the model under a clean prompt and its noisy counterpart, and conduct a detailed analysis using mutual information theory. We augment the FLAN dataset by constructing paired prompts, each consisting of a clean prompt and its corresponding noisy version for training. Additionally, to evaluate the effectiveness, we develop NoisyPromptBench, a benchmark enhanced and derived from the existing PromptBench. Experimental results conducted on NoisyPromptBench demonstrate that our proposed method achieves a significant improvement in average accuracy over the current state-of-the-art approaches. The source code of CoIPO, pair-wise FLAN datasets, and NoisyPromptBench have already been released on https://github.com/vegetable-yx/CoIPO.

arXiv:2603.03318v1 Announce Type: cross Abstract: Recent advances in Natural Language Processing have been predominantly driven by transformer-based architectures, which rely heavily on self-attention mechanisms to model relationships between tokens in a sequence. Similarly, the field of Quantum Natural Language Processing, which seeks to leverage quantum principles to address challenges in language understanding and generation tasks, has seen the recent development of quantum self-attention mechanisms. We propose a classical quantum-inspired self-attention (QISA) mechanism and integrate it into the full autoregressive language modeling pipeline of GPT-1. To the best of our knowledge, this is the first integration of this kind, as previous quantum self-attention mechanisms have been primarily tested on text classification. In our experiments, QISA achieves better performance when compared to standard self-attention on the metrics character error rate ($15.5\times$ better), word error rate ($4.7 \times $) and cross-entropy loss ($13 \times$). This is achieved while only requiring a $ 2.6\times$ longer inference time.

arXiv:2603.03329v1 Announce Type: cross Abstract: Despite significant strides in language models in the last few years, when used as agents, such models often try to perform actions that are not just suboptimal for a given state, but are strictly prohibited by the external environment. For example, in the recent Kaggle GameArena chess competition, 78% of Gemini-2.5-Flash losses were attributed to illegal moves. Often people manually write "harnesses" around LLMs to prevent such failures. In this paper, we demonstrate that Gemini-2.5-Flash can automatically synthesize such a code harness, using a small number of rounds of iterative code refinement given feedback from the (game) environment. The resulting harness prevents all illegal moves in 145 different TextArena games (both 1-player and 2-player), enabling the smaller Gemini-2.5-Flash model to outperform larger models, such as Gemini-2.5-Pro. Pushing our technique to the limit, we can get Gemini-2.5-Flash to generate the entire policy in code, thus eliminating the need to use the LLM at decision making time. The resulting code-policy receives a higher average reward than Gemini-2.5-Pro and GPT-5.2-High on 16 TextArena 1-player games. Our results show that using a smaller model to synthesize a custom code harness (or entire policy) can outperform a much larger model, while also being more cost effective.

arXiv:2603.03388v1 Announce Type: cross Abstract: Recent neural solvers have achieved strong performance on vehicle routing problems (VRPs), yet they mainly assume symmetric Euclidean distances, restricting applicability to real-world scenarios. A core challenge is encoding the relational features in asymmetric distance matrices of VRPs. Early attempts directly encoded these matrices but often failed to produce compact embeddings and generalized poorly at scale. In this paper, we propose RADAR, a scalable neural framework that augments existing neural VRP solvers with the ability to handle asymmetric inputs. RADAR addresses asymmetry from both static and dynamic perspectives. It leverages Singular Value Decomposition (SVD) on the asymmetric distance matrix to initialize compact and generalizable embeddings that inherently encode the static asymmetry in the inbound and outbound costs of each node. To further model dynamic asymmetry in embedding interactions during encoding, it replaces the standard softmax with Sinkhorn normalization that imposes joint row and column distance awareness in attention weights. Extensive experiments on synthetic and real-world benchmarks across various VRPs show that RADAR outperforms strong baselines on both in-distribution and out-of-distribution instances, demonstrating robust generalization and superior performance in solving asymmetric VRPs.

arXiv:2603.03585v1 Announce Type: cross Abstract: Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across demographic groups due to differences in underlying beliefs. As Large Language Models (LLMs) are increasingly used to simulate human behaviors, we investigate whether they can simulate demographic misinformation susceptibility, treating beliefs as a primary driving factor. We introduce BeliefSim, a simulation framework that constructs demographic belief profiles using psychology-informed taxonomies and survey priors. We study prompt-based conditioning and post-training adaptation, and conduct a multi-fold evaluation using: (i) susceptibility accuracy and (ii) counterfactual demographic sensitivity. Across both datasets and modeling strategies, we show that beliefs provide a strong prior for simulating misinformation susceptibility, with accuracy up to 92%.

arXiv:2603.03644v1 Announce Type: cross Abstract: Educational games can foster critical thinking, problem-solving, and motivation, yet instructors often find it difficult to design games that reliably achieve specific learning outcomes. Existing authoring environments reduce the need for programming expertise, but they do not eliminate the underlying challenges of educational game design, and they can leave non-expert designers reliant on opaque suggestions from AI systems. We designed a controlled natural language framework-based web tool that positions language as the primary interface for LLM-assisted educational game design. In the tool, users and an LLM assistant collaboratively develop a structured language that maps pedagogy to gameplay through four linked components. We argue that, by making pedagogical intent explicit and editable in the interface, the tool has the potential to lower design barriers for non-expert designers, preserves human agency in critical decisions, and enables alignment and reflections between pedagogy and gameplay during and after co-creation.

arXiv:2603.03772v1 Announce Type: cross Abstract: AI-driven analytics are increasingly crucial to data-centric decision-making. The practice of exporting data to machine learning runtimes incurs high overhead, limits robustness to data drift, and expands the attack surface, especially in multi-tenant, heterogeneous data systems. Integrating AI directly into database engines, while offering clear benefits, introduces challenges in managing joint query processing and model execution, optimizing end-to-end performance, coordinating execution under resource contention, and enforcing strong security and access-control guarantees. This paper discusses the challenges of joint DB-AI, or AIxDB, data management and query processing within AI-powered data systems. It presents various challenges that need to be addressed carefully, such as query optimization, execution scheduling, and distributed execution over heterogeneous hardware. Database components such as transaction management and access control need to be re-examined to support AI lifecycle management, mitigate data drift, and protect sensitive data from unauthorized AI operations. We present a design and preliminary results to demonstrate what may be key to the performance for serving AIxDB queries.

arXiv:2603.03939v1 Announce Type: cross Abstract: Multimodal industrial anomaly detection benefits from integrating RGB appearance with 3D surface geometry, yet existing \emph{unsupervised} approaches commonly rely on memory banks, teacher-student architectures, or fragile fusion schemes, limiting robustness under noisy depth, weak texture, or missing modalities. This paper introduces \textbf{CMDR-IAD}, a lightweight and modality-flexible unsupervised framework for reliable anomaly detection in 2D+3D multimodal as well as single-modality (2D-only or 3D-only) settings. \textbf{CMDR-IAD} combines bidirectional 2D$\leftrightarrow$3D cross-modal mapping to model appearance-geometry consistency with dual-branch reconstruction that independently captures normal texture and geometric structure. A two-part fusion strategy integrates these cues: a reliability-gated mapping anomaly highlights spatially consistent texture-geometry discrepancies, while a confidence-weighted reconstruction anomaly adaptively balances appearance and geometric deviations, yielding stable and precise anomaly localization even in depth-sparse or low-texture regions. On the MVTec 3D-AD benchmark, CMDR-IAD achieves state-of-the-art performance while operating without memory banks, reaching 97.3\% image-level AUROC (I-AUROC), 99.6\% pixel-level AUROC (P-AUROC), and 97.6\% AUPRO. On a real-world polyurethane cutting dataset, the 3D-only variant attains 92.6\% I-AUROC and 92.5\% P-AUROC, demonstrating strong effectiveness under practical industrial conditions. These results highlight the framework's robustness, modality flexibility, and the effectiveness of the proposed fusion strategies for industrial visual inspection. Our source code is available at https://github.com/ECGAI-Research/CMDR-IAD/

arXiv:2603.03983v1 Announce Type: cross Abstract: Recent advances in MLLMs are reframing segmentation from fixed-category prediction to instruction-grounded localization. While reasoning based segmentation has progressed rapidly in natural scenes, remote sensing lacks a generalizable solution due to the prohibitive cost of reasoning-oriented data and domain-specific challenges like overhead viewpoints. We present GeoSeg, a zero-shot, training-free framework that bypasses the supervision bottleneck for reasoning-driven remote sensing segmentation. GeoSeg couples MLLM reasoning with precise localization via: (i) bias-aware coordinate refinement to correct systematic grounding shifts and (ii) a dual-route prompting mechanism to fuse semantic intent with fine-grained spatial cues. We also introduce GeoSeg-Bench, a diagnostic benchmark of 810 image--query pairs with hierarchical difficulty levels. Experiments show that GeoSeg consistently outperforms all baselines, with extensive ablations confirming the effectiveness and necessity of each component.

arXiv:2603.04113v1 Announce Type: cross Abstract: Demographic attributes such as age, sex, and race can be predicted from medical images, raising concerns about bias in clinical AI systems. In brain MRI, this signal may arise from anatomical variation, acquisition-dependent contrast differences, or both, yet these sources remain entangled in conventional analyses. Without disentangling them, mitigation strategies risk failing to address the underlying causes. We propose a controlled framework based on disentangled representation learning, decomposing brain MRI into anatomy-focused representations that suppress acquisition influence and contrast embeddings that capture acquisition-dependent characteristics. Training predictive models for age, sex, and race on full images, anatomical representations, and contrast-only embeddings allows us to quantify the relative contributions of structure and acquisition to the demographic signal. Across three datasets and multiple MRI sequences, we find that demographic predictability is primarily rooted in anatomical variation: anatomy-focused representations largely preserve the performance of models trained on raw images. Contrast-only embeddings retain a weaker but systematic signal that is dataset-specific and does not generalise across sites. These findings suggest that effective mitigation must explicitly account for the distinct anatomical and acquisition-dependent origins of the demographic signal, ensuring that any bias reduction generalizes robustly across domains.

arXiv:2603.04128v1 Announce Type: cross Abstract: Developing Audio-Visual Large Language Models (AV-LLMs) for unified scene understanding is pivotal in multimodal intelligence. While instruction tuning enables pre-trained models with multi-task abilities, we observe that conventional multi-task unification methods often suffer from severe negative transfer, where nearly 55% of tasks degrade compared to single-task training. We attribute this phenomenon to audio-visual task heterogeneity, characterized by disparate task granularity and divergent capability demands, which lead to negative interference under joint training. To tackle this, we present Crab$^{+}$, a scalable and unified audio-visual scene understanding model that addresses task heterogeneity through explicit cooperation from both data and model perspectives. On the data side, we introduce AV-UIE v2, a comprehensive Audio-Visual Unified Instruction-tuning dataset with Explicit reasoning processes. It contains approximately 222K samples spanning 17 datasets and 7 tasks, enabling the model to capture cross-task relationships at different levels of granularity. On the model side, we design a unified interface to align heterogeneous task formulations, and propose Interaction-aware LoRA (I-LoRA), which explicitly models inter-task relationships via dynamic routing to coordinate distinct audio-visual interaction patterns, mitigating parameter interference. Extensive experiments show Crab$^{+}$ covers broader tasks than existing unified models while outperforming specialized models on various benchmarks. We successfully reverse the negative transfer trend, achieving positive transfer where multi-task learning surpasses single-task baselines in nearly 88% of tasks. These results hold across diverse AV-LLM paradigms and are validated through in-depth visualization, positioning Crab$^{+}$ as a robust step towards holistic audio-visual scene understanding.

arXiv:2603.04314v1 Announce Type: cross Abstract: Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of $1,000$ cattle individuals captured from $128$ uniformly sampled viewpoints ($128,000$ annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at https://github.com/TurtleSmoke/MOO.

arXiv:2603.04366v1 Announce Type: cross Abstract: Generative audio requires fine-grained controllable outputs, yet most existing methods require model retraining on specific controls or inference-time controls (\textit{e.g.}, guidance) that can also be computationally demanding. By examining the bottlenecks of existing guidance-based controls, in particular their high cost-per-step due to decoder backpropagation, we introduce a guidance-based approach through selective TFG and Latent-Control Heads (LatCHs), which enables controlling latent audio diffusion models with low computational overhead. LatCHs operate directly in latent space, avoiding the expensive decoder step, and requiring minimal training resources (7M parameters and $\approx$ 4 hours of training). Experiments with Stable Audio Open demonstrate effective control over intensity, pitch, and beats (and a combination of those) while maintaining generation quality. Our method balances precision and audio fidelity with far lower computational costs than standard end-to-end guidance. Demo examples can be found at https://zacharynovack.github.io/latch/latch.html.

arXiv:2601.16529v2 Announce Type: replace Abstract: Large language models (LLMs) show promise in clinical decision support yet risk acquiescing to patient pressure for inappropriate care. We introduce SycoEval-EM, a multi-agent simulation framework evaluating LLM robustness through adversarial patient persuasion in emergency medicine. Across 20 LLMs and 1,875 encounters spanning three Choosing Wisely scenarios, acquiescence rates ranged from 0-100\%. Models showed higher vulnerability to imaging requests (38.8\%) than opioid prescriptions (25.0\%), with model capability poorly predicting robustness. All persuasion tactics proved equally effective (30.0-36.0\%), indicating general susceptibility rather than tactic-specific weakness. Our findings demonstrate that static benchmarks inadequately predict safety under social pressure, necessitating multi-turn adversarial testing for clinical AI certification.