arXiv:2605.15764v1 Announce Type: new Abstract: Understanding social interactions requires reasoning over subtle non-verbal cues, yet current multimodal large language models (MLLMs) often fail to identify who interacts with whom in multi-person videos. We introduce GRASP, a large-scale social reasoning dataset that connects high-level social QA with fine-grained gaze and deictic gesture events. GRASP contains 290K question--answer pairs over 46K videos totaling 749 hours, organized by a 16-category taxonomy spanning gaze, gesture, and joint gaze--gesture reasoning, together with GRASP-Bench for evaluation. Unlike prior resources that focus on either isolated cues or high-level social QA, GRASP builds questions from identity-consistent gaze trajectories, deictic gestures, and their joint compositions into social events. Moreover, we propose Social Grounding Reward (SGR), a learning signal that uses these social events to encourage models to reason about the participants involved in each interaction. Experiments show that SGR improves performance on GRASP-Bench while maintaining zero-shot performance on related social video QA benchmarks.
Science Journals
arXiv:2605.15205v1 Announce Type: new Abstract: Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective social interactions between these AI models and humans. However, the existing benchmarks often measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective, while ignoring the first-person, dynamic, and open-ended nature of human-AI (HAI) interactions. To directly examine how ToM improvement techniques benefit HAI interactions, we first proposed the new paradigm of interactive ToM evaluation with both perspective and metric shifts. Next, following the paradigm, we conducted a systematic study of four representative ToM enhancement techniques using both four real-world datasets and a user study, covering both goal-oriented tasks (e.g., coding, math) and experience-oriented tasks (e.g., counseling). Our findings reveal that improvements on static benchmarks do not always translate to better performance in dynamic HAI interactions. This paper offers critical insights into ToM evaluation, showing the necessity of interaction-based assessments in developing next-generation, socially aware LLMs for HAI symbiosis.
arXiv:2605.15763v1 Announce Type: new Abstract: Current state-of-the-art Quality Estimation (QE) in machine translation relies on massive, proprietary LLMs, raising data privacy concerns. We demonstrate that smaller, open-source LLMs (<30B parameters) are a viable, cost-effective and privacy-preserving alternative. Using a single-pass prompting strategy, our models simultaneously generate quality scores, MQM error annotations, suggested error corrections, and full post-editions. Our analysis shows these models achieve highly competitive system-level correlations with human judgments that outperform traditional neural metrics, fine-tuned models, and human inter-annotator agreement, effectively approximating the capabilities of much larger proprietary LLMs.
arXiv:2605.15204v1 Announce Type: new Abstract: Multi-agent orchestration frameworks such as LangChain, LangGraph, and CrewAI route tasks through graph-based pipelines but do not enforce the stage constraints that govern real business processes. We present SDOF, a framework that treats multi-agent execution as a constrained state machine. SDOF operates through two primary defensive layers, implemented by three components: (1) an Online-RLHF Specialized Intent Router trained via Generative Reward Modeling (GRPO) and (2) a StateAwareDispatcher with GoalStage finite-automaton checks and precondition/postcondition SkillRegistry validation for auditable execution control. On a recruitment system backed by the Beisen iTalent platform (6000+ enterprises), 185 expert-curated scenarios trigger 1671 live API calls. Our GSPO-aligned 7B Intent Router achieves higher joint accuracy than zero-shot GPT-4o on this FSM-constrained adversarial routing benchmark (80.9% versus 48.9%). In end-to-end execution, SDOF reaches 86.5% task completion (95% confidence interval 80.8 to 90.7) and blocks all 22 operations in the injection, illegal HR subset. Under a broader message-level blocking audit, SDOF attains precision 100% and recall 88%, expert agreement kappa=0.94. A separate evaluation on 960 SGD-derived dialogues spanning 8 service domains surfaces 201 stage-order conflicts under our FSM mapping, 41 of which arise in the normal split. This arXiv version reports the current validated scope; extended multi-seed training comparisons and deeper workflow evaluations will be released in a subsequent update.
arXiv:2605.16101v1 Announce Type: cross Abstract: Measurement is an important scientific activity. In most of science, including classical physics, is may be understood as a way of finding out about the physical world and representing the results numerically. No-go theorems show that measurement of quantum observables is not like that: the recorded outcome is typically created rather than revealed in a quantum measurement, in which case there is no objective fact about the observable's prior value. Other no-go theorems show that unitary quantum theory can generally neither explain nor even represent a unique recorded outcome, thereby threatening that outcome's objectivity. Methodological norms inherent in quantum physical practice nevertheless institute the objectivity, not only of unique recorded outcomes of quantum measurements, but also of non-quantum features of the world that physicists and other scientists take their models to represent.
arXiv:2605.15750v1 Announce Type: new Abstract: The rapid expansion of electric vehicles (EVs) necessitates scalable and efficient fast charging station (FCS) infrastructure. These stations often operate in oversubscribed configurations where the total port rating exceeds a station-level cap reflecting infrastructure limits, grid constraints or market setpoints. In such settings, ensuring fairness in real-time power allocation is essential to prevent user bias and secure equitable access to limited resources while maximizing infrastructure utilization. This task is further complicated by state-of-charge dependent EV power limits defined by charge curves, for which accurate data is often unavailable. This paper introduces two fairness-guaranteed online power allocation policies: FAIR-OPAP-C for conventional FCSs with continuously adjustable power delivery, and FAIR-OPAP-M for modular FCSs composed of discrete assignable power modules. Unlike existing methods, these algorithms require no prior knowledge of charge curves, utilizing only instantaneous power requests available via standard protocols. We formalize fairness with a unified framework encompassing envy-freeness, Pareto efficiency, and proportionality, and establish theoretical guarantees for both algorithms. The algorithms rely on lightweight operations, achieving near-linear and logarithmic scalability for the conventional and modular cases, respectively. Comprehensive evaluations show the proposed methods achieve superior performance across various metrics among seven benchmarks from EV charging and fair division literature. Furthermore, they are orders of magnitude faster than optimization-based approaches, with runtimes below 1 ms for up to 300 EVs, validating their suitability for real-time deployment on hardware-constrained edge devices.
arXiv:2605.15737v1 Announce Type: new Abstract: Machine unlearning has reached a critical bottleneck. As traditional weight-space interventions focus primarily on erasing targeted concepts, they often fail to prevent the unintended suppression of other significant representations. This leads to substantial collateral damage, with essential knowledge being forgotten, because these methods lack formal mathematical guarantees for the preservation of neutral concepts. To avoid degradation, they are frequently forced into conservative updates. We propose BARRIER (Bounded Activation Regions for Robust Information Erasure), a paradigm-shifting framework that shifts the locus of intervention from static model weights to the dynamic geometry of hidden-layer activations. Unlike existing methods, BARRIER employs Interval Arithmetic (IA) on SVD-based projections of the activation space to encapsulate the specific target region within a bounding hypercube. By driving unlearning updates exclusively within this forget interval and mathematically bounding the model response on the complement, we ensure rigorous protection of the retain distribution. This geometric construction transforms the preservation of knowledge from an empirical heuristic into a formal optimization target with a probabilistic tail bound on functional drift. Crucially, this stability permits highly aggressive unlearning updates within the forget region. Empirical evaluations demonstrate that BARRIER matches state-of-the-art trade-offs across classifiers and diffusion models, maximizing targeted concept erasure while safeguarding the integrity of all other representations. Our code is available at https://github.com/OneAndZero24/BARRIER.
arXiv:2603.14764v4 Announce Type: replace Abstract: Geometric data augmentation is widely used in segmentation workflows, but polygon annotations are often assumed to remain valid after transformation. This assumption can fail in structured domains such as architectural floorplan analysis, where a region may contain an interior void encoded as part of a single ordered polygon chain. Cropping or clipping can remove bridge vertices in this chain, causing one semantic region to split into disconnected components. We propose a lightweight topology-preserving augmentation strategy that repairs missing adjacency relations in index space while preserving the original vertex order. The method adds minimal overhead and can be integrated into existing preprocessing workflows. Experiments show that the proposed approach achieves near-perfect Cyclic Adjacency Preservation (CAP) across common geometric transformations and improves annotation consistency in polygon-based segmentation.
arXiv:2603.09650v2 Announce Type: replace Abstract: Toroidal topologies and helicity are pervasive in nature and hold basic importance in scientific research. In particular, the interplay between these features gives rise to fascinating toroidal helical electromagnetic excitations. Here, we present a theoretical framework and experimental realization to introduce a family of toroidal helical pulses, exploring the intersection of the helicity and propagating toroidal modes. For this purpose, we propose a configuration combining a coaxial horn emitter and an equiangular spiral grating to directly generate such single-cycle pulses. In addition to their inherent non-transverse toroidal topology and space-time nonseparability, such pulses also possess controllable helicity. This work gives rise to a helical version of propagating toroidal electrodynamics, thereby paving the way for advanced applications, such as nontrivial light-matter interactions and data transfer.
arXiv:2603.05917v3 Announce Type: replace Abstract: Stock market prediction presents considerable challenges for investors, financial institutions, and policymakers operating in complex market environments characterized by noise, non-stationarity, and behavioral dynamics. Traditional forecasting methods, including fundamental analysis and technical indicators, often fail to capture the intricate patterns and cross-sectional dependencies inherent in financial markets. This paper presents an integrated framework combining a node transformer architecture with BERT-based sentiment analysis for stock price forecasting. The proposed model represents the stock market as a graph structure where individual stocks form nodes and edges capture relationships including sectoral affiliations, correlated price movements, and supply chain connections. A fine-tuned BERT model extracts sentiment information from social media posts and combines it with quantitative market features through attention-based fusion mechanisms. The node transformer processes historical market data while capturing both temporal evolution and cross-sectional dependencies among stocks. Experiments conducted on 20 S&P 500 stocks spanning January 1982 to March 2025 demonstrate that the integrated model achieves a mean absolute percentage error (MAPE) of 0.80% for one-day-ahead predictions, compared to 1.20% for ARIMA and 1.00% for LSTM. The inclusion of sentiment analysis reduces prediction error by 10% overall and 25% during earnings announcements, while the graph-based architecture contributes an additional 15% improvement by capturing inter-stock dependencies. Directional accuracy reaches 65% for one-day forecasts. Statistical validation through paired t-tests confirms the significance of these improvements (p < 0.05 for all comparisons). The model maintains lower error during high-volatility periods, achieving MAPE of 1.50% while baseline models range from 1.60% to 2.10%.
arXiv:2605.15842v1 Announce Type: new Abstract: The semiconductor industry is foundational to modern technology, yet its complex global multi-relational firm network remains poorly understood, posing challenges to scientists, firms, and policymakers. Traditional analysis relies on proprietary databases that are often expensive, incomplete, and slowly updated, limiting their ability to capture rapidly evolving dependencies. Here, we demonstrate that a novel, generalizable methodology combining Large Language Models (LLMs) with open web data can reconstruct this network and its structural dynamics at scale. We identify and classify supply-chain, partnership, and ownership links from 170 million semiconductor firm webpages, yielding a temporal network of over 1,300 linked firms. We validate link-extraction quality (Precision: 0.884; F1-score: 0.784), network overlap and complementarity with a proprietary database, and consistency with aggregate economic data. Our network reveals a temporary 9% decline in edges during the 2022 chip shortage, rapid increases in the centrality of AI supply-chain bottleneck firms such as NVIDIA, and geographic realignment of interfirm relations amid geopolitical turbulence. This generalizable framework overcomes barriers to transparency and provides essential, up-to-date maps for assessing resilience and informing policy across strategically relevant sectors.
arXiv:2603.04261v2 Announce Type: replace Abstract: Evidence on the effectiveness of Man-At-The-End (MATE) software protections, such as code obfuscation, has mainly come from limited empirical research. Recently, however, an automatable method was proposed to obtain statistical models of the required effort to attack (protected) software. The proposed method was sketched for a number of attack strategies but not instantiated, evaluated, or validated for those that require human interaction with the attacked software. In this paper, we present a full instantiation of the method to obtain statistical effort models for game resource localisation attacks, which represent a major step towards creating game cheats, a prime example of MATE attacks. We discuss in detail all relevant aspects of our instantiation and the results obtained for two game use cases. Our results confirm the feasibility of the proposed method and its utility for decision support for users of software protection tools. These results open up a new avenue for obtaining models of the impact of software protections on reverse engineering attacks, which will scale much better than empirical research involving human participants.
arXiv:2605.16020v1 Announce Type: new Abstract: Monte Carlo methods are essential across diverse scientific fields, yet their efficiency is frequently hampered by critical slowing down-a sharp increase in autocorrelation times near phase transitions. Although deep learning approaches, such as neural-network-based samplers, have been proposed to alleviate this issue, they face another serious problem: the difficulty of training the models. This difficulty partially stems from the overly general nature of original machine-learning architectures, which often ignore underlying physical symmetries and force networks to relearn them from scratch. In this paper, we demonstrate that incorporating physical priors into the model significantly enhances performance. Building upon existing strategies that integrate spin-spin interactions, we propose a framework that utilizes a prior probability distribution as a starting point for training. Our results for the Ising model, as well as for the Edwards-Anderson spin glass model, suggest that moving away from `blank slate' models in favor of physics-informed priors reduces the training burden and facilitates the simulation of larger system sizes in discrete spin models.
arXiv:2605.15721v1 Announce Type: new Abstract: Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly treat this as a global search problem, seeking a single context strategy that maximizes average performance across a dataset. This restrictive assumption overlooks the fact that different inputs often require distinct guidance, leaving substantial instance-level performance gains untapped. In this paper, we propose a paradigm shift by formulating context engineering as a recommendation problem. We introduce \textbf{Neural Collaborative Context Engineering (NCCE)}, a framework that transitions optimization from a static global search to dynamic, instance-wise routing. NCCE first bootstraps a diverse catalog of anchor contexts and then employs a novel \textbf{Context-CF Co-Evolution} mechanism. This stage establishes a synergistic feedback loop: a lightweight Neural Collaborative Filtering (NCF) model learns instance-context preferences to guide the generation of specialized context variants, while the newly evaluated contexts continuously refine the NCF model's understanding of latent preferences. At inference time, the trained NCF model acts as a context router, dynamically assigning the most suitable context strategy to each unseen instance. Theoretical Proofs and comprehensive experiments demonstrate that by matching individual inputs with their optimal contexts, NCCE significantly improves task accuracy, highlighting the critical importance of personalization in LLM context engineering.
arXiv:2605.15584v1 Announce Type: new Abstract: Vision-language models like CLIP have demonstrated remarkable zero-shot transfer capabilities. However, their susceptibility to imperceptible adversarial perturbations remains a critical security concern. While test-time defenses offer a pragmatic solution for deployed models, existing approaches typically rely on gradient-based optimization during inference, incurring significant computational overhead. In this paper, we revisit the role of data augmentation in CLIP robustness and observe that augmentations are not equally effective: specific augmentations consistently provide robust geometric cues that align with correct class semantics in the hyperspherical feature space. Based on this, we propose Adaptive Geodesic Correction (AGC), a training-free defense mechanism that requires no parameter updates. AGC identifies a reliable augmentation as a geometric anchor and corrects the input feature towards it, utilizing an adaptive step size to balance robustness against clean accuracy preservation. AGC achieves superior performance across eight fine-grained datasets and three CLIP backbones, improving average robust accuracy by 44.4\% over state-of-the-art baseline while delivering a 10$\times$ reduction in inference latency. Our findings reveal a fundamental geometric property of CLIP features, offering a highly efficient and effective paradigm for robust multimodal deployment.
arXiv:2605.15202v1 Announce Type: new Abstract: Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize the artifact (a visually plausible deck) while under-optimizing the delivery process (pacing, narrative, and presentation preparation). We present DeepSlide, a human-in-the-loop multi-agent system that supports preparing the full presentation process, from requirement elicitation and time-budgeted narrative planning, to evidence-grounded slide--script generation, attention augmentation, and rehearsal support. DeepSlide integrates (i) a controllable logical-chain planner with per-node time budgets, (ii) a lightweight content-tree retriever for grounding, (iii) Markov-style sequential rendering with style inheritance, and (iv) sandboxed execution with minimal repair to ensure renderability. We further introduce a dual-scoreboard benchmark that cleanly separates static artifact quality from dynamic delivery excellence. Across 20 domains and diverse audience profiles, DeepSlide matches strong baselines on artifact quality while consistently achieving larger gains on delivery metrics, improving narrative flow, pacing precision, and slide--script synergy with clearer attention guidance.
arXiv:2605.15538v1 Announce Type: cross Abstract: We study a stochastic optimization problem in which the sampling distribution depends on the decision variable, and the available samples are generated through an iterate-dependent Markov chain. Such settings arise naturally in problems with decision-dependent uncertainty; however, they introduce bias and temporal dependence, which render standard techniques developed for i.i.d.\ noise inapplicable. In this work, we analyze the stochastic mirror descent algorithm under iterate-dependent Markov noise. We first establish almost sure convergence for both convex and non-convex problems under the mild assumption of Lipschitz continuity of the objective function, without requiring differentiability. We then derive finite-time concentration bounds for smooth objectives. In the convex setting, the resulting sample complexity matches the classical rate of stochastic mirror descent under i.i.d.\ noise. In the non-convex setting, we obtain a sample complexity bound in terms of the norm of the Riemannian gradient over the probability simplex. Overall, our results establish a unified convergence framework for stochastic mirror descent with state-dependent Markov noise, and highlight its behavior in both convex and non-convex regimes.
arXiv:2605.15439v1 Announce Type: cross Abstract: We reformulate the R\'enyi entanglement of purification as a constrained minimum output R\'enyi entropy problem. Equivalently, for $p>1$, this formulation can be expressed in terms of a constrained maximal output Schatten $p$-norm. More precisely, for a completely positive map $\Omega:L(B')\to L(A)$, we consider the quantity $\upsilon_p(\Omega)$ defined by optimizing $\|(\Omega\otimes \mathrm{id}_E)(\sigma^{B'E})\|_p$ over all bipartite states $\sigma^{B'E}$ whose $B'$-marginal is maximally mixed. We focus on the case $p=2$. First, we compute $\upsilon_2$ for the transpose-depolarizing channel and prove that it is multiplicative under tensor powers. We then establish a general multiplicativity criterion: whenever a completely positive map $N:L(B')\to L(A)$ satisfies $N^{\dagger} \mathbin{\circ} N=a\,\mathrm{id}_A+b\,\mathrm{Tr}[\cdot]\,I_d$ for some constants $a,b\ge 0$, where $N^{\dagger}$ denotes the Hilbert-Schmidt adjoint of $N$, the quantity $\upsilon_2(N)$ is multiplicative under tensor powers. Examples of channels satisfying this criterion include the transpose-depolarizing channel, the depolarizing channel, and their respective complementary channels. Furthermore, we show that, for every completely positive map $\Omega$, multiplicativity of $\upsilon_p(\Omega)$ implies multiplicativity for its complementary map. This yields the corresponding additivity statements for the associated R\'enyi-2 entanglement of purification.
arXiv:2605.15581v1 Announce Type: new Abstract: LLM-based root cause analysis (RCA) agents have recently emerged as a promising paradigm for incident diagnosis in microservice AIOps. However, their reliability remains fragile: an error in early evidence collection, hypothesis formulation, or causal analysis can propagate through the reasoning trace and eventually corrupt the final diagnosis. In this paper, we present \textbf{STAR}, a \emph{Stage-attributed Triage and Repair} framework for repairing erroneous RCA traces. STAR explicitly decomposes an RCA workflow into four structured stages, namely \emph{Evidence Package} (EP), \emph{Hypothesis Set} (HS), \emph{Analysis Structure} (AS), and \emph{Decision Report} (DR), and treats agent failure as a stage-localizable reasoning bug rather than a monolithic end-to-end error. Built on top of LangGraph, STAR performs stage-wise auditing, budget-aware \emph{Fast/Slow Routing}, \emph{decisive stage localization via counterfactual candidate evaluation}, and stage-specific patch-and-replay repair. We evaluate STAR on a public large-scale benchmark and a real-world production dataset, using two RCA agent workflows and three foundation models. Experimental results show that STAR consistently improves both root cause localization and fault type classification over strong baselines. Moreover, STAR identifies the decisive faulty stage with high accuracy, repairs most initially incorrect traces within one or two replay rounds, and benefits substantially from both Fast/Slow Routing and counterfactual stage evaluation. These results suggest that explicitly modeling \emph{where} an RCA agent fails is an effective path toward reliable, debuggable, and self-repairing agentic RCA systems.
arXiv:2605.12667v2 Announce Type: replace Abstract: The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form question answering and open-ended instruction following. These domains often rely on LLM based auto-raters to provide granular, multi-tier discrete rewards (e.g., 1-10 rubrics) that are inherently stochastic due to prompt sensitivity and sampling randomness. We empirically verify the stochasticity of auto-raters that can propagate and corrupt standard advantage estimators like GRPO and MaxRL, as a noisy reward samples can skew normalization statistics and degrade the global learning signal. Empirically, sampling more rewards and taking majority voting may reduce the noise and improve performance, but this approach is computationally expensive. To address this bottleneck, we introduce $\textbf{O}$rdinal $\textbf{D}$ecomposition for $\textbf{R}$obust $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{ODRPO}$), a framework that structurally isolates evaluation noise by decomposing discrete rewards into a sequence of ordinal binary indicators. By independently computing and accumulating advantages across these progressively challenging success thresholds, ODRPO prevents outlier evaluations from corrupting the global update while establishing an implicit, variance-aware learning curriculum. Empirically, ODRPO achieves robust performance on Qwen2.5-7B and Qwen3-4B models, outperforming baselines with relative improvements of upto 14.8% on FACTS-grounding-v2 and 7.5% on Alpaca-Evals. Critically, these gains are achieved with negligible training-time overhead, as ODRPO requires no additional compute per step compared to standard estimators. Supported by theoretical analysis confirming its optimization stability, ODRPO provides a scalable and robust framework for aligning models within the noisy, discrete evaluation landscape of modern RLAIF.
arXiv:2510.02453v3 Announce Type: replace Abstract: Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting. We introduce Advisor Models, a method to train small open-weight models to generate dynamic, per-instance natural language advice that improves the capabilities of black-box frontier models. Advisor Models improve GPT-5.2's performance on RuleArena (Taxes) by 27.4%, reduce Gemini 3 Pro's steps taken in SWE agent tasks by 24.6%, and outperform static prompt optimizers in personalizing GPT-5 to user preferences (85-100% vs. 40-60%). We also find that advisors are transferable: an advisor trained with a low-cost student model still transfers improvements to a frontier model. Moreover, Advisor Models are robust: we observe no degradation on other benchmarks than the pipeline is trained on. Our method shows how to perform parametric optimization for black-box frontier models in a practical and cost-effective way.
arXiv:2605.15556v1 Announce Type: new Abstract: Large language models (LLMs) have evolved AI assistants into autonomous reasoning engines that maintain context, invoke tools, and pursue long-horizon tasks. This has spurred Agent Operating Systems (Agent OS) as kernel-like layers for lifecycle management, memory, scheduling, and access control. Yet most designs remain agent-centric, treating the OS as a single-host runtime for internal reasoning and tool use, leaving open how autonomous actions integrate with distributed, collaborative, permission-sensitive workflows. TopoClaw is an open-source, human-centric, topology-aware Agent OS modeling the user's ecosystem as two coupled structures: a physical device topology of heterogeneous surfaces and a social relationship topology of shared spaces, teams, and delegated roles. It unifies device operation, messaging, and skills around accountable cross-boundary execution, with three core contributions: (1) cross-device action placement, decoupling intent from actuation and routing distributed actions across the device cluster based on hardware affordances and user context; (2) cross-user identity attribution, treating agents as socially situated "Digital Twins" that coordinate in multi-user spaces while preserving provenance, role-aware permissions, and human accountability; (3) cross-context authority governance, pairing broad capability with distributed, context-aware policy enforcement across physical and social trust boundaries to bound proactive autonomy at the OS layer. This report presents TopoClaw as an engineering-oriented reference architecture, covering its design principles, runtime, cross-device execution, collaboration mechanisms, security model, and deployment outlook.
arXiv:2505.11708v3 Announce Type: replace Abstract: Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain opaque, hindering trust, debugging, and defensive preparedness. In high-stakes cybersecurity contexts, explainability is essential for understanding how adversarial strategies are formed and evolve over time. In this paper, we propose a unified, multi-layer explainability framework for RL-based attacker agents that reveals both strategic (Markov Decision Process (MDP)-level) and tactical (policy-level) reasoning. At the MDP-level, we model cyberattacks as a Partially Observable Markov Decision Process (POMDP) to expose exploration-exploitation dynamics and phase-aware behavioural shifts. At the policy-level, we analyse the temporal evolution of Q-values and use Prioritised Experience Replay (PER) to surface critical learning transitions and evolving action preferences. Evaluated across CyberBattleSim environments of increasing complexity, our framework offers interpretable insights into agent behaviour at scale. Unlike previous explainable RL methods, which are {predominantly} post-hoc, domain-specific, or limited in depth, our approach is both agent- and environment-agnostic, {supporting use cases such as red-team simulation, RL policy debugging, phase-aware threat modelling and anticipatory defence planning.} By transforming black-box learning into actionable behavioural intelligence, our framework enables both defenders and developers to better anticipate, analyse, and respond to autonomous cyber threats.
arXiv:2504.21850v3 Announce Type: replace Abstract: Visual instruction tuning (VIT) datasets have grown rapidly in scale, yet the informativeness of individual training samples has largely been overlooked. Recent dataset selection methods have shown that a small fraction of such datasets enriched with informative samples can lead to efficient finetuning of Multimodal Large Language Models. In this work, we explore the impact of sample complexity on informative data curation and introduce COMPACT (COMPositional Atomic-to-complex Visual Compositional Tuning), a compositional VIT data recipe that scales training sample complexity by combining multiple atomic visual capabilities in a single training example. Concretely, we synthesize rich and informative text questions for each image, allowing us to significantly reduce the number of training examples required for effective VIT. COMPACT demonstrates superior data efficiency compared to existing data reduction methods. When applied to the LLaVA-665K VIT dataset, COMPACT reduces the data budget by 90% while still achieving 100.2% of the full VIT performance (compared to only 97.5% by the state-of-the-art method) across eight multimodal benchmarks. Furthermore, training on the COMPACT data outperforms training on the full-scale VIT data on particularly complex benchmarks such as MM-Vet (+8.6%) and MMStar (+2.9%). COMPACT offers a scalable and efficient synthetic data generation recipe to improve on vision-language tasks.
arXiv:2512.16933v4 Announce Type: replace Abstract: The dynamics of a degenerate spherically symmetric wormhole in a vacuum is considered. An extension of the equivalence principle to matter free objects that are the source of a gravitational field is proposed. Using the Klinkhamer metric as an example, it is shown that a degenerate wormhole is precisely such an object. Application of the extended equivalence principle reduces the radial dynamics of the Klinkhamer wormhole to the dynamics of the radial fall of a test particle in a Schwarzschild gravitational field. It is proven that any bound state of the traversable Klinkhamer wormhole eventually collapses into a nontraversable Einstein-Rosen wormhole. An estimate is presented showing that the traversable Klinkhamer wormhole, although nonstationary, is a longlived state.