arXiv:2605.15410v1 Announce Type: cross Abstract: Adaptive Non-local Observables (ANOs) have shown that making quantum observables dynamic can substantially enlarge the function space of Variational Quantum Algorithms, partly shifting hardware demands from circuit synthesis to measurement design. However, this advantage is accompanied by a steep increase in the number of parameters, as well as the classical optimization cost for varying general Hermitian observables. We propose a special form of ANO that significantly reduces this burden by considering only diagonal observables paired with quantum circuits. Mathematically, this is equivalent to the full ANO of a large parameter space since diagonal matrices are canonical representatives of the ANO space modulo unitary similarity. As a result, Diagonal ANO retains the same capability of full ANO while reducing $k$-local observable complexity from $O(4^k)$ to $O(2^k)$ and lowering the corresponding measurement-side classical computation. In this sense, diagonal ANO preserves much of the benefit of full ANO while encompassing conventional VQCs as a special case.
Science Journals
arXiv:2605.12509v2 Announce Type: replace Abstract: Many real-world phenomena are naturally modeled by graphs and networks. However, classical graph models are often limited to pairwise interactions and may not adequately capture the richer structures that arise in practice. Higher-order graph formalisms extend this framework by incorporating multiway, hierarchical, temporal, multilayer, recursive, and tensor-based interactions, thereby providing more expressive representations of complex systems. This book presents a comprehensive overview of mathematical notions that can be used to model higher-order networks. It surveys foundational concepts, extensional frameworks, and newly introduced formalisms, with an emphasis on their structural principles, relationships, and modeling roles. The aim is to provide a unified perspective that helps readers compare diverse higher-order network models and identify appropriate tools for theoretical study and practical applications. This book is Edition 2.0. It mainly includes the addition of several concepts, as well as corrections and improvements of typographical errors and explanations.
arXiv:2506.06739v3 Announce Type: replace Abstract: Inductive logic programming (ILP) is a form of logical machine learning. The goal is to search a hypothesis space for a hypothesis that generalises training examples and background knowledge. We introduce an approach that 'shrinks' the hypothesis space before an ILP system searches it. Our approach uses background knowledge to find rules that cannot be in an optimal hypothesis regardless of the training examples. For instance, our approach discovers relationships such as "even numbers cannot be odd" and "prime numbers greater than 2 are odd". It then removes violating rules from the hypothesis space. We implement our approach using answer set programming and use it to shrink the hypothesis space of a constraint-based ILP system. Our experiments on multiple domains, including visual reasoning and game playing, show that our approach can substantially reduce learning times whilst maintaining predictive accuracies. For instance, given just 10 seconds of preprocessing time, our approach can reduce learning times from over 10 hours to only 2 seconds.
arXiv:2605.15601v1 Announce Type: new Abstract: Quantum programs often produce probability distributions rather than deterministic outputs, making verification inherently statistical and increasingly costly on real hardware. In practice, developers still frequently rely on testing with fixed shot budgets on simulators, which are simple but time-consuming and poorly suited to noisy backends. What is missing is a verification approach that is both statistically explicit and budget-aware. This paper formulates Bayesian sequential verification as a reference-based Bayesian hypothesis testing workflow in which priors are derived from explicit reference sources, such as finite-shot reference runs or ideal/statevector-based computation, and verification decisions are updated batch by batch as measurement evidence accumulates. This approach is evaluated in Qiskit on two complementary workloads: Bell-state and QAOA-MaxCut. Across both case studies, the results show that Bayesian sequential verification can substantially reduce measurement costs compared to fixed-budget baselines when the success probability of the program exceeds the target threshold. The findings position Bayesian sequential verification as a practical verification workflow for quantum programs. The approach provides a foundation for future quantum continuous-integration pipelines that require reliable, budget-aware pass/fail decisions and motivates validation on real quantum hardware.
arXiv:2605.15784v1 Announce Type: cross Abstract: How many measurements are fundamentally required to capture a signal. Shannon's information theory established the bedrock of this question in 1948, the Nyquist Shannon theorem set the first answer, and compressed sensing (CS) rewrote it in 2006 by reducing the required measurement number to M = O(Klog(N/K)) for a K sparse signal. Here, we propose quantum compressed sensing (QCS), a paradigm that reframes signal acquisition as a unitary quantum evolution. By encoding high dimensional signal information into a single quantum probe state, then introducing domain-alignment evolution,a physically realizable unitary transformation that maps the sparse basis directly onto the measurement basis. QCS executes the support-set search at the quantum level without consuming measurement trials. The logarithmic penalty vanishes, compressing the required measurement number from the classical bound to M =O(K) and reducing reconstruction from ill posed optimization to linear estimation. We experimentally validate QCS using frequency and time domain sparse signals, confirming that the measurement number scales linearly with sparsity and decouples entirely from the signal dimension. Our work provides a physical pathway toward ultimate information acquisition efficiency, with broad implications for sensing, imaging, and communication.
arXiv:2605.15800v1 Announce Type: cross Abstract: The Alliance for Open Media (AOMedia) has developed the AV2 video coding standard to supersede AV1, aiming for substantial compression efficiency gains across diverse media applications. This paper details the quality and performance evaluation methodology defined in the AV2 Common Test Conditions (CTC), which introduces new evaluation methods and content, including convex-hull-based adaptive streaming (AS) configuration, user-generated content (UGC), and extended chroma formats. We present the coding gains of the AV2 (v13.0) against the AV1 baseline. Experimental results show that AV2 achieves significant Bj{\o}ntegaard-Delta Rate (BD-rate) reductions of 29.81\% and 33.79\% for PSNR-YUV and VMAF, respectively, under random access configuration, validating the efficiency of AV2 for next-generation streaming applications.
arXiv:2605.16078v1 Announce Type: cross Abstract: Neural network surrogate models have emerged as a promising approach to model solution fields for a wide variety of boundary value problems encountered in physical modeling. Stochastic problems represent an area of particularly high interest because of the potential to significantly reduce the repeated evaluation of expensive forward models via traditional numerical solvers when conducting parametric analysis. However, many studies found in the literature primarily focus on the ability of neural network surrogate models to represent deterministic samples or mean field solutions and largely overlook surrogate model performance at the tails of the distribution. The present study examines in detail the ability of neural network surrogate models to capture the full distribution of solution fields over the entire probability space, while emphasis is placed at the tails of the distribution. Serving as a canonical problem is the heat conduction equation with a highly stochastic source term, inducing extremely large variation in the thermal solution field. Comparisons are made between a classic feed-forward fully connected network and a Deep Operator Network architecture, using both data-driven and physics-informed loss functions. Results show that the worst-case prediction errors are an order of magnitude larger than the mean field error, highlighting the importance of the outlier samples. The large errors associated with extreme samples result from the networks having to extrapolate beyond the bounds of the training data. A method for identifying these samples is presented along with a discussion of potential approaches to account of their errors. Among the models considered, the fully connected neural network trained using a weak form residual loss performs best in handling these extrapolated inputs, achieving the highest prediction accuracy for the numerically produced datasets.
arXiv:2504.09006v4 Announce Type: replace Abstract: We initiate the study of structured Stackelberg games, a novel form of strategic interaction between a leader and a follower where contextual information can be predictive of the follower's (unknown) type. Motivated by applications such as security games and AI safety, we show how this additional structure can help the leader learn a utility-maximizing policy in both the online and distributional settings. In the online setting, we first prove that standard learning-theoretic measures of complexity do not characterize the difficulty of the leader's learning task. Notably, we find that there exists a learning-theoretic measure of complexity, analogous to the Littlestone dimension in online classification, that tightly characterizes the leader's instance-optimal regret. We term this the Stackelberg-Littlestone dimension, and leverage it to provide a provably optimal online learning algorithm. In the distributional setting, we provide analogous results by showing that two new dimensions control the sample complexity upper- and lower-bound.
arXiv:2605.15618v1 Announce Type: new Abstract: Self-supervised video models are increasingly framed as world models, yet their evaluation remains largely confined to a single top-1 accuracy score on clean benchmarks. This leaves a major gap in comprehending their potential as world models. We present the first systematic study addressing this gap, analyzing four matched-capacity frontier video foundation models, V-JEPA 2.1, V-JEPA 2, VideoPrism, and VideoMAEv2, across five robustness axes relevant to their deployment as video world models: feature discriminability, corruption robustness, fine-grained discrimination, occlusion robustness, and sensitivity to temporal direction. Our evaluations establish that across all five axes, latent-prediction models form a distinct and consistent profile. They degrade more gracefully under pixel corruption, preserve usable class structure rather than mere geometric stability under occlusion, capture fine-grained physical contact cues without reconstructing pixels, and uniquely encode the arrow of time. These advantages can even survive task adaptation: a frozen V-JEPA 2 backbone with a lightweight attentive probe outperforms a fully fine-tuned VideoMAE and a supervised TimeSformer on corruption and occlusion robustness. Our extensive results offer concrete new evidence in favor of latent prediction for robust world modeling.
arXiv:2505.15692v5 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts that fail to capture transferable problem-solving strategies. To address this limitation, we propose **TemplateRL**, a structured template-guided RL framework that augments policy optimization with explicit template guidance. Our approach first constructs a problem-solving template library via MCTS on a small seed set, then seamlessly integrates this high-level structured guidance into RL training. By guiding rollout generation to align with proven template structures, TemplateRL significantly improves high-quality trajectory hit rates while reducing ineffective exploration. This structure-guided design steers the policy toward validated strategic patterns, stabilizing training dynamics, and enhancing RL sampling efficiency. Notably, the explicit template library is interpretable, editable, and supports online updates-enabling continuous updates during both training and inference. Extensive experiments demonstrate that TemplateRL outperforms GRPO by 99% on AIME and 41% on AMC, with superior stability on weak models and remarkable cross-domain generalization, highlighting its potential for broader tasks.
arXiv:2506.23552v2 Announce Type: replace Abstract: The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS) are typically addressed as separate tasks. This paper introduces JAM-Flow, a unified framework to simultaneously synthesize and condition on both facial motion and speech. Our approach leverages flow matching and a novel Multi-Modal Diffusion Transformer (MM-DiT) architecture, integrating specialized Motion-DiT and Audio-DiT modules. These are coupled via selective joint attention layers and incorporate key architectural choices, such as temporally aligned positional embeddings and localized joint attention masking, to enable effective cross-modal interaction while preserving modality-specific strengths. Trained with an inpainting-style objective, JAM-Flow supports a wide array of conditioning inputs-including text, reference audio, and reference motion-facilitating tasks such as synchronized talking head generation from text, audio-driven animation, and much more, within a single, coherent model. JAM-Flow significantly advances multi-modal generative modeling by providing a practical solution for holistic audio-visual synthesis. project page: https://joonghyuk.com/jamflow-web
arXiv:2509.22739v3 Announce Type: replace Abstract: Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often requires manual trial-and-error. While activation steering (AS) promises a cheap, fast, and controllable alternative to the two existing post-training methods, current AS techniques require hand-crafted prompt pairs or labor-intensive feature annotation, making them more inconvenient than the plug-and-play methods such as Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT). We introduce Painless Activation Steering (PAS), a family of fully automated methods that make AS readily usable with any given labeled dataset, with no need for prompt construction, feature labeling, or human intervention. We evaluate PAS on three open-weight models (Llama3.1-8B-Instruct, DeepSeek-R1-Distill-8B, and Nous-Hermes-2) and 18 tasks; we find that PAS reliably improves performance for behavior tasks, but not for intelligence-oriented tasks. The introspective variant (iPAS) delivers the strongest causal steering effects (10.1% on Bias, 5.2% on Morality, and 34.8% on Alignment). We also show PAS delivers additional gains on top of In-Context Learning (ICL) and SFT. PAS constructs a fast, lightweight activation vector that can be cheaply trained, easily stored, and activated at will. Our results provide a characterization of where AS helps, where it fails, and how to deploy it as a practical, automated LM post-training option.
arXiv:2605.15134v2 Announce Type: replace Abstract: Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely large enough to observe the failures that matter. Jones et al. (2025) address this by extrapolating from the largest k failure scores in an evaluation set to predict deployment-scale failure rates. We give a finite-k decomposition of this estimator's forecast error and show that it has a built-in bias toward over-prediction in the typical case, which is the safety-favorable direction. This bias is offset when the evaluation set misses a rare high-failure mode that the deployment set contains, leaving the forecast to under-predict at deployment scale. We propose a fine-tuning objective, the forecastability loss, that addresses this failure mode. In two proof-of-concept experiments, a language-model password game and an RL gridworld, fine-tuning substantially reduces held-out forecast error while preserving primary-task capability and achieving safety similar to that of supervised baselines.
arXiv:2406.14930v5 Announce Type: replace-cross Abstract: The minimization principle $\textsf{MIN}(\triangleleft)$ studied in bounded arithmetic says that a strict linear ordering $\triangleleft$ on any finite interval $[0,\dots,n)$ has the minimal element. We shall prove that bounded arithmetic theory $\textsf{T}^1_2(\triangleleft)$ augmented by instances of the pigeonhole principle for all $\Delta^b_1(\triangleleft)$ formulas does not prove $\textsf{MIN}(\triangleleft)$.
arXiv:2511.07646v2 Announce Type: replace Abstract: This paper studies distributed adaptive estimation over sensor networks with partially unknown source dynamics. We present parallel continuous-time and discrete-time designs in which each node runs a local adaptive observer and exchanges information over a directed graph. For both time scales, we establish stability of the network coupling operators, prove boundedness of all internal signals, and show convergence of each node's estimate to the source despite model uncertainty and disturbances. We further derive input-to-state stability (ISS) bounds that quantify robustness to bounded process noise. A key distinction is that the discrete-time design uses constant adaptive gains and per-step regressor normalization to handle sampling effects, whereas the continuous-time design does not. A unified Lyapunov framework links local observer dynamics with graph topology. Simulations on star, cyclic, and path networks corroborate the analysis, demonstrating accurate tracking, robustness, and scalability with the number of sensing nodes.
arXiv:2511.07720v2 Announce Type: replace Abstract: Robot learning empowers the robot system with human brain-like intelligence to autonomously acquire and adapt skills through experience, enhancing flexibility and adaptability in various environments. Aimed at achieving a similar level of capability in large language models (LLMs) for embodied intelligence, data quality plays a crucial role in training a foundational model with diverse robot skills. In this study, we investigate the collection of data for manipulation tasks using teleoperation devices. Different devices yield varying effects when paired with corresponding controller strategies, including position-based inverse kinematic (IK) control, torque-based inverse dynamic (ID) control, and optimization-based compliant control. Analysis of experimental results suggests the importance of the relationship between teleoperation devices and controllers for real tasks.
arXiv:2605.09231v3 Announce Type: replace Abstract: Deep generative models provide flexible frameworks for modeling complex, structured data such as images, videos, 3D objects, and texts. However, when applied to sequences of human skeletons, standard variational autoencoders (VAEs) often allocate substantial capacity to nuisance factors-such as camera orientation, subject scale, viewpoint, and execution speed-rather than the intrinsic geometry of shapes and their motion. We propose the Elastic Shape - Variational Autoencoder (ES-VAE), a geometry-aware generative model for skeletal trajectories that leverages the transported square-root velocity field (TSRVF) representation on Kendall's shape manifold. This representation inherently removes rigid translations, rotations, and global scaling of shapes, and temporal rate variability of sequences, isolating the underlying shape dynamics. The ES-VAE encoder maps skeletal sequences to a low-dimensional latent space incorporating the Riemannian logarithm map, while the decoder reconstructs sequences using the corresponding exponential map. We demonstrate the effectiveness of ES-VAE on two datasets. First, we analyze skeletal gait cycles to predict clinical mobility scores and classify subjects into healthy and post-stroke groups. Second, we evaluate action recognition on the NTU RGB+D dataset. Across both settings, ES-VAE consistently outperforms standard VAEs and a range of sequence modeling baselines, including temporal convolutional networks, transformers, and graph convolutional networks. More broadly, ES-VAE provides a principled framework for learning generative models of longitudinal data on pose shape manifolds, offering improved latent representation and downstream performance compared to existing deep learning approaches.
arXiv:2511.19931v2 Announce Type: replace Abstract: Cross-domain Sequential Recommendation (CDSR) has been proposed to enrich user-item interactions by incorporating information from various domains. Despite current progress, the imbalance issue and transition issue hinder further development of CDSR. The former one presents a phenomenon that the interactions in one domain dominate the entire behavior, leading to difficulty in capturing the domain-specific features in the other domain. The latter points to the difficulty in capturing users' cross-domain preferences within the mixed interaction sequence, resulting in poor next-item prediction performance for specific domains. With world knowledge and powerful reasoning ability, Large Language Models (LLMs) partially alleviate the above issues by performing as a generator and an encoder. However, current LLMs-enhanced CDSR methods are still under exploration, which fail to recognize the irrelevant noise and rough profiling problems. Thus, to make peace with the aforementioned challenges, we proposed an LLMs Enhanced Cross-domain Sequential Recommendation with Dual-phase Training ({LLM-EDT}). To address the imbalance issue while introducing less irrelevant noise, we first propose the transferable item augmenter to adaptively generate possible cross-domain behaviors for users. Then, to alleviate the transition issue, we introduce a dual-phase training strategy to empower the domain-specific thread with a domain-shared background. As for the rough profiling problem, we devise a domain-aware profiling module to summarize the user's preference in each domain and adaptively aggregate them to generate comprehensive user profiles. The experiments on three public datasets validate the effectiveness of our proposed LLM-EDT. To ease reproducibility, we have released the detailed code online at {https://anonymous.4open.science/r/LLM-EDT-583F}.
arXiv:2512.00417v5 Announce Type: replace Abstract: This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in the uniquely demanding and fast-paced cryptocurrency domain. Unlike general-purpose agent benchmarks for search and prediction, professional crypto analysis presents specific challenges: \emph{extreme time-sensitivity}, \emph{a highly adversarial information environment}, and the critical need to synthesize data from \emph{diverse, specialized sources}, such as on-chain intelligence platforms and real-time Decentralized Finance (DeFi) dashboards. CryptoBench thus serves as a much more challenging and valuable scenario for LLM agent assessment. To address these challenges, we constructed a live, dynamic benchmark featuring 50 questions per month, expertly designed by crypto-native professionals to mirror actual analyst workflows. These tasks are rigorously categorized within a four-quadrant system: Simple Retrieval, Complex Retrieval, Simple Prediction, and Complex Prediction. This granular categorization enables a precise assessment of an LLM agent's foundational data-gathering capabilities alongside its advanced analytical and forecasting skills. Our evaluation of ten LLMs, both directly and within an agentic framework, reveals a performance hierarchy and uncovers a failure mode. We observe a \textit{retrieval-prediction imbalance}, where many leading models, despite being proficient at data retrieval, demonstrate a pronounced weakness in tasks requiring predictive analysis. This highlights a problematic tendency for agents to appear factually grounded while lacking the deeper analytical capabilities to synthesize information.
arXiv:2604.09796v2 Announce Type: replace-cross Abstract: Superconducting qubit fabrication innovations continue to be explored to achieve higher performance. Despite improvements to base layer fabrication and processing, resist-based Josephson junction (JJ) schemes have largely remained unchanged. The polymer mask during deposition causes chemical contamination and limits in situ and ex situ surface preparation, junction materials, and scalability. Here, we demonstrate a resist-free approach to junction fabrication based on etched silicon trenches that is CMOS compatible and easily integrated into existing innovations in qubit base layer fabrication and chemical processing. We fabricate Al-AlOx-Al JJs and qubits using this method, measuring median energy relaxation times up to 184 microseconds. We find minimal contamination at the substrate-metal interface and fluctuations of energy relaxation on a 35 hour timescale that are narrow and normally distributed. The method widens the process window for substrate preparation and new materials platforms.
arXiv:2602.01295v3 Announce Type: replace Abstract: We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity in adversarial regimes. In this work, we propose algorithms HT-FTRL-OM and HT-FTRL-UOB for HTMDPs that achieve Best-of-Both-Worlds (BoBW) guarantees: instance-independent regret in adversarial environments and logarithmic instance-dependent regret in self-bounding (including the stochastic case) environments. For the known transition setting, HT-FTRL-OM applies the Follow-The-Regularized-Leader (FTRL) framework over occupancy measures with novel skipping loss estimators, achieving a $\widetilde{{O}}(T^{1/\alpha})$ regret bound in adversarial regimes and a ${O}(\log T)$ regret in stochastic regimes. Building upon this framework, we develop a novel algorithm HT-FTRL-UOB to tackle the more challenging unknown-transition setting. Under a mild truncative nonnegativity condition on the loss distributions, this algorithm employs a pessimistic skipping loss estimator and achieves a $\widetilde{{O}}(T^{1/\alpha} + \sqrt{T})$ regret in adversarial regimes and a ${O}(\log^2(T))$ regret in stochastic regimes. Our analysis overcomes key barriers through several technical insights, including a local control mechanism for heavy-tailed shifted losses, a new suboptimal-mass propagation principle, and a novel regret decomposition that isolates transition uncertainty from heavy-tailed estimation errors and skipping bias.
arXiv:2602.01970v2 Announce Type: replace Abstract: Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-intensive optimization. Online prompt selection presents a plausible solution by prioritizing informative prompts to improve training efficiency. However, current methods either depend on costly, exact evaluations or construct prompt-specific predictive models lacking generalization across prompts. This study introduces Generalizable Predictive Prompt Selection (GPS), which performs Bayesian inference towards prompt difficulty using a lightweight generative model trained on the shared optimization history. Intermediate-difficulty prioritization and history-anchored diversity are incorporated into the batch acquisition principle to select informative prompt batches. The small predictive model also generalizes at test-time for efficient computational allocation. Experiments across varied reasoning benchmarks indicate GPS's substantial improvements in training efficiency, final performance, and test-time efficiency over superior baseline methods.
arXiv:2602.04759v2 Announce Type: replace Abstract: The last decade has witnessed a rapid advancement of generative AI technology that significantly scaled the accessibility of AI-generated non-consensual intimate images (AIG-NCII), a form of image-based sexual abuse that disproportionately harms and silences women and girls. There is a patchwork of commendable efforts across industry, policy, academia, and civil society to address AIG-NCII. However, these efforts lack a shared, consistent mental model that clearly situates the technologies they target within the context of a large, interconnected, and ever-evolving technological ecosystem. As a result, interventions remain siloed and are difficult to evaluate and compare, leading to a reactive cycle of whack-a-mole. In this paper, we contribute the first comprehensive AIG-NCII technological ecosystem that maps and taxonomizes 11 categories of technologies facilitating the creation, distribution, proliferation and discovery, infrastructural support, and monetization of AIG-NCII. First, we build and visualize the ecosystem through a synthesis of over a hundred primary sources from researchers, journalists, advocates, policymakers, and technologists. Then, we conduct two detailed walkthroughs to demonstrate the usefulness of the ecosystem in 1) making sense of new AIG-NCII harms using a case study of Grok and 2) mapping a clearer tech policy landscape using U.S. federal law and 63 state laws. We conclude with a vision for future AIG-NCII research that refines the edges of the ecosystem, recommending researchers to study critical relationships between technologies and potential ripple effects from different interventions. Our goal is to produce an AIG-NCII technological ecosystem that provides a clear, shared terminology and framework for stakeholders to move into the future of AIG-NCII prevention with clarity and foresight.
arXiv:2602.04909v3 Announce Type: replace Abstract: Direct Preference Optimization (DPO) and related methods align large language models from pairwise preferences by regularizing updates against a fixed reference policy. As the policy drifts, a static reference, however, can become increasingly miscalibrated, leading to distributional mismatch and amplifying spurious preference signals under noisy supervision. Conversely, reference-free variants avoid mismatch but often suffer from unconstrained reward drift. We propose Geometric Anchor Preference Optimization (GAPO), which replaces the fixed reference with a dynamic, geometry-aware anchor: an adversarial local perturbation of the current policy within a small radius that serves as a pessimistic baseline. This anchor enables an adaptive reweighting mechanism, modulating the importance of each preference pair based on its local sensitivity. We further introduce the Anchor Gap, the reward discrepancy between the policy and its anchor, and show under smoothness conditions that it approximates worst-case local margin degradation. Optimizing a logistic objective weighted by this gap downweights geometrically brittle instances while emphasizing robust preference signals. Across diverse noise settings, GAPO consistently improves robustness while matching or improving performance on standard LLM alignment and reasoning benchmarks.
arXiv:2605.15203v1 Announce Type: new Abstract: We introduce Agent4POI, the first POI recommendation framework that generates context-conditioned multimodal representations at recommendation time, rather than relying on static POI embeddings pre-computed independently of context. Existing multimodal systems encode each POI once as a static embedding, a design that precludes reasoning about why the same cafe affords solo work on Monday but group celebration on Friday evening. We formally prove that no pre-computed encoder can satisfy context-sensitive ranking under standard bilinear scoring, motivating inference-time item-side representation. Agent4POI inverts this computation: given a situational context, a four-phase LLM agent generates dynamic, context-specific affordance queries (Phase 1) and executes a five-step cross-modal chain-of-thought over image, review, and metadata evidence (Phase 2). The resulting uncertainty-aware affordance representation is grounded in Gibsonian affordance theory. These cross-modal verdicts form a structured, uncertainty-adjusted affordance representation (Phase 3), which is aligned with user preferences via a semantic caching system for low-latency ranking (Phase 4). On three POI benchmarks and three evaluation configurations (standard, cold-start, context-shift), Agent4POI achieves a 23.2% relative gain over the strongest baseline and degrades by only 7.5% under context-shift versus 16--17\% for the strongest baselines. In cold-start scenarios, Agent4POI outperforms the best content-based baseline by up to 2.4x, whereas ID-based methods fail to generalize.