arXiv:2605.09038v3 Announce Type: replace Abstract: Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain question answering, where broad or copied queries often waste retrieval budget and derail later reasoning. We propose \Ours, a framework that makes query planning explicit through reusable search skills. At each step, the model first selects a skill, then generates a search or answer action conditioned on the selected skill card. The skill inventory itself is not fixed: SearchSkill maintains an evolving SkillBank, expands or refines it from recurrent failure patterns, and reconstructs affected trajectories before supervised training. The resulting two-stage SFT recipe aligns training with the inference-time protocol of skill selection followed by skill-grounded execution. Across open-source and closed-source models, SearchSkill improves exact match on knowledge-intensive QA benchmarks and yields better retrieval behavior, including fewer copied first queries, more atomic hop-focused queries, and more correct answers within a small search budget. These results suggest that explicit skill-conditioned query planning is a lightweight alternative to treating search as an undifferentiated action.
Science Journals
t-STEP: An interpretable model for Total Electron Content predictions and irregularities estimations
arXiv:2606.29644v1 Announce Type: new Abstract: Earth system infrastructures relying on satellite-based technologies, such as Global Positioning System (GPS) communications, are affected by ionospheric Total Electron Content (TEC) gradients. Modeling these gradients under physical constraints remains challenging due to their dynamic and transient nature. While existing machine learning (ML) models can predict hourly TEC variations, it remains unclear whether their temporal resolution is sufficient to preserve small-scale TEC irregularities within predicted signals. To address this gap, we introduce an interpretable ML-based model, t-STEP, designed to predict TEC at a 30-second resolution and estimate irregularity signatures from the modeled signals. This high cadence enables the derivation of Rate of TEC changes (ROT) and the ROT Index (ROTI) as diagnostic indicators of ionospheric variability. The model is developed using GPS observations from solar cycle 24 at a station located at 5.49{\deg}S, 47.49{\deg}W. A multi-metric evaluation framework, including dynamic time warping, is used for robustness assessment, while SHAP (SHapley Additive exPlanations) provides insight into feature contributions. The 30-second TEC predictions achieve 91% accuracy with a mean absolute error (MAE) of 4.38 TECU during high solar activity (2015). Compared with the International Reference Ionosphere (IRI-2020), the hourly model improves accuracy by 35%, reduces absolute errors by 57%, and increases prediction skill by 54%. More importantly, the 30-second model captures TEC irregularity dynamics and morphologies during geomagnetic storms of different intensities, outperforming an attention-based Long Short-Term Memory model under the same experimental conditions. This study demonstrates the potential of a single TEC prediction framework for scalable irregularity monitoring without requiring separate models for individual transient events.
arXiv:2605.01971v2 Announce Type: replace Abstract: Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic biases present in the training data. Existing fairness-aware methods address this by redesigning the self-supervised objective itself, limiting portability across the rapidly evolving landscape of self-supervised learning (SSL) frameworks. We propose ProtoFair, a fairness-aware contrastive loss designed to work alongside existing SSL objectives without modifying them. ProtoFair leverages unsupervised prototype clustering to identify pseudo-counterfactual pairs: samples sharing the same cluster assignment but belonging to different sensitive groups. By pulling these content-matched, cross-group samples together in the embedding space, ProtoFair encourages the encoder to learn representations that are invariant to the sensitive attribute. The method requires only sensitive attribute annotations, no target labels, and integrates seamlessly with both SimCLR and SupCon. Experiments on CelebA and UTKFace demonstrate consistent fairness improvements while maintaining competitive accuracy.
arXiv:2604.19191v2 Announce Type: replace Abstract: Deploying AI-based anomaly detection across diverse clinical imaging settings remains challenging because most existing methods rely on modality-specific architectures, anatomical priors, or extensive retraining, limiting their use as general-purpose screening tools. One-class classification (OCC) offers a label-efficient alternative by training exclusively on normal data, but conventional two-stage pipelines fit a density estimator directly on raw pretrained embeddings, leaving substantial discriminative structure in the latent space unexploited. We introduce a training-free, modality-agnostic framework that inserts an explicit manifold-refinement stage between feature extraction and anomaly scoring. Empirical density weights, estimated via a UMAP-derived neighborhood graph, guide an iterative shift of embeddings toward locally dense regions, compacting normal samples, leaving anomalies relatively isolated prior to Gaussian density estimation and Mahalanobis-based scoring. This refinement introduces no additional trainable parameters and no architectural modification, allowing it to be layered onto any pretrained encoder. Evaluated on the MedIAnomaly benchmark across seven datasets spanning five imaging modalities (X-ray, MRI, fundus, dermatoscopy, histopathology), the framework achieves the best AUC on four datasets and the best Average Precision on five datasets among methods evaluated in the benchmark, outperforming specialized reconstruction and diffusion-based methods with a single fixed hyperparameter configuration across all modalities. These results demonstrate that meaningful gains can be achieved through post-hoc geometric refinement of existing representations rather than bespoke encoders, offering a practical and scalable AI screening framework for real-world, multi-modality clinical workflows where retraining and abnormal-case annotation are costly or infeasible.
arXiv:2605.24896v3 Announce Type: replace Abstract: Seasonal forecasting of summer rainfall in East Asia remains a grand challenge, as predictability at 3 to 6 month lead times is constrained by the spring predictability barrier, weak large-scale signals, and localized nonlinear convective extremes. We address this challenge with CAPES, which integrates a kilometer-resolution coupled regional model with atmosphere, land, and ocean components and a data-driven AI seasonal forecasting system. At 15 km resolution, the fused workflow combines 174 numerical members from varying start times, physics schemes, and parameter perturbations with 1,600 AI members generated from initial and physical perturbations. Using the full LineShine system, CAPES completes ten annual 1,774-member hindcasts for 2016 to 2025 within 14.6 hours, improving the mean prediction score from ECMWF's 71.8 to 75.9 and delivering a major gain in operational forecasting capability. The 1-km configuration further enables fine-scale typhoon simulation and establishes the feasibility of kilometer-scale fused ensemble forecasting on a one-week timescale.
arXiv:2605.25044v2 Announce Type: replace Abstract: Learning universal policies from cross-embodied data remains a fundamental challenge in robotics. Although Vision-Language-Action (VLA) models are pre-trained on large and diverse datasets, they typically rely on embodiment-specific fine-tuning to achieve strong performance in downstream tasks. This requirement severely limits their generalization capability and restricts knowledge transfer across embodiments performing similar tasks. To overcome these limitations, we focus on cross-embodied settings with shared robotic bases and heterogeneous end-effectors, and propose X-DiffVLA, a diffusion-based VLA model featuring a unified cross-embodied action head. X-DiffVLA can leverage the generative strengths of diffusion models to capture both the diversity and latent correlations in cross-embodied datasets. Specifically, we introduce Embodiment Forcing, a classifier-free guidance technique to implicitly steer action generation toward embodiment-specific functional components, capturing fine-grained structural nuances without explicit supervision. In addition, a Morphological Tree Diffusion approach is designed to strengthen behavioral correlations across diverse end-effectors, maximizing the transferability of heterogeneous demonstrations. Experimental results across RoboCasa and Isaac Gym, covering different embodiments from grippers to dexterous hands, show that X-DiffVLA achieves state-of-the-art performance, with improvements of 15.3% and 12.5%, respectively. Real-world evaluations further validate the robustness of the proposed framework and its effectiveness in scalable cross-embodied policy learning.
arXiv:2605.25063v2 Announce Type: replace Abstract: Scan-order design in laser directed energy deposition (LDED) is a delayed, path-dependent thermo-mechanical decision problem, because sequence quality becomes observable only after the complete deposition and cooling cycle. This work formulates LDED scan-order optimisation as a finite-horizon, permutation-constrained reinforcement-learning problem and develops a bilevel finite-element-teacher-labelled AI workflow. A surrogate-assisted teacher-guided optimisation loop learns the Abaqus-labelled response landscape and provides a tractable terminal-reward environment for policy training. A frozen Maskable Proximal Policy Optimization (MaskablePPO) policy is then used to generate legal scan-order candidates, which are independently validated through Abaqus thermo-mechanical simulations. The results show bounded, N-dependent policy-generation value rather than record-level dominance over the mature surrogate-assisted optimiser. The strongest scan orders are obtained by the teacher-guided surrogate loop, whereas PPO autonomously reaches competitive regions of the native response landscape, with stronger rank concentration at smaller track counts and a clear reliability boundary at longer horizons. The teacher-labelled landscape further supports a physically gated lexicographic reward hierarchy in which warpage admissibility is the primary constraint, plastic strain acts as a safety filter and residual-stress-related improvement is pursued conditionally within the admissible region. Validated sequences also reveal an interpretable scale-separated ordering tendency that combines global spatial dispersion with local structured grouping. This workflow provides a route from fixed scan-rule selection toward finite-element-teacher-validated policy generation, while preserving independent finite-element validation as the final physical gate.
arXiv:2605.25253v2 Announce Type: replace Abstract: Higher-dimensional automata (HDA) are a model of concurrency that models simultaneous execution of events using higher dimensional cells. HDA recognize languages of pomsets, a generalization of finite words whose letters are partially ordered. We prove a new algebraic characterization of HDA languages: a language of pomsets is regular if and only if it is the inverse image of a functor from the category of pomsets into a finite category. Furthermore, the language is definable in first-order logic exactly when it is recognized by an aperiodic category, generalizing the McNaughton-Papert theorem to HDA languages. We also investigate a notion of counter-free HDA, and show that if a language is accepted by a counter-free HDA, it must be definable in first-order logic. The converse, however, is still open.
arXiv:2604.12211v2 Announce Type: replace Abstract: Ollivier-Ricci curvature (ORC), defined via the Wasserstein distance that captures rich geometric information, has received growing attention in both theory and applications. However, the high computational cost of Wasserstein distance evaluation has significantly limited the broader practical use of ORC. To alleviate this issue, previous work introduced a computationally efficient lower bound as a proxy for ORC based on 1-hop random walks, but this approach empirically exhibits large gaps from the exact ORC. In this paper, we establish a substantially tighter lower bound for ORC than the existing lower bound, while retaining much lower computational cost than exact ORC computation, with practical speedups of tens of times. Moreover, our bound is not restricted to 1-hop random walks, but also applies to k-hop random walks (k > 1). Experiments on several fundamental graph structures demonstrate the effectiveness of our bound in terms of both approximation accuracy and computational efficiency.
arXiv:2605.09076v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also become a source of vulnerability, as unreliable or Byzantine agents may sway neighboring agents toward incorrect conclusions and degrade overall system performance. Existing methods rely on leader-based coordination or self-reported confidence, both of which are susceptible to adversarial manipulation. We study decentralized LLM multi-agent systems (LLM-MAS) and propose Self-Anchored Consensus (SAC), a fully decentralized iterative filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs. We present $(F{+}1)$-robustness conditions for the communication graph that ensure honest agents preserve and propagate reliable information despite Byzantine influence. Experiments on mathematical and commonsense reasoning benchmarks show that SAC effectively suppresses Byzantine influence and consistently improves performance across diverse communication topologies, whereas prior methods degrade under adversarial conditions.
arXiv:2604.14603v2 Announce Type: replace Abstract: The fundamental limit of natural signal compression has traditionally been characterized by classical rate-distortion (RD) theory through the tradeoff between coding rate and reconstruction distortion, while the rate-distortion-perception (RDP) framework introduces a divergence-based measure of perceptual quality as a modeling principle, leaving its theoretical origin unclear. In this paper, motivated by a synonymity-based semantic information perspective, we reformulate perceptual reconstruction as recovering any admissible sample within an ideal synonymous set (synset) associated with the source, rather than the source sample itself, and establish a synonymous source coding architecture. On this basis, we develop a synonymous variational inference (SVI) analysis framework with a synonymous variational lower bound (SVLBO) for tractable analysis of synset-oriented compression. Within this framework, we establish a synonymity-perception consistency principle, showing that optimal identification of semantic information is theoretically consistent with perceptual optimization. Based on this result, we further derive a tight-bound synonymous source coding rate characterization and show that its Jensen-limit relaxation leads to a synonymous rate-distortion-perception form for practical optimization. These analytical results show that the distributional divergence term arises naturally from the synset-based reconstruction objective, clarify its compatibility with existing RDP formulations and classical RD theory, and suggest the potential advantages of synonymous source coding.
arXiv:2604.15835v3 Announce Type: replace Abstract: Rain introduces broadband and frequency-selective attenuation in wideband terahertz (THz) links, making it necessary to identify a compact spectral descriptor that captures how the dominant loss region evolves with rainfall conditions. This article investigates the peak-frequency behavior of rain attenuation by combining Mie theory calculations with one separable laboratory Gaussian drop-size distribution (DSD) and eight outdoor empirical DSD models whose spectral shapes vary with rainfall rate. The analysis compares total loss, absorption, and scattering components, examines the roles of the characteristic DSD scale and representative drop size statistics, and evaluates the effect of temperature on the peak location. The results show that, unlike the fixed-shape laboratory case where the peak frequency remains unchanged with rainfall rate, all outdoor empirical DSD models exhibit a monotonic migration of the attenuation peak toward lower frequencies as rainfall rate increases. This migration follows a quasi-exact inverse scaling with the rainfall-dependent DSD characteristic scale, follows a family-specific asymptotic power law in rainfall rate, and is governed mainly by characteristic drop size, while fixed-temperature dielectric dispersion contributes only secondary corrections in the broad-peak, low-rainfall regime.
arXiv:2604.16325v3 Announce Type: replace Abstract: Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges. Existing Transformer-based methods capture temporal correlations through attention mechanisms but suffer from quadratic computational cost, while state-space models like Mamba achieve efficient long-context modeling yet lack explicit temporal pattern recognition. Therefore we introduce UniMamba, a unified spatial-temporal forecasting framework that integrates efficient state-space dynamics with attention-based dependency learning. UniMamba employs a Mamba Variate-Channel Encoding Layer enhanced with FFT-Laplace Transform and TCN to capture global temporal dependencies, and a Spatial Temporal Attention Layer to jointly model inter-variate correlations and temporal evolution. A Feedforward Temporal Dynamics Layer further fuses continuous and discrete contexts for accurate forecasting. Comprehensive experiments on eight public benchmark datasets demonstrate that UniMamba consistently outperforms state-of-the-art forecasting models in both forecasting accuracy and computational efficiency, establishing a scalable and robust solution for long-sequence multivariate time-series prediction.
arXiv:2604.17157v2 Announce Type: replace Abstract: Gravitational spectroscopy tests the coupling of gravity to matter by measuring gravitationally induced frequency shifts of quantum transitions. While modern optical clocks probe the gravitational response of electronic transitions with extraordinary precision, tests in the nuclear sector have not progressed since the M\"ossbauer measurements of the gravitational redshift by Pound and Rebka. Here we introduce a new approach to nuclear gravitational spectroscopy based on phase-sensitive heterodyne interferometry of time-resolved nuclear resonant scattering of synchrotron radiation. In this scheme the gravitational redshift appears as a slowly accumulating phase drift of a delayed heterodyne beat signal, converting nuclear gravitational spectroscopy from energy-domain detection to time-domain interferometry. A Fisher-information analysis supported by Monte Carlo simulations and experimentally confirmed photon count rates shows that the nuclear gravitational redshift of $^{57}$Fe can be detected within hours on a few-meter-scale vertical baseline, with percent-level precision on deviations from general relativity becoming accessible on day-scale timescales. The method thus establishes an experimentally realistic and scalable platform for precision tests of gravitational coupling to nuclear structure.
arXiv:2604.19224v2 Announce Type: replace Abstract: Automatically generating bug reproduction tests (BRT) from issue descriptions is crucial for software maintenance. LLM-based approaches have shown great potential for this task. Their effectiveness heavily relies on retrieving high-quality context from the codebase. The retrieval phase of existing approaches relies on either traditional methods like BM25 or LLM-driven strategies. LLM-based retrieval strategies typically equip an LLM with tools to autonomously explore the repository or select the most relevant files and code snippets from a provided list as context. However, these retrieval methods suffer from three key limitations: 1) They often employ a unified strategy for retrieving both source code and test cases, overlooking their distinct retrieval requirements. 2) They focus solely on semantic similarity while ignoring function call relationships, leading to irrelevant context. 3) The retrieval lacks a feedback loop from the generation phase, preventing it from refining the context based on execution results. These limitations collectively result in low-quality context, thereby hindering the accuracy of bug reproduction. To address these challenges, we propose iCoRe, an iterative, correlation-aware context retrieval approach explicitly aware of three key correlations: 1) between source code and test cases, which requires differentiated retrieval, 2) between textual semantics and function call structures for accurate relevance assessment, and 3) between the retrieval and generation phases, which enables iterative feedback and refinement. To evaluate iCoRe, we integrate it with an LLM-based BRT generator and conduct a comprehensive evaluation on the SWT-bench Lite and TDD-bench Verified benchmarks. Experimental results show that our method achieves a Fail-to-Pass rate of 42.0% and 52.8% respectively, representing 19.7%-31.7% relative improvements over existing retrieval methods.
arXiv:2605.26343v2 Announce Type: replace Abstract: Mechanistic interpretability seeks to explain a model's behaviour by finding its circuit: the sparse subgraph of the model's computation that is causally responsible for it. Automated methods have made this search systematic, but each one starts afresh for every behaviour, and the effort spent finding one circuit does nothing for the next. Circuit discovery has thus been automated, but not amortised. We ask whether circuit discovery can itself be learned. We frame it as a sequential decision problem over the computation graph of GPT-2 small, in which a policy removes edges until it reaches a compact subgraph that preserves the behaviour, guided by a faithfulness reward defined through causal intervention. A single policy trained across twelve behaviours recovers a faithful circuit for each, and once frozen it transfers to behaviours it never saw during training, recovering their known circuits without further search. A short warm-start improves these transferred circuits, returning far smaller ones than training from scratch. While the learned policy does not match a per-behaviour search on circuit size or cost, it shows that circuit discovery is a learnable, transferable procedure rather than a search repeated for every behaviour.
arXiv:2605.26755v3 Announce Type: replace Abstract: Multilingual fact verification requires evidence that is both relevant and sufficiently complete for reliable factuality prediction. However, existing systems often rely on search snippets, sentence-level evidence, or locally segmented passages, which can miss decisive context and produce fragmented evidence. To overcome these limitations, we propose SEEK, a Semantic Evidence Extraction with an adaptive chunKing framework that constructs coherent evidence chunks from full fact-checking articles by identifying semantic topic transitions and preserving local verification context. The constructed chunks are encoded using a multilingual encoder and then multilingual LLMs are finetuned using LoRA adapter for veracity prediction. Experiments on X-FACT and RU22Fact show that SEEK improves macro-f1 by up to 10% over semantic chunking, 19% over sentence chunking, and 20% over search-snippet baselines. Evidence completeness and significance analyses further show that SEEK preserves richer verification context and enables more reliable multilingual fact-checking.
arXiv:2605.26790v3 Announce Type: replace Abstract: Low-thrust trajectory design relies heavily on repeated evaluations of fuel consumption and transfer feasibility, which require expensive optimal control solutions. In this work, we show these quantities can be accurately approximated by machine learning surrogates, enabling fast and scalable evaluation across a wide range of scenarios. By increasing both dataset size and model capacity, we observe that low-thrust trajectory optimization follows a scaling law, with performance improving linearly with the logarithm of training data and network parameters, and no evidence of saturation within the explored regime. Guided by this observation, we construct a large-scale dataset using the proposed homotopy-ray strategy tailored to mission design requirements. A key is the introduction of a self-similar transformation, which allows generalization across semi-major axes, inclinations, and central bodies avoiding retraining. As a result, the same neural approximator can be applied to diverse orbital environments and mission classes. The proposed models accurately predict optimal fuel consumption and minimum transfer time for single- and multi-revolution transfers. Their performance and generalization are demonstrated on a public dataset, a multi-asteroid flyby problem from the Global Trajectory Optimization Competition, and an asteroid rendezvous mission design. The models and datasets are released as open-source to support the space community.
arXiv:2605.13057v2 Announce Type: replace Abstract: Ultrasound for microstructure characterisation is increasingly studied and is often assessed through inversion performance. However, the framework is fundamentally constrained by the information content available in the measured response. Hence, this work examines identifiability directly by analysing the geometry of the forward operator in both a canonical pulse-echo model and a stochastic surrogate microstructure. For the canonical model, a closed-form sensitivity analysis reveals information limits arising from parameter coupling, dimensional restriction, and interface-driven saturation. For the surrogate microstructures represented by Gaussian random fields, the forward map from correlation length $D$ and texture-coherence parameter $T$ to the attenuation and velocity observables remains structurally full rank. However, the sensitivity geometry is strongly anisotropic, with uneven parameter influence across the observable space. When intrinsic microstructural variability is incorporated, practical identifiability is further reduced. A variance-weighted Fisher framework shows that recoverability is governed by the balance between sensitivity magnitude and stochastic variability, rather than by structural rank alone. Inversion results confirm this behaviour: single observables produce elongated and weakly constrained objective landscapes, whereas combined observables improve conditioning through complementary sensitivities. These results show that, within the feature-level framework considered here, identifiability limits are governed primarily by forward-map structure and intrinsic variability, with direct implications for observable selection and measurement design.
arXiv:2605.27792v2 Announce Type: replace Abstract: Atmospheric gusts expose wall-bounded turbulence to severe unsteady forcing, triggering complex non-equilibrium dynamics and extreme aerodynamic loads. In this study, direct numerical simulations are performed to investigate the spatiotemporal modulation of turbulent structures and the triggering mechanisms of near-wall extreme events under Gaussian-type transient forcing. The results reveal that high-amplitude gusts inject energy primarily into the streamwise velocity component, inducing a pronounced non-equilibrium phase lag during turbulent energy redistribution. This process produces hysteresis in wall friction and extends the relaxation time. Spectral and continuous wavelet analyses demonstrate that intense gust forcing suppresses high-frequency random fluctuations and reorganizes turbulent kinetic energy into low-frequency coherent structures. The characteristic frequency of these energetic structures locks onto the gust driving frequency, with a relative deviation of only $2.4\%$. Furthermore, the occurrence probability of extreme near-wall events, including extreme positive (EP) wall-shear-stress events and rare backflow (BF) events, increases by up to an order of magnitude under severe forcing. Using a two-step conditional averaging technique, we demonstrate that BF events are actively driven by intense, localized adverse pressure gradients and energetic ejections, which promote spanwise vortex roll-up in the buffer layer. By contrast, EP events are governed by energetic sweeps of high-speed fluid that compress intense spanwise vorticity into the immediate vicinity of the wall. These findings provide physical insights into non-equilibrium energy transfer and offer theoretical guidance for load alleviation and robust flow control of unmanned aerial vehicles operating in unsteady atmospheric environments.
arXiv:2605.28092v2 Announce Type: replace Abstract: Signal Temporal Logic (STL), has recently seen extensive development, owing to its rich expressivenes for autonomous planning and control. Nevertheless, existing verification and control synthesis methods are limited with respect to the complexity and degree of nesting of the formulae. In this work, we propose a novel approach to STL based on an operator acting on reachability value functions. This constitutes a new theoretical framework for handling complex multi-nested formulae while at the same time providing tools for on-line control synthesis. In contrast to focusing on the design of STL-based reachability (or control barrier) functions, we develop operator-based nesting rules directly. Our method's expressiveness is demonstrated both theoretically, where necessary and sufficient conditions for STL formula satisfaction are extracted, as well as in simulations with complex fragments.
arXiv:2605.28512v2 Announce Type: replace Abstract: Self-evolving scientific agents capable of conquering the hard tail of formal mathematics require Compositional Learning Behaviours (CLBs) -- the capacity to ground and recombine novel symbolic structures in context, beyond mere recombination of prelearned atoms. We propose S2B-LM, an adaptation of the CLB-evaluating Symbolic Behaviour Benchmark that removes numerical processing as a confound and adds chain-of-thought scaffolding to elicit rather than merely probe latent CLB competency. Cross-evaluating ten Lean~4 theorem provers on CLB competency in S2B-LM and miniF2F whole-proof performance, we find correlational and causal evidence of our claim: First, a necessary-condition analysis via quadrant test yields $p=0.004$, with model scale being ruled out as a confound. Second, extracting a CLB-encoding activation direction from DeepSeek-Prover-V2-7B using S2B-LM traces via Contrastive Activation Addition and applying it during miniF2F whole-proof generation on the AIME subset, CLB suppression collapses solve rate from $32.3\%$ to $2.9\%$, without loss of coherence, while suppressing a random activation direction of equal magnitude leaves it at $31.9\%$. Together, these results show that CLB competency is necessary but not sufficient for the hard tail of formal mathematical verification.
arXiv:2605.28863v2 Announce Type: replace Abstract: Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study these challenges in Big 2, a four-player imperfect-information card game. We develop a self-play RL framework for Big 2 that enables controlled comparisons between policy-gradient and value-approximating agents. Under a common environment, input representation, training budget, and evaluation protocol, PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against random, greedy, and heuristic Big 2 opponents. We further find that moderate entropy regularization improves PPO by preventing the policy from becoming overly deterministic, and that current-policy self-play provides a stronger finite-budget curriculum than checkpoint self-play or fixed-opponent training. Together, these results show that Big 2 is a useful controlled setting for studying deep RL under imperfect information, multiplayer interaction, delayed rewards, and variable action sets.
arXiv:2605.29032v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably exploit minor model inaccuracies, leading to simulator exploitation and a reality gap where policies succeed in simulation but fail in the real world. We propose that the objective for learning simulators should be strategic robustness rather than predictive accuracy, and formulate this as a zero-sum minimax game between a model player and an adversarial policy player. We provide a comprehensive theoretical analysis: (1) an online learning guarantee showing the game is learnable with sublinear regret bounds; (2) a tractable critic-based simplification bounding the global policy-value gap by the local critic's loss; and (3) an Error-MDP duality, proving that finding the worst-case policy is formally dual to a standard RL problem where the reward is the one-step critic error. This duality yields a provably convergent active data selection algorithm. Experiments on continuous control tasks demonstrate that our approach reduces prediction error in strategically important regions by $1.5$-$2.2\times$ and enables policies trained purely in simulation to match near-optimal real-world performance.
arXiv:2605.29212v2 Announce Type: replace Abstract: Image quality in modern imaging systems emerges from the coupled effects of the sensor, optics, and computational reconstruction. Ultra-thin metalenses offer a path toward substantial miniaturization of optical modules, but practical designs often exhibit pronounced chromatic and field-dependent aberrations that necessitate computational reconstruction. In current metalens pipelines, reconstruction models are commonly trained and selected using distortion-based fidelity objectives, such as PSNR, yet these proxies can be weakly correlated with human preference and downstream utility, reflecting the well-known perception--distortion trade-off. We introduce MetaRanker, a human-in-the-loop active ranking framework that formalizes metalens image quality in terms of semantic interpretability, defined as the degree to which humans can reliably recognize objects and structures in the presence of optical artifacts. MetaRanker combines a probabilistic preference model with uncertainty-aware query selection, and leverages vision--language models to provide lightweight semantic priors. Importantly, these priors are used only to guide the sampling of informative comparisons; human judgments remain the primary supervision signal throughout. Across real-world and synthetic metalens datasets with distinct degradation profiles, MetaRanker produces rankings that align most closely with human assessments, while reducing the number of pairwise annotations required by approximately 80% relative to exhaustive pairwise evaluation. Finally, we show that standard image quality assessment metrics exhibit limited alignment with human interpretability in the metalens domain, positioning MetaRanker as a practical step toward perceptually grounded metalens evaluation and co-design.