arXiv:2605.30883v1 Announce Type: new
Abstract: The rise of LLM agents introduces a new threat by enabling planning, coding, and even end-to-end execution of expert-level attack workflows. However, this threat remains underexplored and underestimated since (i) safety alignment prevents LLMs from directly generating harmful instructions, and (ii) most existing jailbreak methods cannot consistently induce agents to execute malicious operations. In this paper, we propose TRACE, a practical agentic jailbreaking framework to further reveal the risks of this threat surface. To conceal the malicious intent, TRACE decomposes a malicious task into multiple subtask sequences under different schemes and selects the sequence with the fewest explicitly harmful subtasks. TRACE then disguises the remaining harmful subtasks as benign-looking instructions by embedding them in task-aware scenarios with related roles, environments, directives, and heuristics. The scenarios are iteratively evolved through well-defined transformation actions, which are sampled by a Q-learning-inspired mechanism, for inducing the agent to execute on the harmful subtasks. Extensive evaluations on AgentHarm and AdvCUA show that TRACE consistently outperforms existing jailbreak baselines across multiple advanced LLM agents, achieving up to 100% bypass rate and 0.73 average success score. We also demonstrate the effectiveness of TRACE in controlled cyberattack instances. Our code and demos are available at https://github.com/ZJU-LLM-Safety/TRACE.git.
Science Journals
arXiv:2605.30873v1 Announce Type: new
Abstract: Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce a monolithic reward model, inevitably averaging out inherently conflicting user preferences (e.g., helpfulness vs. harmlessness). While Variational Preference Learning (VPL) offers a pathway to personalization, adapting it to decentralized settings presents a fundamental challenge: posterior collapse driven by severe local data scarcity and heterogeneity. In this paper, we propose Federated Variational Preference Alignment with Gumbel-Softmax Prior (FedVPA-GP), a framework designed to disentangle diverse preferences without compromising privacy. To stabilize variational inference, we introduce a Federated Mixture Prior that enables clients to leverage the aggregate population distribution as a dynamic prior. Furthermore, we incorporate an Orthogonal Loss that explicitly enforces the separation of preference prototypes in the latent space. Experiments on the HH-RLHF dataset demonstrate that FedVPA-GP significantly outperforms monolithic baselines, successfully disentangling conflicting user intents and enabling dynamic preference switching.
arXiv:2605.30851v1 Announce Type: new
Abstract: Parallel decoding improves generation efficiency by processing multiple decode positions within a single decode forward, but reported speedups conflate algorithmic token utilization with the system cost of executing multiple positions. We isolate the system side by introducing Near-Free Parallelism (NFP), the maximum number of positions executable at near-free latency. Analyzing Dense FFNs, MoE FFNs, and Attention against an idle-compute baseline, we find that NFP is shaped not by memory-bound resource slack alone, but also by implementation-induced kernel-granularity slack. Based on these mechanisms, we establish a Near-Free Parallelism principle that predicts the NFP boundary from hardware balance and implementation granularity. Validation on representative Dense and MoE models -- spanning both diffusion and autoregressive decoding -- shows that the principle accurately predicts practical NFP boundaries, revealing that the standard idle-compute intuition can over-predict by up to 23x -- offering a system-side budget for parallelism selection and model-system co-design.
arXiv:2605.30914v1 Announce Type: new
Abstract: Automated formal verification remains challenging for large language models because data for proof assistants and verification-aware languages is scarce, and correctness depends on satisfying precise machine-checkable specifications rather than producing plausible code. This thesis studies how verifier environments can improve LLM generation of verified programs and proofs through reinforcement learning from verifiable rewards (RLVR) and verifier-guided inference-time search. First, we train open-source models in Dafny with RLVR using Group Relative Policy Optimization (GRPO) and related variants, assembling generated candidates into complete programs and scoring them with compiler and verifier outcomes. Initial experiments on an APPS-derived Dafny dataset increased verified reward from 2.2% to 58.1%, but revealed specification hacking, where models exploit weak formal specifications instead of implementing the intended solutions. After filtering underspecified and vulnerable tasks, multi-turn RLVR on the refined benchmark improves the verified pass rate from 9.7% to 31.1%. Second, we develop a verifier-guided inference scaffold in Lean that treats proof generation as structured search over decomposed subgoals, verifier feedback, diagnostics, and repair. With a fixed base model, the full scaffold with proof reviser improves pass rate on an initial VeriCoding pilot set from 46.2% under direct repair to 69.2%. On the larger VERINA dataset, whole-task decomposition plus proof reviser solves 7 of 42 previously unsolved tasks. We also introduce Dalek-Bench, a repository-scale Lean benchmark derived from the Rust $\texttt{curve25519-dalek}$ verification project; preliminary results remain weak, indicating that stronger progress evaluation and task-specific tool-use policies are still needed.
arXiv:2605.31288v1 Announce Type: new
Abstract: Parameter-dependent dynamical systems that exhibit bifurcations pose significant computational challenges, as traditional continuation methods require repeated, costly simulations across large ranges of parameter values to capture sudden qualitative changes in the solution. In this work, we propose a systematic approach to reconstruct the branches of the entire bifurcation diagram in a single numerical solver leveraging generalized Polynomial Chaos (PC) expansion. By treating the parameter as a random variable, we cast the deterministic parameter-dependent model in a weak stochastic form, and then use a Galerkin projection to recover bifurcation branches globally across the parameter domain without iterative pointwise continuation. We show that the resulting Galerkin system, in the non-uniqueness regime, produces many discrete algebraic roots that naturally split into two classes: highly oscillatory solutions and branch-approximating ones. We develop a rigorous theoretical framework that establishes consistency, proves convergence of the branch-approximating solutions to the true steady states, and guarantees uniqueness of the Galerkin solution under suitable assumptions. Finally, we confirm these theoretical results with numerical experiments on several parameter-dependent ordinary differential equations (ODEs), demonstrating the accuracy and computational efficiency of our single-run framework in capturing complex bifurcation diagrams for both scalar and vector-valued systems.
arXiv:2604.13624v2 Announce Type: replace
Abstract: InGaZnO (IGZO)-channel FeFETs have attracted notable interest thanks to recent advances in endurance, opening up their application space for read-dominated AI memory tiers. This work evaluates the viability of NOR-type IGZO FeFETs for 3D heterogeneous AI memories from a read-centric design-technology co-optimization (DTCO) perspective, spanning on-chip back-end-of-line (BEOL) RAMs and hybrid-bonded memory chiplets, and off-chip, monolithically integrated 3D FeNOR storage-class memories (SCMs). For on-chip BEOL RAMs and memory chiplets, we demonstrate the cross-node bitcell footprint scalability of IGZO FeFETs capable of delivering down to 10-A SRAM-equivalent bitcell area ($\sim$0.016 $\mu$m$^2$) with 7-nm ground rules while maintaining a sub-5 ns random access latency -- despite their writability challenges. We further identify the sensing margin penalty in NOR FeFET arrays arising from sneak current associated with the negative program-state $V_t$, which requires positive-$V_t$ engineering in order to eliminate the unwanted negative voltage read inhibition -- for example, by ferroelectric layer thinning. Last but not least, we elucidate the read margin implications on 3D FeNOR for SCMs, with the 3D stacking density limited by additional sneak current from neighbor channel shunting.
arXiv:2605.31327v1 Announce Type: new
Abstract: The ICARUS detector, a key component of the Short Baseline Neutrino (SBN) Program at Fermi National Acelerator Laboratory (FNAL), is a 600-ton Liquid Argon Time Projection Chamber (LArTPC) equipped with a Light Detection System (LDS) that uses 360 Hamamatsu R5912-MOD 8-inch photomultiplier tubes (PMTs), specifically designed to operate under cryogenic conditions ($\sim 87 \ K$). These PMTs feed the trigger signal to the readout, improve the spatial and timing resolution of the events, and contribute to cosmic rays mitigation. During operation at FNAL, a progressive degradation in the PMT gain was observed. We developed an experimental setup to investigate the temperature dependence of PMT performance. Gain measurements were carried out from room temperature to $-70 ^\circ C$ using an environmental chamber. The results show that, while the PMTs exhibit stable performance at room temperature, a significant and irreversible reduction in gain emerges at lower temperatures. Al though $-70 ^\circ C$ remains above the liquid argon temperatures, the trend clearly reveals a gain-sensitive degradation mechanism. A simplified physical model was developed to reproduce and interpret the observed behavior. Based on these findings, a series of mitigation strategies were implemented in the ICARUS detector to preserve PMT performance and ensure reliable operation under cryogenic conditions.
arXiv:2605.31337v1 Announce Type: new
Abstract: Reliable identification of encrypted data fragments is essential in cybersecurity, with applications to ransomware detection, digital forensics, and large-scale data analysis. Distinguishing encrypted from compressed fragments is particularly challenging, as short fragments lack structural data and exhibit low statistical redundancy. Traditional statistical methods based on byte-level distributions show limited effectiveness on this task. Recent machine learning approaches improve performance by learning subtle patterns from raw bytes, but predominantly rely on single-modal representations, implicitly assuming that a single view of the data is sufficient for accurate classification. This paper shows that this assumption becomes a fundamental limitation in low-information settings, when only small fragments of data are available (512--2048 Bytes). We propose Triumvir, a multi-modal, uncertainty-aware ensemble architecture that integrates statistical, sequential, and spatial representations of raw byte fragments. Extensive experimental analysis demonstrates that Triumvir consistently outperforms state-of-the-art methods with gains of up to +4.5pp in binary and +6.4pp in multiclass classification. Ablation studies confirm that combining modalities is critical, yielding improvements of up to +5pp over partial configurations.
arXiv:2604.15959v2 Announce Type: replace
Abstract: Multi-objective Bayesian optimization (MOBO) provides a principled framework for optimizing multiple expensive black-box functions. However, existing MOBO methods often struggle with coverage, scalability, and handling constraints and preferences. In this work we propose STAGE-BO, Sequential Targeting Adaptive Gap-Filling $\varepsilon$-Constraint Bayesian Optimization: by analyzing the coverage of the surrogate Pareto front, our method identifies the Pareto front point with the largest uncovered gap, and uses its coordinates to define adaptive constraints in $\varepsilon$-constraint method, which transforms the problem into a sequence of inequality-constrained subproblems, efficiently solved via constrained expected improvement acquisition. Our approach provides uniform Pareto coverage without hypervolume computation and naturally handles constraints and preferences. Experiments on synthetic and real-world benchmarks demonstrate superior coverage and competitive hypervolume performance against state-of-the-art baselines. Our code implementation can be found at https://github.com/YangYaohong1/STAGE-BO.
arXiv:2604.09429v4 Announce Type: replace
Abstract: Recovering camera parameters from images and rendering scenes from novel viewpoints have been treated as separate tasks in computer vision and graphics. This separation breaks down when image coverage is sparse or poses are ambiguous, since each task depends on what the other produces. We propose Rays as Pixels, a Video Diffusion Model (VDM) that learns a joint distribution over videos and camera trajectories. To our knowledge, this is the first model to predict camera poses and do camera-controlled video generation within a single framework. We represent each camera as dense ray pixels (raxels), a pixel-aligned encoding that lives in the same latent space as video frames, and denoise the two jointly through a Decoupled Self-Cross Attention mechanism. A single trained model handles three tasks: predicting camera trajectories from video, generating video from input images along a pre-defined trajectory, and jointly synthesizing video and trajectory from input images. We evaluate on pose estimation and camera-controlled video generation, and introduce a closed-loop self-consistency test showing that the model's predicted poses and its renderings conditioned on those poses agree. Ablations against Pl\"ucker embeddings confirm that representing cameras in a shared latent space with video is subtantially more effective.
arXiv:2605.30849v1 Announce Type: new
Abstract: To enable reliable climbing locomotion of quadruped robots on ferromagnetic surfaces, this paper presents a high-load-density electro-permanent magnetic foot with controllable adhesion, featuring force-feedback circular Halbach-net electro-permanent magnet (CHN-EPM) adhesion units and a magnetization control system. Due to its three-dimensional magnetic circuit structure and flux-concentration effect, the CHN-EPM enables a distributed parallel magnetic flux path with enhanced flux utilization, resulting in reduced sensitivity to air-gap variations and allowing effective adhesion to be maintained even under partial contact conditions. The proposed CHN-EPM generates a maximum adhesion force exceeding 1000 N with a load-to-weight ratio over 200:1. A magnetization driver and a two-stage pulse current control strategy are developed to regulate the excitation current amplitude and duration, enabling accurate and reliable magnetization. By incorporating a flexible pressure sensor for contact force feedback, the system can effectively monitor attachment and detachment states, ensuring robust adhesion switching under uncertain contact conditions. The proposed system is integrated into a commercial quadruped robot (Unitree GO2), demonstrating high-load adhesion on ceiling and vertical-wall surfaces and stable locomotion on painted, perforated, and curved ferromagnetic surfaces.
arXiv:2605.30843v1 Announce Type: new
Abstract: In the forward reinforcement-learning problem, the reward is fixed and known; the learner is asked to find a good policy or value function. Here we turn the question around. Given offline data generated by an expert, can we recover the reward the expert was optimizing? This is the inverse reinforcement learning problem, and remarkably, two communities, structural econometricians studying dynamic discrete choice (DDC) and machine learners studying entropy-regularized IRL, have been working on exactly the same probabilistic model under different names. We begin by proving their equivalence. We then develop the classical identification result of Magnac and Thesmar and the classical computational paradigms that grew out of it: Rust's nested fixed-point algorithm, the conditional-choice-probability approach of Hotz and Miller, and the two temporal-difference approaches of Adusumilli and Eckardt: linear semi-gradient TD and approximate value iteration. Each route has its limits: dimensionality, transition-kernel estimation, the deadly triad, or projected fixed-point bias. We then walk through the modern ML/IRL strand: adversarial IRL, occupancy matching, IQ-Learn, and offline ML-IRL, deriving each method's actual objective and stating precisely what it does and does not identify. We close with the empirical-risk-minimization framework of Kang et al., which yields a gradient-based estimator for offline IRL/DDC.
arXiv:2605.30838v1 Announce Type: new
Abstract: LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmful intents may decompose into seemingly innocuous sub-queries that lead to unsafe outcomes. Existing alignment methods struggle to capture sparse safety signals and fail to supervise diverse violations across multi-step interactions. We propose COMPASS, a Cognitive MCTS-Guided Process Alignment framework designed to achieve robust safety alignment throughout the agent workflow while preserving general utility. COMPASS integrates cognitive tree exploration (CTE) to efficiently synthesize stealthy attack trajectories, and introspective step-wise alignment (ISA) to isolate risky intermediate actions for fine-grained process supervision. Empirical results show that COMPASS achieves a favorable safety-utility trade-off while requiring substantially less training data.
arXiv:2605.30825v1 Announce Type: new
Abstract: Unlearning in diffusion models aims to remove undesirable data or concepts while preserving the utility of pretrained models -- two fundamentally conflicting objectives. We propose a principled constrained optimization framework that formulates unlearning as minimizing the deviation from a pretrained model, subject to explicit separation constraints from the unlearning distributions. Specifically, we formulate three constrained optimization problems based on reverse and forward KL divergences, and likelihood constraints. The first two generalize existing approaches for concept and data unlearning, while the third offers a novel and natural formulation for unlearning. Despite the nonconvexity of the KL constraints, we establish strong duality for all three problems, enabling us to explicitly characterize their optimal solutions as unlearning targets and develop primal-dual algorithms for each formulation. Experimental results demonstrate that our KL-constrained approach achieves superior retention-unlearning tradeoffs compared to weight-based baselines for concept and data unlearning, and that our likelihood-based approach matches unlearning effectiveness while better preserving retained concepts compared to baselines.
arXiv:2605.31406v1 Announce Type: new
Abstract: This paper describes AIM (Automatic Index Manager), a configurable index management system, which identifies impactful secondary indexes for SQL databases to efficiently use available resources such as CPU, I/O and storage. It has been validated on thousands of databases which support production systems. With AIM, the physical design of the database adapts itself to the changes in the workload.We lay out the end to end design of AIM while calling out the guarantees and tradeoffs associated with our design choices. Some of the salient features of AIM include fast convergence even while recommending wide composite indexes, reduced reliance on the query optimizer and a "no regression" guarantee for production workloads. Each index recommendation from AIM is accompanied with a metrics driven explanation, making it easier to verify machine driven changes.AIM is one of the few industrial strength index recommendation engines that is deployed on production databases at a large scale. The experimental results show that AIM is quick in identifying the most effective indexes and the resulting physical design is close to optimal.
arXiv:2604.16278v2 Announce Type: replace
Abstract: Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in natural language processing. In this work, we identify a primary bottleneck in informal theorem proving as a lack of insight, namely the difficulty of recognizing the core techniques required to solve complex problems. To address this, we propose $\texttt{DeepInsight}$, a unified training framework designed to cultivate this essential reasoning skill and enable LLMs to perform insightful reasoning. Our framework consists of three components: (1) $\texttt{DeepInsightTheorem}$, a hierarchical dataset that structures informal proofs by explicitly extracting core techniques and proof sketches alongside the final proof; (2) a Progressive Multi-Stage SFT strategy that mimics the human learning process, teaching the model proof writing, planning, and insight identification; and (3) $\texttt{InsightPO}$, a policy optimization method that assigns structured rewards over this insight hierarchy. Our experiments on challenging mathematical benchmarks demonstrate that this insight-aware generation strategy significantly outperforms baselines. These results demonstrate that teaching models to identify and apply core techniques can substantially improve their mathematical reasoning.
arXiv:2605.31408v1 Announce Type: new
Abstract: Skill documents provide procedural knowledge to large-language-model agents at inference time. This article studies whether the presentation granularity of controlled skill knowledge changes downstream task success. The experiment uses a pinned SkillsBench version, a 30-task domain-balanced subset validated by official oracle runs, two reasoning-enabled model configurations, six skill conditions, and five trials per task-condition-model cell. Skill availability is the clearest empirical signal. Relative to no skill, skill conditions increase task-mean pass rate by 26.7 to 36.0 percentage points for GPT-5.5 and by 18.0 to 26.0 percentage points for DeepSeek V4-Flash. The final data contain 1,800 rows, with 900 rows for each model. The task is the inference unit. Five trials are aggregated within each task-condition-model cell before paired contrasts are estimated over 30 tasks. The primary presentation contrasts are smaller and uncertain. Low-abstraction guidance differs from high-abstraction guidance by +0.7 percentage points for GPT-5.5 and -6.7 percentage points for DeepSeek V4-Flash, with both 95% bootstrap confidence intervals crossing zero. Adding one worked example to medium-abstraction guidance differs from the no-example variant by +0.7 and +1.3 percentage points. Mean-reward robustness checks preserve the same substantive conclusion. In this controlled subset, skill availability is associated with higher success than no skill, while the tested presentation-granularity changes yield small, uncertain, and model-dependent effects.
arXiv:2604.16922v3 Announce Type: replace
Abstract: Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-driven nature required in professional climate science.To bridge this gap, we introduce ClimAgent, a general-purpose autonomous framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields. By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis. To foster systematic evaluation, we propose ClimaBench, the first comprehensive benchmark for real-world climate discovery. It encompasses challenging problems spanning 5 distinct task categories derived from professional scenarios between 2000 and 2025. Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality. Our code are available at https://github.com/usail-hkust/ClimAgent.
arXiv:2604.17551v2 Announce Type: replace
Abstract: Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient due to bootstrapping. While recent work has explored contrastive and supervised formulations to improve stability, we present a probabilistic alternative, called survival value learning (SVL), that reframes GCRL as a survival learning problem by modeling the time-to-goal from each state as a probability distribution. This structured distributional Monte Carlo perspective yields a closed-form identity that expresses the goal-conditioned value function as a discounted sum of survival probabilities, enabling value estimation via a hazard model trained via maximum likelihood on both event and right-censored trajectories. We introduce three practical value estimators, including finite-horizon truncation and two binned infinite-horizon approximations to capture long-horizon objectives. Experiments on offline GCRL benchmarks show that SVL combined with hierarchical actors matches or surpasses strong hierarchical TD and Monte Carlo baselines, excelling on complex, long-horizon tasks. Webpage and Code: https://simple-robotics.github.io/publications/survival-value-learning/
arXiv:2604.21928v3 Announce Type: replace
Abstract: Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large Language Models (LLMs) remain underexplored for this task. This paper evaluates their relevance through three approaches: (1) selecting the best hypothesis between two candidates, (2) computing semantic distance using generative embeddings, and (3) qualitative classification of errors. On the HATS dataset, the best LLMs achieve 92--94\% agreement with human annotators for hypothesis selection, compared to 63\% for WER, also outperforming semantic metrics. Embeddings from decoder-based LLMs show performance comparable to encoder models. Finally, LLMs offer a promising direction for interpretable and semantic ASR evaluation.
arXiv:2604.26262v3 Announce Type: replace
Abstract: Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the difficulty of interacting with these representations compared to traditional, human-authored 3D assets. While previous research has attempted to impose semantic decomposition on these models, significant challenges remain regarding segmentation quality and consistency. To address this, we introduce Semantic Foam, extending the recently proposed Radiant Foam representations to semantic decomposition tasks. Our approach integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level. This explicit structure enables direct spatial regularization, which prevents artifacts caused by occlusion or inconsistent supervision across views - common pitfalls for other point-based representations. Experimental results show that our method achieves comparable or superior object-level segmentation performance compared to state-of-the-art methods like Gaussian Grouping and SAGA.
arXiv:2605.30818v1 Announce Type: new
Abstract: Non-contact material identification enables adaptive interaction for embodied intelligence yet faces challenges from geometry-induced variations (e.g., orientation, shape, distance) and single-modality ambiguities. In this paper, we present GaMi, a multimodal material identification system integrating mmWave and acoustic sensing to robustly operate under unconstrained geometric conditions. By leveraging the insight of shared geometric consistency between co-located bimodal sensors, GaMi employs an intra-sample cross-modal subtractive disentanglement framework. By semantically aligning modalities and subtracting the shared geometric context, it isolates intrinsic material features. Furthermore, GaMi incorporates inter-sample contrastive learning to correct the residual interference caused by cross-modal misalignment. Additionally, a pairing-based adaptation strategy between two modalities enables few-shot generalization across devices. Extensive evaluations on 20 materials show that GaMi achieves 95.2% accuracy, outperforming single-modality baselines across unseen geometric conditions.
arXiv:2605.30906v1 Announce Type: new
Abstract: To enable an efficient interaction of non-communicating mobile robots in collision avoidance scenarios, we present a novel combined trajectory planning and prediction algorithm. Inverse optimal control is used to estimate unknown goal states of all robots based on observed past trajectories. Each robot also takes the perspective of other robots in considering self-prediction and solves a joint prediction problem using the estimated goal states. The resulting predictions are then considered for planning. Simulation results of scenarios with 2-8 robots show that the median of the durations until all vehicles reach their goals is 9.8 % faster compared to planning with constant acceleration based estimated goal states. Moreover, the proposed approach never leads to the solver being unable to find a solution to the planning or prediction problem.
arXiv:2512.11779v2 Announce Type: replace-cross
Abstract: Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although conformal methods can give guarantees on marginal coverage, no method can guarantee to produce sets with correct conditional coverage, leaving practitioners without a clear way to interpret local deviations. To overcome sample-inefficiency and overfitting issues of existing metrics, we cast conditional coverage estimation as a classification problem. Conditional coverage is violated if and only if some classifier can achieve lower risk than the target coverage. Through the choice of a (proper) loss function, the resulting risk difference gives a conservative estimate of natural miscoverage measures such as L1 and L2 distance, and can even separate the effects of over- and under-coverage, and non-constant target coverages. We call the resulting family of metrics excess risk of the target coverage (ERT). We show experimentally that the use of modern classifiers provides much higher statistical power than simple classifiers underlying established metrics like CovGap. Additionally, we use our metric to benchmark different conformal prediction methods. Finally, we release an open-source package for ERT as well as previous conditional coverage metrics. Together, these contributions provide a new lens for understanding, diagnosing, and improving the conditional reliability of predictive systems.
arXiv:2601.15662v2 Announce Type: replace-cross
Abstract: Chemically fueled supramolecular systems provide a versatile platform for generating nonequilibrium structures and dynamical instabilities, including chemical oscillations and traveling waves reminiscent of biological organization. However, a minimal mechanistic framework capable of capturing the emergence of such spatiotemporal order is still lacking. Here, we develop a minimal reaction-transport framework for fuel-driven supramolecular polymerization that couples activation-deactivation chemistry with cooperative assembly, fragmentation, and polymer length-dependent diffusion. The model captures autonomous oscillations arising through a Hopf bifurcation and demonstrates how temporal instabilities evolve into spatial self-organization upon inclusion of transport. We show that the nonlinear interplay between reaction kinetics and state-dependent mobility gives rise to traveling polymerization fronts, oscillatory wave dynamics, and complex spatiotemporal patterns. The propagating fronts exhibit near-ballistic dynamics, revealing a fundamentally nonequilibrium transport mechanism emerging from reactive feedback and dynamically evolving diffusivity. These findings establish a minimal physical framework connecting dissipative self-assembly, nonlinear transport, and active matter, while providing design principles for programmable supramolecular materials capable of autonomous spatiotemporal organization.