# Research Papers — 2026-05 · bundle page 203 of 326 > Full-text markdown of papers #10101–10150 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/203 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/202.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/204.md) ### Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation Authors: Yuwei Zhang, Sha Li, Changlong Yu, Qin Lu, Shuowei Jin, Chengyu Dong, Haoran Liu, Ilgee Hong, Xintong Li, Zhenyu Shi, Bing Yin, Jingbo Shang Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12741v1 Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy self-distillation offers a promising paradigm, existing methods predominantly treat environmental feedback as a passive conditioning signal. Consequently, they heavily rely on successful demonstrations and struggle to learn in rare-success regimes. To bridge this gap, we introduce Reflection-Enhanced Self-Distillation (RESD), a framework that transforms raw failure feedback into an active source of corrective supervision. Instead of passively appending feedback, RESD interprets failed trajectories by generating retrospective reflections to diagnose local errors, and curates a persistent global playbook to preserve reusable lessons across training steps. The enriched context enables the self-teacher to provide actionable token-level supervision even in the absence of successful rollouts. Empirical evaluations on multiple continual learning tasks demonstrate that RESD substantially outperforms standard self-distillation baselines. Furthermore, RESD achieves significantly faster early-stage improvement than GRPO with $8\times$ samples using only a single rollout per prompt, highlighting its superior interaction efficiency. --- ### ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis Authors: Mohammad Jahid Ibna Basher, Ali Khodabandeh Yalabadi, Ivan Garibay, Ozlem Ozmen Garibay Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12736v1 Template based single step retrosynthesis predicts reactants by selecting and applying an explicit reaction template, making each prediction traceable to a chemical transformation rule. This is useful for synthesis planning, but template based methods are often viewed as less competitive than template free models because template prediction is commonly formulated as global classification over a long tailed rule library. We argue that this weakness is not inherent to templates, but to the learning formulation. We present ConRetroBert, a dual encoder framework that reframes template based retrosynthesis as dense product template retrieval followed by candidate set listwise ranking. Stage 1 uses contrastive pretraining to learn a shared embedding space between products and reaction templates. Stage 2 refines template ranking over mined hard negative candidate sets with a multi positive listwise objective. To enable template side adaptation without destabilizing hard negative mining, ConRetroBert uses a slow moving exponential moving average template encoder for retrieval bank construction while updating the live template encoder through the ranking loss. On the local USPTO-50k benchmark, Stage 2 candidate set ranking improves top-1 reaction accuracy from 50.5% to 61.3%, while EMA stabilized template adaptation further improves it to 62.4%. Fine tuning from a leakage controlled USPTO-Full checkpoint reaches 75.4% top-1 accuracy on USPTO-50k. We also show that retrieval based template prediction is strong in the long tail of rare templates, and that many correct reactant predictions arise from alternative explicit templates rather than only the recorded positive label. Code and data are available at https://github.com/JahidBasher/ConRetroBert. --- ### From Generalist to Specialist Representation Authors: Yujia Zheng, Fan Feng, Yuke Li, Shaoan Xie, Kevin Murphy, Kun Zhang Published: 2026-05-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.12733v1 Given a generalist model, learning a task-relevant specialist representation is fundamental for downstream applications. Identifiability, the asymptotic guarantee of recovering the ground-truth representation, is critical because it sets the ultimate limit of any model, even with infinite data and computation. We study this problem in a completely nonparametric setting, without relying on interventions, parametric forms, or structural constraints. We first prove that the structure between time steps and tasks is identifiable in a fully unsupervised manner, even when sequences lack strict temporal dependence and may exhibit disconnections, and task assignments can follow arbitrarily complex and interleaving structures. We then prove that, within each time step, the task-relevant latent representation can be disentangled from the irrelevant part under a simple sparsity regularization, without any additional information or parametric constraints. Together, these results establish a hierarchical foundation: task structure is identifiable across time steps, and task-relevant latent representations are identifiable within each step. To our knowledge, each result provides a first general nonparametric identifiability guarantee, and together they mark a step toward provably moving from generalist to specialist models. --- ### BEHAVE: Real-Time Modeling of Human Systems as Observable Complex Dynamical Systems and Operational Objects for Physical AI Authors: Helene Malyutina Published: 2026-05-12 Categories: cs.AI, cs.GR, cs.MA, physics.soc-ph arXiv: https://arxiv.org/abs/2605.12730v2 A robot can track every person and still fail to see the system those people form. BEHAVE treats an interacting human group as a complex dynamical system: a HumanSystem, an observable, persistent, relational object whose state is carried partly by interaction structure. It is therefore neither explicit in independent individual-track representations nor reducible to simple aggregates. We call this operational emergence. On public pedestrian data, interaction evidence improves group discrimination beyond proximity (AUC 0.896->0.933). On 24 bottleneck runs, future-calm and future-breakdown moments matched on density, mean speed, flow and speed dispersion differ in neighbour-level organization under run-level inference (p=0.028). From interaction evidence K, BEHAVE constructs conservative routing P and local dynamics J=-D+GP, separating routing from gain and relaxation. Stability, critical modes and response become explicit model quantities. We derive exact bounds on what topology can change in collective stability, and conditions under which an observable is blind to the mode becoming unstable. In a causal real-data stress test, the coupled operator improves held-out local dynamics over self-only relaxation by 4.5%. The fitted stability margin St is prospectively associated with future throughput loss but overlaps with lag-1 autocorrelation and self-only relaxation; we read it as a model-based early-warning quantity, not a superior scalar alarm. For Physical AI, the HumanSystem provides a real-time human-side object between perception and action. A robot or scheduler can query group state, structure, critical modes and forced response. Action-conditioned stability changes are reported only when supported by identified changes in human dynamics or signed human-machine coupling. Mixed human-machine systems are represented through a joint Jacobian. --- ### BEHAVE: A Hybrid AI Framework for Real-Time Modeling of Collective Human Dynamics Authors: Helene Malyutina Published: 2026-05-12 Categories: cs.AI, cs.GR, cs.MA, physics.soc-ph arXiv: https://arxiv.org/abs/2605.12730v1 Existing AI systems for modeling human behavior operate at the level of individuals or detect events after they occur. As a result, they systematically fail to capture the collective dynamics that determine whether a group remains stable or transitions into escalation or breakdown. We propose a different foundation: a group of interacting humans constitutes a complex dynamical system in the precise mathematical sense, exhibiting emergence, nonlinearity, feedback loops, sensitivity near critical points, and phase transitions between qualitatively distinct regimes. The state of such a system is not located within any single participant; it is distributed across mutual influence loops and observable through the micro-dynamics of the body. We introduce BEHAVE (Behavioral Engine for Human Activity Vector Estimation), a formal framework that models collective dynamics as continuous behavioral fields defined over an interaction space derived from observable physical signals. Kinematic micro-signals (position, velocity, body orientation, gestural activity) are structured into a directed interaction graph and aggregated into a basis of behavioral fields capturing distinct, non-redundant axes of collective state. The framework rests on one theorem and two structural propositions characterizing the tension field, the field basis, and the criticality index. Perception and forecasting layers are implemented using neural models, enabling data-driven learning and approximation of system dynamics. BEHAVE is formulated as a computational system for learning, representing, and forecasting collective dynamics from data. A working pipeline is demonstrated on a 7-agent negotiation snapshot. The same fields, recalibrated, apply to crowd safety, crisis-team dynamics, education, and clinical contexts. --- ### Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety Authors: Muhammad Bilal, Jon Crowcroft, Ruizhi Wang, Xiaolong Xu, Schahram Dustdar Published: 2026-05-12 Categories: cs.NI, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.12729v3 Large language models (LLMs) are increasingly being used in network operations (NetOps) and artificial intelligence for IT operations (AIOps) for tasks ranging from telemetry retrieval and incident diagnosis to configuration planning and bounded remediation. As these systems acquire greater access to operational tools, the central question is no longer only what an LLM can do, but whether operational assurance increases commensurately with the authority granted to it. This survey examines that question through a structured, evidence-stratified review of agentic NetOps and AIOps. We organise the field around autonomy, tool scope, evidence traces, assurance controls, evaluation, security, and governance, and introduce an operational assurance contract that links each autonomy level to permitted tools, required evidence, independent gates, execution budgets, rollout and rollback duties, and audit requirements. The synthesis reveals a capability--assurance gap: evidence is comparatively strong for read-oriented assistance and tool-grounded diagnosis, but becomes substantially less complete as systems approach configuration change, bounded execution, and closed-loop operation. We therefore argue that evaluation should move beyond static question answering and model accuracy towards workflow-level assessment of evidence quality, tool use, policy and invariant compliance, staged execution, recovery, calibration, cost, and human intervention. We also examine prompt-borne attacks, poisoned or stale operational evidence, excessive agency, privilege boundaries, and weak auditability. Taken together, the survey frames agentic NetOps and AIOps as constrained operational control, in which useful autonomy depends on independently enforced assurance rather than model capability alone. --- ### Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety Authors: Muhammad Bilal, Jon Crowcroft, Ruizhi Wang, Xiaolong Xu, Schahram Dustdar Published: 2026-05-12 Categories: cs.NI, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.12729v2 Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited self-healing. In both NetOps and AIOps, this shift is changing how tasks are managed. Agent-based operations work as workflows, from gathering evidence to taking action, following permissions, policies, and checks, and providing rollback options when necessary. This is crucial because operational decisions can have instant impacts. To make the argument concrete, we organise the relevant literature around the hierarchy of autonomy, tool scope, evidence traces, and assurance contracts. These contracts define what an agent may observe, propose, and execute. They also define the checks that must pass before any action is allowed. A consistent pattern appears across work on telemetry query recommendation, diagnosis, root-cause analysis, configuration synthesis, change planning, and limited self-healing. Operational reliability does not come chiefly from the model itself. It depends on the machinery around the model. We also argue that evaluation should go beyond static question answering. Agentic NetOps and AIOps systems require workflow-centred evaluation, including trace quality, bounded tool use, safe proposal generation, replay in sandboxed environments, and canary trials with rollback-aware scoring. Without these measures, a system may appear robust yet remain too fragile. Finally, we examine security, privacy, and governance risks that become acute when agents sit close to operational control surfaces. Taken together, the survey concludes that progress in intelligent NetOps and AIOps will depend on treating autonomy as a constrained operational control problem, whose outputs must be reliable, auditable, and securely deployable. --- ### Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics Authors: Boming Liu, Jin Dong, Jianming Lian Published: 2026-05-12 Categories: eess.SY, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.12728v2 The power distribution engineering workforce faces a projected shortage of up to 1.5 million engineers by 2030, creating urgent demand for more accessible analysis tools. This paper introduces Grid-Orch, a framework that bridges Large Language Models (LLMs) and power system simulation through the Model Context Protocol (MCP), enabling engineers to perform complex distribution analyses via natural language. Using OpenDSS as the reference implementation, Grid-Orch provides 36 domain-specific tools across eleven categories, covering power flow, voltage analysis, quasi-static time series (QSTS) simulation, and automated optimization. A provider-agnostic LLM layer supports both cloud-hosted (Gemini, Claude) and locally deployed (Ollama, llama-cpp) models, enabling air-gapped operation for security-sensitive utility environments. Three optimization skills, capacitor placement, voltage violation analysis, and overvoltage mitigation, extend the platform beyond single-tool queries to multi-step engineering workflows. Grid-Orch is delivered as an interactive web platform with chat-based interaction, a QSTS dashboard, and feeder topology visualization, and renders simulation results inline. Workflow demonstrations show that distribution analyses formerly requiring hours of scripting, such as distributed energy resource (DER) interconnection screening, complete in under two minutes through natural language, producing numerically identical results to direct OpenDSS scripting. --- ### Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics Authors: Boming Liu, Jin Dong, Jamie Lian Published: 2026-05-12 Categories: eess.SY, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.12728v1 The power distribution engineering workforce faces a projected shortage of up to 1.5 million engineers by 2030, creating urgent demand for more accessible analysis tools. This paper introduces Grid-Orch, a framework that bridges Large Language Models (LLMs) and power system simulation through the Model Context Protocol (MCP), enabling engineers to perform complex distribution analyses via natural language. Using OpenDSS as the reference implementation, Grid-Orch provides 36 domain-specific tools across eleven categories, covering power flow, voltage analysis, quasi-static time series (QSTS) simulation, and automated optimization. A provider-agnostic LLM layer supports both cloud-hosted (Gemini, Claude) and locally deployed (Ollama, llama-cpp) models, enabling air-gapped operation for security-sensitive utility environments. Three optimization skills, capacitor placement, voltage violation analysis, and overvoltage mitigation, extend the platform beyond single-tool queries to multi-step engineering workflows. Grid-Orch is delivered as an interactive web platform with chat-based interaction, a QSTS dashboard, and feeder topology visualization, and renders simulation results inline. Workflow demonstrations show that distribution analyses formerly requiring hours of scripting, such as distributed energy resource (DER) interconnection screening, complete in under two minutes through natural language, producing numerically identical results to direct OpenDSS scripting. --- ### Before the Last Token: Diagnosing Final-Token Safety Probe Failures Authors: Shravan Doda Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12726v2 Final-token safety probes monitor a single hidden state after prompt prefill, but jailbreak prompts can contain probe-visible unsafe evidence distributed across earlier user-token representations that is missed by this readout. We study this prefill-time failure mode using SafeSwitch-style probes trained only on clean harmful and benign prompts across three instruction-tuned LLMs. The probes achieve high recall on clean harmful prompts, but miss many jailbreaks and can produce false positives on safety-adjacent benign prompts. Subspace analyses suggest that missed jailbreaks differ from clean benign prompts along directions that are poorly captured by the probe's representational subspace, and increasing probe bottleneck width does not reliably resolve this mismatch. Token-level prefill analyses reveal that probe-visible unsafe evidence often appears earlier in the sequence but is not exposed at the final-token readout, while naive max-pooling over token positions overfires on safe prompts. A simple PCA-HMM trajectory model, trained only on the same clean split, recovers many final-token misses from user-content prefill trajectories without the catastrophic false-positive behavior of naive token pooling, motivating trajectory-aware hidden-state analyses as diagnostic complements to final-token probes --- ### Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models Authors: Furkan Mumcu, Michael J. Jones, Anoop Cherian, Yasin Yilmaz Published: 2026-05-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.12725v1 Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes. While this focus has led to improvements in scalability and multi-scene generalization, it has also shifted the field away from modeling the scene-specific and context-dependent nature of normal behavior. Contemporary approaches frequently rely on video-level weak supervision and opaque pretrained representations from multi-modal large language models (MLLMs), which encourage models to respond to familiar semantic anomaly categories rather than to deviations from the normal patterns of a particular environment. This trend suppresses spatial localization, introduces semantic bias, and reduces anomaly detection to a form of action recognition. In this paper, we examine whether these prevailing formulations align with the core requirements of real-world VAD, which is typically performed within a single scene where normality is determined by local geometry, semantics, and activity patterns. Through targeted visual analyses and empirical evaluations, we demonstrate the practical consequences of these limitations and show that meaningful progress in VAD requires renewed focus on single-scene, spatially-aware, and explainable formulations that capture the nuanced structure of normality within individual environments. --- ### Inline Critic Steers Image Editing Authors: Weitai Kang, Xiaohang Zhan, Yizhou Wang, Mang Tik Chiu, Jason Kuen, Kangning Liu, Yan Yan Published: 2026-05-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.12724v1 Instruction-based image editing exhibits heterogeneous difficulty not only across cases but also across regions of an image, motivating refinement approaches that allocate correction to where the model struggles. Existing refinement signals arrive late, after a fully generated image or a completed denoising step. We ask whether such a signal can act within an ongoing forward pass. To investigate this, we probe a frozen image-editing model and find that although generation capability emerges only in the last few layers, the error pattern is already set in early layers (rank correlation \r{ho} = 0.83 with the final-layer error map). Based on this, we introduce Inline Critic, a learnable token that critiques a frozen model's predictions at its intermediate layers and steers its hidden states to refine generation during the forward pass. A three-stage recipe is proposed to stabilize the training from learning how to critique to steering generation. As a result, we achieve state of the art on GEdit-Bench (7.89), a +9.4 gain on RISEBench over the same backbone, and the strongest open-source result on KRIS-Bench (81.92, surpassing GPT-4o). We further provide analyses showing that the critic genuinely shapes the model's attention and prediction updates at subsequent layers. --- ### Optimal sequential tests yield log-optimal e-processes Authors: Ashwin Ram, Aaditya Ramdas Published: 2026-05-12 Categories: math.ST, math.PR, stat.ML arXiv: https://arxiv.org/abs/2605.12720v1 It has been recently shown that e-processes are sufficient for sequential testing in the following sense: every level-$α$ sequential test can be obtained by thresholding an e-process at $1/α$. However, in the above result, neither does the test have to be asymptotically optimal (in terms of stopping times) nor does the e-process have to be asymptotically log-optimal. It has separately been shown that asymptotically log-optimal e-processes yield asymptotically optimal sequential tests. In this paper, we prove the converse, arguably completing the story: it is possible to aggregate asymptotically optimal sequential tests into asymptotically log-optimal e-processes. This is accomplished by using a new class of WAIT e-processes: those that are Weighted Aggregates of Indicators of stopping Times that begin at zero, are nondecreasing and increase to infinity under the alternative at the optimal rate. Importantly, the paper discusses several nuances in the varied definitions of asymptotic (log-)optimality. --- ### A Five-Layer MLOps Architecture for Connected Automated Driving Authors: Bastian Lampe, Lutz Eckstein Published: 2026-05-12 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2605.12719v1 The continual assurance of safety and performance of automated driving systems (ADSs) poses significant challenges. ADSs operate in complex, dynamic, open-world environments allowing a wide range of scenarios, including ones that are rare or not foreseen during initial development. While the incorporation of artificial intelligence (AI) and machine learning (ML) technology allows ADSs to learn from data gathered during operation and thus enables them to adapt over time, these approaches come with their own challenges. A key advantage of ADSs compared to human drivers is their greater ability to gather data collectively across a fleet of vehicles, or even across multiple fleets operated by different entities, and to learn from this data collectively. Vehicles can share and combine their data to identify additional learning opportunities otherwise missed by individual vehicles. This creates new opportunities to tackle the challenges of continual assurance of safety and performance, but requires the implementation of architectures that leverage the collective learning potential. Based on established MLOps principles and existing work in the field of connected automated driving, this paper presents a five-layer architecture for collective learning-enabled MLOps processes for ADSs. The goal of this architecture is to provide a conceptual blueprint for the design and implementation of MLOps processes by fleet operators and other relevant stakeholders. The paper describes the main responsibilities of each layer, their interactions, and how multi-level self-assessments enabled by the architecture can support the detection and reduction of edge cases including black swan events. --- ### CHAL: Council of Hierarchical Agentic Language Authors: Tommaso Giovannelli, Griffin D. Kent Published: 2026-05-12 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.12718v1 Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority voting accounts for most observed gains, and LLMs exhibit confidence escalation rather than calibration across rounds. We argue that the genuine value of debate, and dialectic systems as a whole, lies not in ground-truth tasks but in defeasible domains, where every position can in principle be defeated by better reasoning. We present the Council of Hierarchical Agentic Language (CHAL), a multi-agent dialectic framework that treats defeasible argumentation as an engine for belief optimization. Each agent maintains a CHAL Belief Schema (CBS), a graph-structured belief representation with a Bayesian-inspired architecture, that facilitates belief revision through a gradient-informed dynamic mechanism by leveraging the strength of the belief's thesis as a differentiable objective. Meta-cognitive value systems spanning epistemology, logic, and ethics are elevated to configurable hyperparameters governing agent reasoning and adjudication outcomes. We provide a series of ablation experiments that demonstrate systematic and interpretable effects: the adjudicator's value system determines the debate's overall trajectories in latent belief space, council diversity refines beliefs for all participants, and the framework generalizes across broad fields. CHAL is, to our knowledge, the first framework to treat multi-agent debate as structured belief optimization over defeasible domains. Further, the auditable belief artifacts it produces establish the foundation for dedicated evaluation suites for defeasible argumentation, with broader implications for building AI systems whose reasoning and value commitments are transparent, aligned, and subject to human oversight. --- ### The End Justifies the Mean: A Linear Ranking Rule for Proportional Sequential Decisions Authors: Carmel Baharav, Niclas Boehmer, Bailey Flanigan, Maximilian T. Wittmann Published: 2026-05-12 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2605.12717v1 AI alignment and participatory design motivate a new democratic design problem: how to collectively choose a decision rule to use repeatedly. We study this problem for linear ranking rules, which repeatedly rank items $x_j$ within batches $X=(x_1,\dots,x_m)\in(\mathbb{R}^d)^m$, where each item's ranking is dictated by its score $\langle θ^*,x_j\rangle$ according to a fixed scoring vector $θ^*$. Given voters' preferred scoring vectors $θ^{(1)},\dots,θ^{(n)}$ and their population fractions $α^{(1)},\dots,α^{(n)}$, we ask how to choose a collective vector $θ^*$ satisfying individual proportionality (IP): every voter type $i$ should agree with the resulting rankings to an $α^{(i)}$-proportional degree, either on average over time (long-run IP) or even within each batch (per-batch IP). The default rule, the arithmetic mean of the $θ^{(i)}$, has been shown to be severely majoritarian; more generally, it is not clear that any fixed linear rule can balance many voters' disparate opinions. Our main result is that, surprisingly, there is a simple rule that does satisfy long-run IP: the angular mean, the spherical analog of the arithmetic mean. We then show that exact per-batch IP is impossible for fixed linear rules, but that the gap between per-batch and long-run IP shrinks quickly with batch size. Experiments on three real-world preference datasets show that all rules perform similarly when voters' preferences are homogeneous, while the angular mean substantially improves proportionality in high-disagreement regimes. --- ### Scaling Laws for Mixture Pretraining Under Data Constraints Authors: Anastasiia Sedova, Skyler Seto, Natalie Schluter, Pierre Ablin Published: 2026-05-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.12715v2 As language models scale, the amount of data they require grows -- yet many target data sources, such as low-resource languages or specialized domains, are inherently limited in size. A common strategy is to mix this scarce but valuable target data with abundant generic data, which presents a fundamental trade-off: too little target data in the mixture underexposes the model to the target domain, while too much target data repeats the same examples excessively, yielding diminishing returns and eventual overfitting. We study this trade-off across more than 2,000 language-model training runs spanning multiple model and target dataset sizes, as well as several data types, including multilingual, domain-specific, and quality-filtered mixtures. Across all settings, we find that repetition is a central driver of target-domain performance, and that mixture training tolerates much higher repetition than single-source training: scarce target corpora can be reused 15-20 times, with the optimal number of repetitions depending on the target data size, compute budget, and model scale. Next, we introduce a repetition-aware mixture scaling law that accounts for the decreasing value of repeated target tokens and the regularizing role of generic data. Optimizing the scaling law provides a principled way to compute effective mixture configurations, yielding practical mixture recommendations for pretraining under data constraints. --- ### Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs Authors: Jingzhou Jiang, Yi Yang, Kar Yan Tam Published: 2026-05-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.12714v1 Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We propose Layer-wise Representation Dynamics (LRD), a framework with three layer-wise measurement families: Frenet (Grassmann speed and curvature) for global subspace motion, Neighborhood Retention Score (NRS) for local nearest-neighbor retention, and Graph Filtration Mutual Information (GFMI) for alignment with the final layer. Applying LRD to 31 models (encoder-based and decoder-based embedders, plus base LLMs) on 30 MTEB tasks reveals architectural and task-level differences that are not apparent from final-layer representations alone. We then use LRD for two applications: label-free model selection and inference-time layer pruning. For selection, all three model-level scores correlate positively with downstream MTEB performance, with end-to-end subspace displacement (d_{0,L}) the strongest, and the same direction holds on a smaller base-LLM MMLU panel. For pruning, GFMI is the only measurement-guided rule that beats Random at the 15% and 20% budgets and has the best median change at every budget. Frenet is effective only at the lightest budget, while NRS does not transfer from model selection to pruning. These results show that layer-wise structure provides signal for both interpretation and deployment decisions. --- ### Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs Authors: Erik L. Connerty, Ethan N. Evans Published: 2026-05-12 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2605.12713v3 In the field of quantum reservoir computing (QRC), many different computational models and architectures have been proposed. From these models, we identify feedback-based models -- which use a feedback mechanism to re-embed classical measurements from the QRC -- and recurrent models -- which use a multi-register approach with memory and readout qubits -- as the two major competing architectures that have been discussed and validated on hardware. In this paper, we advance upon the recurrent architectures, which employ a two register approach to endow the QRC with a fading memory. While these approaches have been validated on hardware and have demonstrated great real-world performance on noisy-intermediate-scale-quantum (NISQ) quantum processing units (QPUs), the exact mechanism through which the memory capacity arises is not completely understood or fully controllable. With this, we augment the recurrent approaches and present a hardware-realizable mechanism, which we call a tunable partial-SWAP, that allows for the direct control of the rate of memory dissipation from a QRN implemented on a gate-based QPU. The theory behind this mechanism is discussed in terms of a controlled amplitude-damping channel and validation experiments using a randomized short-term memory capacity (STMC) recall benchmark and the NARMA-5 dataset are conducted using simulation and IBM QPUs, respectively. --- ### Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations Authors: Tomasz Dądela, Adam Kania, Maciej Rut, Przemysław Spurek Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12709v1 Implicit Neural Representations (INRs) model continuous signals using multilayer perceptrons (MLPs), enabling compact, differentiable, and high-fidelity representations of data across diverse domains. However, due to the low-frequency bias of MLPs that prevents effective learning of small details, the model's frequency must be carefully tuned through the embedding layer. Prior work established that this tuning can be performed before training based on the target signal, but it did not account for the significant effect of model depth, indicating that our understanding of the relationship between frequency and INR performance remains limited. To gain insights into this relationship, we utilize the Spectral Energy Centroid (SEC) metric that quantifies the frequency of target images and the spectral bias of INR models. We show that SEC is a versatile tool for INR analysis, demonstrating its utility across three tasks: (1) a data-driven strategy (SEC-Conf) for hyperparameter selection that outperforms existing heuristics and is robust to model depth, (2) a reliable proxy for signal complexity, and (3) effective alignment of spectral biases across diverse INR architectures. --- ### A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data Authors: Ziwei Huang, Zeyuan Song, Paola Sebastiani, Stefano Monti Published: 2026-05-12 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2605.12706v1 RSNet is an open-source R package that provides a resampling-based framework for robust and interpretable network inference, designed to address the limited-sample-size challenges common in high-dimensional data. It supports both the estimation of partial correlation networks modeled as Gaussian networks and conditional Gaussian Bayesian networks for mixed data types that combine continuous and discrete variables. The framework incorporates multiple resampling strategies, including bootstrap, subsampling, and cluster-based approaches, to accommodate both independent and correlated observations. To enhance interpretability, RSNet integrates graphlet-based topology analysis that captures higher-order connectivity and edge sign information, enabling single-node and subnetwork-level insights. Notably, RSNet is the first R package to efficiently construct signed graphlet degree vector matrices (GDVMs) in near-constant time for sparse networks, providing scalable analysis of higher-order network structure. Collectively, RSNet offers a versatile tool for statistically reliable and interpretable network inference in high-dimensional data. --- ### Early Data Exposure Improves Robustness to Subsequent Fine-Tuning Authors: Lawrence Feng, Gaurav R. Ghosal, Jacob Mitchell Springer, Ziqian Zhong, Aditi Raghunathan Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12705v2 How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate forgetting of upstream capabilities, we study how upstream training choices - that is, the manner in which a capability is acquired - shape how robustly that capability is retained. We investigate this question in a controlled three-stage language-model pipeline: pretraining, post-training to acquire a target capability, and downstream fine-tuning on a new objective. Across 135M and 1B models, two post-training domains, and two downstream fine-tuning tasks, we find that immediate post-training performance does not reliably predict retention after subsequent fine-tuning: training recipes that look equivalent immediately after post-training can retain the target capability very differently after subsequent fine-tuning. In particular, early exposure - mixing post-training data into pretraining - consistently improves the frontier between retained upstream performance and downstream performance. In compute-matched experiments, where the target data must be allocated between pretraining and post-training, we find that the optimum lies at neither extreme. Together with our other empirical and theoretical findings, this supports the view that post-training drives immediate specialization while early exposure improves robustness to later forgetting. Replay and dropout, typically used to mitigate forgetting as it occurs during fine-tuning, provide complementary gains to early exposure when applied during post-training. Our findings suggest that robustness to subsequent fine-tuning should be treated as a first-class objective of upstream training, addressed preventatively through choices like early exposure rather than reactively during fine-tuning itself. --- ### Early Data Exposure Improves Robustness to Subsequent Fine-Tuning Authors: Lawrence Feng, Gaurav R. Ghosal, Jacob Mitchell Springer, Ziqian Zhong, Aditi Raghunathan Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12705v1 How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate forgetting of upstream capabilities, we study how upstream training choices - that is, the manner in which a capability is acquired - shape how robustly that capability is retained. We investigate this question in a controlled three-stage language-model pipeline: pretraining, post-training to acquire a target capability, and downstream fine-tuning on a new objective. Across 135M and 1B models, two post-training domains, and two downstream fine-tuning tasks, we find that immediate post-training performance does not reliably predict retention after subsequent fine-tuning: training recipes that look equivalent immediately after post-training can retain the target capability very differently after subsequent fine-tuning. In particular, early exposure - mixing post-training data into pretraining - consistently improves the frontier between retained upstream performance and downstream performance. In compute-matched experiments, where the target data must be allocated between pretraining and post-training, we find that the optimum lies at neither extreme. Together with our other empirical and theoretical findings, this supports the view that post-training drives immediate specialization while early exposure improves robustness to later forgetting. Replay and dropout, typically used to mitigate forgetting as it occurs during fine-tuning, provide complementary gains to early exposure when applied during post-training. Our findings suggest that robustness to subsequent fine-tuning should be treated as a first-class objective of upstream training, addressed preventatively through choices like early exposure rather than reactively during fine-tuning itself. --- ### FePySR: A Neural Feature Extraction Framework for Efficient and Scalable Symbolic Regression Authors: Zhiming Yu, Wangtao Lu, Xin Lai Published: 2026-05-12 Categories: cs.SC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.12704v1 A fundamental challenge in symbolic regression (SR) is efficiently recovering complex mathematical expressions from observational data. Although this problem is NP-hard, many expressions of practical interest decompose naturally into combinations of nonlinear feature modules, concentrating structural complexity into a small number of reusable components. Here, we introduce FePySR, a two-stage framework that reduces the SR search space by extracting valid features prior to equation search. FePySR first employs a heterogeneous neural network to constrain observational data to a set of candidate expressions, then performs structural optimization within this refined expression space using PySR. Across five standard benchmarks, FePySR outperforms state-of-the-art methods by achieving higher equation recovery rates. On a set of 75 highly complex synthesized equations, FePySR recovers 36 equations, while producing substantially smaller mean squared errors on the remaining unrecovered cases, with reduced computation time compared to PySR. FePySR's first stage also maintains consistent performance under varying numbers of selected top features and increasing levels of noise in the observational data. Applied to ordinary differential equations governing biological systems, FePySR successfully identifies governing equations in 24 out of 100 tests where PySR recovers none. Taken together, FePySR is a generalizable framework that can enhance the SR solvers, enabling the efficient and reliable recovery of symbolic expressions across scientific domains. --- ### MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence Authors: Yifan Chen, Fei Yin, Qingyan Bai, Zicheng Lin, Yujiu Yang Published: 2026-05-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.12703v1 We introduce MMCL-Bench, a benchmark for multimodal context learning: learning task-local rules, procedures, and empirical patterns from visual or mixed-modality teaching context and applying them to new visual instances. Unlike text-only context learning or standard multimodal question answering, this setting requires models to recover and localize relevant evidence from images, screenshots, manuals, videos, and frame sequences before they can reason over the learned context. MMCL-Bench contains 102 tasks spanning three categories: rule system application, procedural task execution, and empirical discovery and induction. We evaluate frontier multimodal models with strict rubric-based scoring and find that current systems remain far from robust multimodal context learning, with even the strongest model solving fewer than one-third of tasks under strict evaluation. Diagnostic ablations and error analysis show that failures arise throughout the context-to-answer pipeline, including context anchoring, visual evidence extraction, context reasoning, and response construction. MMCL-Bench thus highlights multimodal context learning as an important unsolved capability bottleneck for current multimodal models. --- ### DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models Authors: Eugenia Kim, Ioana Tanase, Christina Mallon Published: 2026-05-12 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.12702v1 General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of twelve disability harm categories co-created with people with disabilities and red teaming experts, a taxonomy-driven evaluation methodology that pairs benign and adversarial prompts across seven life domains, and a dataset of 175 prompts with human-annotated labels on 525 prompt-response pairs. Annotation by four evaluators with lived disability experience reveals three findings: harm rates vary sharply by disability type and will compound in non-text modalities, terminology-driven harm is culturally and temporally bound rather than universally assessable, and standard safety evaluation catches overt failures while missing the subtle harms that only domain expertise can recognize. Disability harm is simultaneously personal, intersectional, and community-defined: it cannot be isolated from the full context of who a person is, and general-purpose benchmarks systematically miss it. We will release the dataset, taxonomy, and methodology via Hugging Face and an open-source red teaming framework for direct integration into existing safety pipelines with no additional infrastructure. --- ### Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions Authors: Gideon Popoola, John Sheppard Published: 2026-05-12 Categories: cs.LG, cs.AI, cs.CE, cs.CY arXiv: https://arxiv.org/abs/2605.12701v1 Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying these metrics does not guarantee that models use the same reasoning for different groups. We show that existing outcome-fair models can still apply fundamentally different reasoning to individuals, a ``hidden procedural bias'' missed by standard fairness metrics and algorithms. We propose Counterfactual Explanation Consistency (CEC), a framework that detects and mitigates this bias by aligning feature attributions between individuals and their counterfactual counterparts. Key contributions include a nearest-neighbor counterfactual generation method, a modified baseline for integrated gradient comparisons, an individual-level procedural fairness metric, and a corresponding training loss. We introduce a taxonomy identifying ``Regime B'' (same outcome, different reasoning) as a critical blind spot. Experiments on synthetic data, German Credit, Adult Income, and HMDA mortgage data demonstrate that outcome-fair baselines exhibit substantial hidden bias, while CEC substantially reduces it with modest utility cost. --- ### UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning Authors: Hanli Qiao, George Em Karniadakis, Muhammad Muniruzzaman Published: 2026-05-12 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2605.12700v1 Neural operators have become an effective framework for learning mappings between function spaces, yet most existing architectures realize operators within a single representational domain, such as physical, spectral, or latent space. In this work, we introduce UFO (Domain-Unification-Free Operator), a cross-domain neural operator framework that realizes operators through adaptive, jointly conditioned interactions among representations defined on distinct domains. UFO enables discretization decoupling: the input function can be observed at resolutions or locations different from those used during training, while the solution can be queried at arbitrary output resolutions. Across four complementary benchmarks covering discontinuous inputs, irregular sampling with spectral mismatch, nonlinear dynamics, and stochastic high-frequency fields, UFO delivers accurate, robust, and physically coherent predictions under distribution shifts. These results establish cross-domain, phase-modulated realization as a powerful framework for discretization-decoupled neural operator learning. --- ### Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification Authors: Kamel Abdous, Nairouz Mrabah, Mohamed Bouguessa Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.12699v1 Existing multiplex graph models often assume homophily, where connected nodes tend to belong to the same class or share similar attributes. Consequently, these models may struggle with graphs exhibiting heterophily, where connected nodes typically belong to different classes and have dissimilar attributes. While recent methods have been developed to learn reliable node representations from unidimensional graphs with heterophily, they do not fully address the complexities of multiplex graphs. In a multiplex graph, nodes are linked through multiple types of edges (referred to as dimensions), which can simultaneously exhibit homophilic and heterophilic interactions. To address this gap, we propose \methodname, a novel method for node classification in multiplex graphs that adapts to both homophilic and heterophilic dimensions. \methodname introduces dimension-specific compatibility matrices to model varying degrees of homophily and heterophily across dimensions. A key innovation is its use of a product of trainable low-pass and high-pass filters, approximated via Chebyshev polynomials, to capture both smooth and abrupt changes in the graph signal. By composing these filters and optimizing label predictions using a proximal-gradient method, \methodname dynamically adjusts to the heterophilic characteristics of each dimension. Extensive experiments on synthetic and real-world datasets provide evidence that \methodname captures the complex interplay of homophilic and heterophilic interactions in multiplex graphs, and tends to yield improved node classification performance compared to state-of-the-art methods. --- ### A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention Authors: Tomohiro Hayase, Ryo Karakida Published: 2026-05-12 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2605.12697v1 Length-dependent logit rescaling is widely used to stabilize long-context self-attention, but existing analyses and methods suggest conflicting inverse-temperature laws for the context length $n$, ranging from $(\log n)^{1/2}$ to $\log n$ and $(\log n)^2$. We provide a general theory showing that the desirable scale is determined by the gap-counting function $N_n$ of each attention row. Counting how many competitors lie within each gap from the maximum, we define an upper-tail accumulation scale and prove that it gives the critical inverse-temperature scale for softmax concentration: below this scale, the top competitors remain unseparated, whereas above it, the attention entropy collapses. This framework unifies prior scaling laws as different $N_n$ and yields a direct diagnostic for attention-score families, from idealized theoretical models to more practical transformers. --- ### Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis Authors: Jacqueline L. Mitchell, Chao Wang Published: 2026-05-12 Categories: cs.SE, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2605.12694v1 Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program analyses that depend on information beyond the source program, or that are otherwise not amenable to conventional static analyzers. However, directly asking an LLM for a one-shot whole-program analysis is brittle because it compresses many evidence-dependent judgments into a single opaque answer, rather than exposing which conclusions are supported or disputed and using intermediate findings to guide later, more focused searches. In this paper, we propose agentic interpretation, a framework that brings the discipline of lattice-based static analysis to LLM-driven program reasoning. At a high level, agentic interpretation decomposes a high-level analysis goal into localized claims, and tracks the LLM's judgment about each claim in a finite-height lattice. A worklist algorithm governs how claims and their judgments evolve during the analysis. We introduce a formal model of agentic interpretation, explore the design space it opens, and illustrate the approach with a worked example analyzing code that depends on opaque third-party components. --- ### IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback Authors: Benjamin Amoh, Geoffrey G. Parker, Wesley Marrero Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12693v1 Decision-focused learning trains predictive models end-to-end against downstream decision loss, but online settings suffer delayed feedback: outcomes may not arrive for many environment interactions. We identify \emph{staleness amplification}, a failure mode unique to bilevel optimization under delay, in which gradient staleness couples with inner-solver sensitivity to inflate regret beyond single-level delay theory. We prove that any black-box delayed optimizer incurs an irreducible regret cost from inner-solver approximation error, and that gradient staleness contributes a quadratically growing transport error without bilevel-aware correction. Our algorithm, \textbf{IGT-OMD}, applies Implicit Gradient Transport to hypergradients within Online Mirror Descent, re-evaluating stale gradients at the current parameters using stored inner solutions. This method reduces transport error from a quadratic to a linear dependence on delay and achieves the first sublinear regret bound for delayed bilevel optimization with queue-length-adaptive step sizes. Controlled experiments provide a \emph{mechanistic fingerprint}: transport benefit is exactly $0.0\%$ ($p=1.00$) at unit delay and grows monotonically to $9.5\%$ at fifty rounds ($p<0.001$), isolating the correction's effect. On Linear Quadratic Regulator, Warcraft shortest-path, and Sinkhorn optimal transport, IGT-OMD reduces decision loss by $17$--$55\%$ relative to single-level baselines, with phase transitions matching the theory. --- ### On the Size Complexity and Decidability of First-Order Progression Authors: Jens Classen, Daxin Liu Published: 2026-05-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.12691v1 Progression, the task of updating a knowledge base to reflect action effects, generally requires second-order logic. Identifying first-order special cases, by restricting either the knowledge base or action effects, has long been a central topic in reasoning about actions. It is known that local-effect, normal, and acyclic actions, three increasingly expressive classes, admit first-order progression. However, a systematic analysis of the size of such progressions, crucial for practical applications, has been missing. In this paper, using the framework of Situation Calculus, we show that under reasonable assumptions, first-order progression for these action classes grows only polynomially. Moreover, we show that when the KB belongs to decidable fragments such as two-variable first-order logic or universal theories with constants, the progression remains within the same fragment, ensuring decidability and practical applicability. --- ### A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions Authors: Mohamed Mahmoud Amar, Nairouz Mrabah, Mohamed Bouguessa, Abdoulaye Baniré Diallo Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.12685v1 Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing methods still predominantly focus on a single graph abstraction level. To address this limitation, we propose a unified contrastive framework that can target node-level, proximity-level, cluster-level, and graph-level information and integrate them through a linear combination of similarity scores on positive pairs and dissimilarity scores (i.e., similarity scores on negative pairs). Furthermore, current approaches typically assign uniform penalty strengths to all examples, which reduces optimization flexibility and leads to ambiguous convergence status. To overcome this, we introduce a novel parameter-free fine-grained self-weighting mechanism that adaptively assigns weights to individual similarity and dissimilarity scores. The proposed mechanism emphasizes the scores that deviate significantly from their target values. Our approach not only enhances optimization flexibility but also eliminates the computational overhead of hyperparameter tuning in conventional multi-task GSSL methods. Comprehensive experiments on real-world datasets show that our methods consistently outperform state-of-the-art approaches across downstream tasks, including classification, clustering, and link prediction, in both single-level and multi-level scenarios. --- ### Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty? Authors: Yichen Feng, Yuetai Li, Chunjiang Liu, Yuanyuan Chen, Fengqing Jiang, Yue Huang, Hang Hua, Zhengqing Yuan, Kaiyuan Zheng, Luyao Niu, Bhaskar Ramasubramanian, Basel Alomair et al. Published: 2026-05-12 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.12684v1 Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an explicit aesthetic judgment. Most existing solutions reduce this judgment to predicting a scalar score for a single image. We first ask whether such scores faithfully capture comparative preference: in a controlled study with eight expert annotators, score-derived rankings align poorly with the same annotators' direct comparisons, while direct ranking yields substantially higher inter-annotator agreement on best- and worst-image labels. Motivated by this finding, we introduce the Visual Aesthetic Benchmark (VAB), which casts aesthetic evaluation as comparative selection over candidate sets with matched subject matter. VAB contains 400 tasks and 1,195 images across fine art, photography, and illustration, with labels derived from the consensus of 10 independent expert judges per task. Evaluating 20 frontier MLLMs and six dedicated visual-quality reward models, we find that the strongest system identifies both the best and the worst image correctly across three random permutations of the candidate order in only 26.5% of tasks, far below the 68.9% achieved by human experts. Fine-tuning a 35B-parameter model on 2,000 expert examples brings its accuracy close to that of a 397B-parameter open-weight model, suggesting that the comparative signal in VAB is transferable. Together, these results expose a clear and measurable gap between current multimodal models and expert aesthetic judgment, and VAB provides the first set-based, expert-grounded testbed on which that gap can be tracked and closed. --- ### Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction Authors: Florian Hess, Florian Götz, Daniel Durstewitz Published: 2026-05-12 Categories: cs.LG, cs.AI, cs.DC, physics.comp-ph arXiv: https://arxiv.org/abs/2605.12683v1 Reconstructing nonlinear dynamical systems (DS) from data (DSR) is a fundamental challenge in science and engineering, but it inherently relies on sequential models. Recent breakthroughs for sequential models have produced algorithms that parallelize computation along sequence length $T$, achieving logarithmic time complexity, $\mathcal{O}(\log T)$. Since sequence lengths have been practically limited due to the linear runtime complexity $\mathcal{O}(T)$ of classical backpropagation through time, this opens new avenues for DSR. This paper studies two prominent classes of parallel-in-time algorithms for this task, both of which leverage parallel associative scans as their core computational primitive. The first class comprises models with linear yet non-autonomous dynamics and a nonlinear readout, such as modern State Space Models (SSMs), while the second consists of general nonlinear models which can be parallelized using the DEER framework. We find that the linear training-time recurrence of the first class of models imposes limitations that often hinder learning of accurate nonlinear dynamics. To address this, we augment DEER with Generalized Teacher Forcing (GTF), a novel variant within the more general nonlinear framework that ensures stable and effective learning of nonlinear dynamics across arbitrary sequence lengths. Using GTF-DEER, we investigate the benefits of training on extremely long sequences ($T>10^4$) for DSR. Our results show that access to such long trajectories significantly improves DSR if the data features long time scales. This work establishes GTF-DEER as a robust tool for data-driven discovery and underscores the largely untapped potential of long-sequence learning in modeling complex DS. --- ### Learning Transferable Latent User Preferences for Human-Aligned Decision Making Authors: Alina Hyk, Sandhya Saisubramanian Published: 2026-05-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.12682v1 Large language models (LLMs) are increasingly used as reasoning modules in many applications. While they are efficient in certain tasks, LLMs often struggle to produce human-aligned solutions. Human-aligned decision making requires accounting for both explicitly stated goals and latent user preferences that shape how ambiguous situations should be resolved. Existing approaches to incorporating such preferences either rely on extensive and repeated user interactions or fail to generalize latent preferences across tasks and contexts, limiting their practical applicability. We consider a setting in which an LLM is used for high-level reasoning and is responsible for inferring latent user preferences from limited interactions, which guides downstream decision making. We introduce CLIPR (Conversational Learning for Inferring Preferences and Reasoning), a framework that learns actionable, transferable natural language rules that represent latent user preferences from minimal conversational input. These rules are iteratively refined through adaptive feedback and applied to both in-distribution and out-of-distribution ambiguous tasks across multiple environments. Evaluations on three datasets and a user study show that CLIPR consistently outperforms existing methods in improving alignment and reducing inference costs. --- ### No One Knows the State of the Art in Geospatial Foundation Models Authors: Isaac Corley, Nils Lehmann, Caleb Robinson, Gabriel Tseng, Anthony Fuller, Hamed Alemohammad, Evan Shelhamer, Jennifer Marcus, Hannah Kerner Published: 2026-05-12 Categories: cs.CV, cs.CY arXiv: https://arxiv.org/abs/2605.12678v3 Geospatial foundation models (GFMs) have been proposed as generalizable backbones for disaster response, land-cover mapping, food-security monitoring, and other high-stakes Earth-observation tasks. Yet the published work about these models does not give reviewers or users enough information to tell which model fits a given task. We argue that nobody knows what the current state of the art is in geospatial foundation models. The methods may be useful, but the GFM literature does not standardize evaluations, training and testing protocols, released weights, or pretraining controls well enough for anyone to compare or rank them. In a 152-paper audit, we find 46 cross-paper disagreements of at least 10 points for the same model, benchmark, and protocol; 94/126 papers with extractable pretraining data use a configuration no other paper uses; and 39% of GFM papers release no model weights. This lack of community standards can be solved. We propose six concrete expectations: named-license weight release, shared core evaluations, copied-versus-rerun baseline annotations, variance reporting, one shared evaluation harness, and data-vs-architecture-vs-algorithm controls. These gaps are a coordination failure, not a fault of any individual lab; the authors of this paper, like many others in the GFM community, have contributed to them. Rather than just critiquing the community, we aim to provide concrete steps toward a shared understanding of how to innovate GFMs. --- ### No One Knows the State of the Art in Geospatial Foundation Models Authors: Isaac Corley, Nils Lehmann, Caleb Robinson, Gabriel Tseng, Anthony Fuller, Hamed Alemohammad, Evan Shelhamer, Jennifer Marcus, Hannah Kerner Published: 2026-05-12 Categories: cs.CV, cs.CY arXiv: https://arxiv.org/abs/2605.12678v2 Geospatial foundation models (GFMs) have been proposed as generalizable backbones for disaster response, land-cover mapping, food-security monitoring, and other high-stakes Earth-observation tasks. Yet the published work about these models does not give reviewers or users enough information to tell which model fits a given task. We argue that nobody knows what the current state of the art is in geospatial foundation models. The methods may be useful, but the GFM literature does not standardize evaluations, training and testing protocols, released weights, or pretraining controls well enough for anyone to compare or rank them. In a 152-paper audit, we find 46 cross-paper disagreements of at least 10 points for the same model, benchmark, and protocol; 94/126 papers with extractable pretraining data use a configuration no other paper uses; and 39% of GFM papers release no model weights. This lack of community standards can be solved. We propose six concrete expectations: named-license weight release, shared core evaluations, copied-versus-rerun baseline annotations, variance reporting, one shared evaluation harness, and data-vs-architecture-vs-algorithm controls. These gaps are a coordination failure, not a fault of any individual lab; the authors of this paper, like many others in the GFM community, have contributed to them. Rather than just critiquing the community, we aim to provide concrete steps toward a shared understanding of how to innovate GFMs. --- ### Revealing Interpretable Failure Modes of VLMs Authors: Isha Chaudhary, Vedaant V Jain, Kavya Sachdeva, Sayan Ranu, Gagandeep Singh Published: 2026-05-12 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.12674v1 Vision-Language Models (VLMs) are increasingly used in safety-critical applications because of their broad reasoning capabilities and ability to generalize with minimal task-specific engineering. Despite these advantages, they can exhibit catastrophic failures in specific real-world situations, constituting failure modes. We introduce REVELIO, a framework for systematically uncovering interpretable failure modes in VLMs. We define a failure mode as a composition of interpretable, domain-relevant concepts-such as pedestrian proximity or adverse weather conditions-under which a target VLM consistently behaves incorrectly. Identifying such failures requires searching over an exponentially large discrete combinatorial space. To address this challenge, REVELIO combines two search procedures: a diversity-aware beam search that efficiently maps the failure landscape, and a Gaussian-process Thompson Sampling strategy that enables broader exploration of complex failure modes. We apply REVELIO to autonomous driving and indoor robotics domains, uncovering previously unreported vulnerabilities in state-of-the-art VLMs. In driving environments, the models often demonstrate weak spatial grounding and fail to account for major obstructions, leading to recommendations that would result in simulated crashes. In indoor robotics tasks, VLMs either miss safety hazards or behave excessively conservatively, producing false alarms and reducing operational efficiency. By identifying structured and interpretable failure modes, REVELIO offers actionable insights that can support targeted VLM safety improvements. --- ### Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack Authors: Hao Wang, Hanchen Li, Qiuyang Mang, Alvin Cheung, Koushik Sen, Dawn Song Published: 2026-05-12 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.12673v1 Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges spontaneously in frontier models without overfitting. We argue that benchmarks must be secure by design. From past incidents of reward hacks, we derive a taxonomy of eight recurring flaw patterns and compile them into the Agent-Eval Checklist for benchmark designers. We condense the insights into BenchJack, an automated red-teaming system that drives coding agents to audit benchmarks and identify possible reward-hacking exploits in a clairvoyant manner. Moreover, we extend BenchJack to an iterative generative-adversarial pipeline that discovers new flaws and patches them iteratively to improve benchmark robustness. We apply BenchJack to 10 popular agent benchmarks spanning software engineering, web navigation, desktop computing, and terminal operations. BenchJack synthesizes reward-hacking exploits that achieve near-perfect scores on most of the benchmarks without solving a single task, surfacing 219 distinct flaws across the eight classes. Moreover, BenchJack's extended pipeline reduces the hackable-task ratio from near 100% to under 10% on four benchmarks without fatal design flaws, fully patching WebArena and OSWorld within three iterations. Our results show that evaluation pipelines have not internalized an adversarial mindset, and that proactive auditing could help close the security gap for the fast-paced benchmarking space. --- ### All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs Authors: Xi Chen, Mingyu Jin, Jingcheng Niu, Yutong Yin, Jinman Zhao, Bangwei Guo, Dimitris N. Metaxas, Zhaoran Wang, Yutao Yue, Gerald Penn Published: 2026-05-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.12671v1 In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional Anisotropy Hypothesis: the idea that functions in large language models (LLMs) are localised to a unique or near-unique internal mechanism. We show that a single LLM task can instead be supported by multiple, structurally distinct circuits or sheaves that are simultaneously faithful, sparse, and complete. To systematically uncover such competing mechanisms, we introduce Overlap-Aware Sheaf Repulsion, a method that augments the CSD objective with an explicit penalty on structural overlap across multiple discovery runs, enabling the discovery of circuits or sheaves with strong task performance but minimal shared structure across a plethora of common CSD benchmarks. We find that this phenomenon becomes increasingly pronounced as the number of discovered sheaves grows and persists robustly across major CSD methods. We further identify an ultra-sparse three-edge sheaf and show that none of its edges is individually indispensable, undermining even weakened notions of canonical or essential components. To explain these findings, we propose a Distributive Dense Circuit Hypothesis and provide a theoretical analysis demonstrating that non-unique, low-overlap circuit explanations arise naturally from high-dimensional superposition under mild assumptions. Together, our results suggest that mechanistic explanations in LLMs are inherently non-canonical and call for a rethinking of how CSD results should be interpreted and evaluated. --- ### Online Conformal Prediction: Enforcing monotonicity via Online Optimization Authors: Eduardo Ochoa Rivera, Ambuj Tewari Published: 2026-05-12 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.12668v1 Conformal prediction provides a principled framework for uncertainty quantification with finite-sample coverage guarantees. While recent work has extended conformal prediction to online and sequential settings, existing methods typically focus on a single coverage level and do not ensure consistency across multiple confidence levels. In many real-world applications, such as weather forecasting, macroeconomic prediction, and risk management, different users operate under heterogeneous risk tolerances and require calibrated uncertainty estimates across a range of coverage levels. In such settings, it is desirable to produce prediction sets corresponding to different coverage levels that are nested and valid simultaneously. In this paper, we propose two novel online conformal prediction methods that output \emph{nested prediction sets} across a range of coverage levels, enabling simultaneous uncertainty quantification across the entire risk spectrum. Beyond interpretability, jointly estimating multiple coverage levels is known to improve statistical efficiency in classical quantile regression by enforcing non-crossing constraints and sharing information across quantiles. Our approaches leverage an online optimization perspective with small regret that translates to quantile estimation error control while enforcing nestedness of prediction sets. Empirical results on synthetic and real-world datasets, including applications in forecasting tasks with heterogeneous risk requirements, demonstrate that our method achieves stable coverage across all levels, strictly nested prediction sets, and improved efficiency compared to existing online conformal baselines. --- ### ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization Authors: Nirmal Patel, Fei Wang, Inderjit S. Dhillon Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.12667v2 The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form question answering and open-ended instruction following. These domains often rely on LLM based auto-raters to provide granular, multi-tier discrete rewards (e.g., 1-10 rubrics) that are inherently stochastic due to prompt sensitivity and sampling randomness. We empirically verify the stochasticity of auto-raters that can propagate and corrupt standard advantage estimators like GRPO and MaxRL, as a noisy reward samples can skew normalization statistics and degrade the global learning signal. Empirically, sampling more rewards and taking majority voting may reduce the noise and improve performance, but this approach is computationally expensive. To address this bottleneck, we introduce $\textbf{O}$rdinal $\textbf{D}$ecomposition for $\textbf{R}$obust $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{ODRPO}$), a framework that structurally isolates evaluation noise by decomposing discrete rewards into a sequence of ordinal binary indicators. By independently computing and accumulating advantages across these progressively challenging success thresholds, ODRPO prevents outlier evaluations from corrupting the global update while establishing an implicit, variance-aware learning curriculum. Empirically, ODRPO achieves robust performance on Qwen2.5-7B and Qwen3-4B models, outperforming baselines with relative improvements of upto 14.8% on FACTS-grounding-v2 and 7.5% on Alpaca-Evals. Critically, these gains are achieved with negligible training-time overhead, as ODRPO requires no additional compute per step compared to standard estimators. Supported by theoretical analysis confirming its optimization stability, ODRPO provides a scalable and robust framework for aligning models within the noisy, discrete evaluation landscape of modern RLAIF. --- ### Profit Maximization in Bilateral Trade against a Smooth Adversary Authors: Simone Di Gregorio, Paul Dütting, Federico Fusco, Chris Schwiegelshohn Published: 2026-05-12 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2605.12664v1 Bilateral trade models the task of intermediating between two strategic agents, a seller and a buyer, who wish to trade a good. We study this problem from the perspective of a profit-maximizing broker within an online learning framework, where the agents' valuations are generated by a smooth adversary. We devise a learning algorithm that guarantees a $\tilde{O}(\sqrt{T})$ regret bound, which is tight in the time horizon $T$ up to poly-logarithmic factors. This matches the minimax rate for the stochastic i.i.d. case, and is also well separated from the adversarial setting, where sublinear-regret is unattainable. By extending the strong regret guarantees from the i.i.d. case to the smooth adversary, we significantly broaden the scope of settings where such fast rate is achievable, while closing an important gap in the regret landscape of this fundamental economic problem. To overcome the challenges posed by this adversary, we leverage a continuity property of smooth instances and combines this with a hierarchical net-construction of the broker's action space, which is analyzed via algorithmic chaining. We showcase the applicability of these techniques by deriving a similarly tight $\tilde{O}(\sqrt{T})$ regret bound for a related mechanism design model: the joint ads problem. --- ### scShapeBench: Discovering geometry from high dimensional scRNAseq data Authors: Andrew J Steindl, João Felipe Rocha, Brian Tshilengi Di Bassinga, Zachary Warren, Matthew Scicluna, César Miguel Valdez Córdova, Shabarni Gupta, Leire Torices, Daniel Neumann, Timothy J. Mann, Ihuan Gunawan, Dhananjay Bhaskar et al. Published: 2026-05-12 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2605.12662v1 High-dimensional point cloud data arise across many scientific domains, especially single-cell biology. The shapes or topologies of these datasets determine the types of information that can be extracted. For example, clustered data supports cell-type identification, trajectory structures support transition analysis, and archetypal structures capture continua of cellular behaviors. Existing analysis pipelines often assume a specific shape. The standard Seurat pipeline combines UMAP visualization with Louvain clustering and therefore assumes clustered data, while tools such as Monocle and SPADE assume tree-like structures, and flow-based models such as MIOFlow and Conditional Flow Matching target trajectories. Choosing which pipeline to apply is therefore often left to bioinformaticians who visually inspect datasets before selecting an analysis strategy. With the rise of agentic AI scientists, automating shape detection is increasingly important for selecting downstream analysis pipelines. To address this problem, we introduce scShapeBench, a benchmark dataset for shape detection containing both synthetic and expert-annotated single-cell datasets. Synthetic datasets are sampled from ground-truth skeleton graphs with controlled variance. Real single-cell datasets are curated from diverse sources and annotated by experts into four categories: clusters, single trajectory, multi-branching, and archetypal. We additionally introduce scReebTower, a baseline method that uses diffusion geometry to extract Reeb graphs and connect visualization with pipeline selection. We provide topology-aware evaluation metrics and compare scReebTower against PAGA and Mapper on synthetic and real data. Our results indicate that scReebTower outperforms existing baselines. Overall, our contributions span benchmarks, evaluation metrics, and a baseline for automated shape detection in single-cell data. --- ### Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning Authors: Wo Wei Lin, Ethan Rathbun, Enrico Marchesini, Xiang Zhi Tan Published: 2026-05-12 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.12655v3 Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instruction objective and restoring the continuation value under the current objective. Unlike reward shaping, MAVIC modifies the bootstrapping target itself, enabling consistent value estimation under stochastic instruction switching within a unified policy. We provide theoretical analysis and an actor-critic implementation, and show that MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments. --- ### Plan Before You Trade: Inference-Time Optimization for RL Trading Agents Authors: Eun Go, Rohan Deb, Arindam Banerjee Published: 2026-05-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.12653v1 Reinforcement learning agents for portfolio management are typically trained and deployed as static policies, with no mechanism for using price forecasts at inference time. We propose $\text{FPILOT}$ (**Fin**ancial **P**lugin **I**nference-time **L**earning for **O**ptimal **T**rading), a plugin inference-time optimization framework inspired by Model Predictive Control (MPC). Our key structural insight is that future prices mostly do not depend on one agent's portfolio allocation, so a suitable predictive model can produce a multi-step price trajectory without iterative action-conditioned rollouts as in typical reinforcement learning. At each decision step, we use the forecaster's predicted price trajectory to construct an allocation-based imagined return objective, and optimize the policy at inference-time before executing one step of the trade. Our framework is compatible with any pre-trained agent and adapts the policy to the forecaster's predictions without any retraining. Evaluated across five policy learning algorithms on the TradeMaster DJ30 benchmark, $\text{FPILOT}$ produces consistent improvements in total return and return-based risk-adjusted metrics (Sharpe, Sortino, Calmar), with stochastic policies benefiting more than deterministic ones. Further, using synthetic forecasts at calibrated quality levels, we show that gains consistently improve with forecaster quality, suggesting that our performance will improve based on advances in financial forecasting. --- ### Multi-Rollout On-Policy Distillation via Peer Successes and Failures Authors: Weichen Yu, Xiaomin Li, Yizhou Zhao, Xiaoze Liu, Ruowang Zhang, Haixin Wang, Yinyi Luo, Chen Henry Wu, Gaurav Mittal, Matt Fredrikson, Yu Hu Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.12652v2 Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser token-level supervision by training on student-generated trajectories, yet existing methods typically distill each rollout independently and ignore the other attempts sampled for the same prompt. We introduce Multi-Rollout On-Policy Distillation (MOPD), a peer-conditioned distillation framework that uses the student's local rollout group to construct more informative teacher signals. MOPD conditions the teacher on both successful and failed peer rollouts: successes provide positive evidence for valid reasoning patterns, while failures provide structured negative evidence about plausible mistakes to avoid. We study two peer-context constructions: positive peer imitation and contrastive success-failure conditioning. Experiments on competitive programming, mathematical reasoning, scientific question answering, and tool-use benchmarks show that MOPD consistently improves over standard on-policy baselines. Further teacher-signal analysis shows that mixed success-failure contexts better align teacher scores with verifier rewards, indicating that the gains arise from more faithful, instance-adaptive supervision. These results indicate that effective on-policy distillation should exploit the student's multi-rollout trial-and-error behavior rather than treating rollouts as isolated samples. --- ### Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic Authors: Parv Kapoor, Abigail Hammer, Ashish Kapoor, Karen Leung, Eunsuk Kang Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.12651v2 Runtime monitoring of autonomous systems traditionally relies on mapping continuous sensor observations to discrete logical propositions defined over low-dimensional state variables. This abstraction breaks down in perception-driven settings, where such mappings require additional learned modules that are often computationally expensive, brittle, and semantically misaligned. In this work, we propose Embedding Temporal Logic (ETL), a temporal logic that performs monitoring directly in learned embedding spaces. ETL defines predicates through distances between observed embeddings and target embeddings derived from reference observations. This formulation allows specifications to capture high-level perceptual concepts, such as similarity to visual goals or avoidance of semantic regions, that are difficult or impossible to express using traditional predicates. By composing these predicates with temporal operators, ETL naturally expresses temporally extended and sequential perceptual behaviors. We introduce ETL monitors for evaluating specifications over bounded embedding traces, along with a conformal calibration procedure that provides reliable and safety-oriented predicate evaluation. We evaluate our approach across multiple manipulation environments to show that ETL achieves strong empirical agreement with ground-truth semantics, including accurate monitoring of temporally composed behaviors. ---