# Research Papers — 2026-06 · bundle page 169 of 260

> Full-text markdown of papers #8401–8450 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-06/page/169
[← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/168.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-06/page/170.md)

### Position: AI Must Become Planet-Centered, Not Just Human-Centered

Authors: Maria Perez-Ortiz
Published: 2026-06-09
Categories: cs.CY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.13704v1

This position paper argues that contemporary AI paradigms are insufficient for supporting complex global goals and introduces Planet-Centered AI (PCAI) as a design philosophy and research agenda that reorients AI toward planetary-scale socio-ecological systems and their long-term trajectories. A planet-centered approach is grounded in systems thinking, treating Earth as an interconnected whole of which humans are part. We diagnose recurring limitations across AI frameworks, many of which remain human-centered, and show why these become especially consequential under current planetary conditions characterized by systemic risk, non-stationarity, and deep uncertainty. We then articulate how PCAI reshapes the AI lifecycle, from problem formulation and model design to evaluation and deployment, by emphasizing alignment with global agendas, developing system-aware AI foundations, trajectory-oriented evaluation, and monitorability. Finally, we advance a falsifiable claim: AI systems optimized without explicit consideration of systemic consequences are more likely to exacerbate systemic instability than to mitigate it.

---

### Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency

Authors: Seth Dobrin, Łukasz Chmiel
Published: 2026-06-09
Categories: stat.ML, cs.CL, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2606.12471v2

Klindt, LeCun, and Balestriero (arXiv:2605.26379) proved that Joint-Embedding Predictive Architectures (JEPAs) achieve linear identifiability, the linear recovery of the world's true latent variables, if and only if the world's latent dynamics follow a Gaussian, stationary process. This Gaussian boundary implies a fundamental limit on temporal consistency: for any non-Gaussian physical system, the representation error of a statistical World Model grows monotonically with time. We prove that this limit is an artifact of the statistical alignment mechanism, not a property of World Models in general. We introduce the Physics-Grounded Symbolic Architecture (PGSA) and prove three results: (1) a PGSA achieves exact linear identifiability for all physical regimes, regardless of the latent distribution; (2) the per-step error of a PGSA is bounded by numerical precision alone; and (3) as a direct consequence, a PGSA maintains temporal consistency for an unbounded number of transitions, a property we term near-infinite temporal consistency. We further prove that statistical World Models cannot achieve this property for any non-Gaussian system, regardless of model capacity or the volume of training data. The algebraic cores of four of the theorems are formalized in Lean 4 with Mathlib4 v4.31.0 (zero sorry placeholders); the Klindt et al. converse is taken as an external premise. The contrast establishes that symbolic grounding in the causal generator of the world's dynamics is the sufficient condition and, in non-Gaussian regimes, the only condition for near-infinite temporal consistency.

---

### Search Discipline for Long-Horizon Research Agents

Authors: Adithya Srinivasan, Devesh Paragiri
Published: 2026-06-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.11522v1

Autoresearch agents now propose, evaluate, and select scientific candidates against a metric, and that metric is usually an aggregate reduced over a heterogeneous space of regions, slices, or cohorts. We show that when scientific validity lives in that disaggregated structure, the aggregate can rank the wrong candidate first. The headline number improves while the structure underneath inverts, so a decision made on the number accepts a candidate that quietly breaks the model. The failure is not domain-specific. It appears wherever a candidate's validity is multi-dimensional but its verifier is a single reduction. We demonstrate the inversion on a fire-model task in the Ecosystem Demography model. The highest-scoring candidate and a slightly lower one are within noise of each other on global score, yet the top-scoring one collapses the protected boreal regions while the other preserves them. What separates them is the per-region behavior, not the headline number. This decision should not be left to the agent that produced the candidates. The agent optimizing the score is the last party likely to catch the score being wrong, and a prompt has no remaining turn once the agent has stopped. We move the decision to an external control loop that audits each candidate on its disaggregated behavior and acts after the agent has decided. It can demote a candidate the agent would have accepted, and it can reopen a run the agent had declared finished. Our contribution is the inversion finding itself, and a search-discipline protocol that decides on reviewable candidate-effect evidence instead of the score.

---

### Counterexample Guided Learning in the Large using Reasoning Agents

Authors: Hongyi Liu, Frederic Sala, Thomas Reps, Adithya Murali
Published: 2026-06-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.11521v1

LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking LLMs to perform regular-expression induction, a classical symbolic learning problem where precise mechanisms for feedback exist in the form of counterexamples. In counterexample-guided learning, a learner (LLM) proposes candidate regular expressions from positive/negative-labeled strings, and the teacher (verifier) returns counterexamples showcasing the difference between the candidate and target languages. We identify novel counterexample-guided refinement strategies that enable effective regex learning, such as regularization and symbolic counterexample clusters. We also explore agentic strategies such as reflection and repair loops. Empirically, we find that verifier feedback substantially improves sample efficiency on challenging regex-induction tasks, reducing the number of labeled examples required and enabling learning of complex target expressions where standard prompting fails. For example, on the hardest task groups, our counterexample-guided framework improves success from 3.2% to 38.1% and from 38.9% to 74.1% on two different regex domains. These results suggest that LLMs can benefit from rich feedback beyond treating it as additional data, opening the door for robust verifier-guided methods for LLM-based program synthesis and formal reasoning.

---

### ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

Authors: Siyuan Luo, Nairong Zheng, Lin Zhou, Tiankuo Yao, Shengyou Yuan, Haojia Yu, Cong Pang, Jiapeng Luo, Lewei Lu
Published: 2026-06-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.11520v4

Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution--properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly. Stage 1 constructs roughly 50000 structured intents via a 4D framework (Persona x Domain x Task x Complexity); after deduplication the pool contains 43956 unique intents and attains a Vendi Score of 61.57 over the entire pool on mpnet-base-v2 embeddings (cosine kernel, q=1). Stage 2 drives multi-turn user-agent interaction through a role-locked user simulator that grounds each user turn in actual execution outcomes, producing 23132 complete trajectories averaging 8.12 user turns and 68.24 total dialogue turns. Stage 3 runs every tool call inside a live, isolated OS workspace, generating authentic failure-recovery dynamics instead of simulated responses. Fine-tuning on ISETrace improves ClawEval pass@1 from 19.3 to 37.7 using Qwen3-8B on agent tool-use tasks with a standard protocol. This result outperforms zero-shot GPT-4o and the larger Qwen3-32B base model which is four times bigger. An ablation on Stage 2 proves multi-turn simulation brings a large portion of the performance gain. We release all source code and dataset at https://github.com/Valiere01/ISE-Trace.

---

### SirenFNO: Efficient and Full Frequency Learning of Fourier Neural Operators

Authors: Pengqing Shi, Jie Yin, Stephen Tierney, Junbin Gao
Published: 2026-06-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.11518v1

Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations. However, owing to the reliance on frequency truncation to maintain learning efficiency of FNOs, empirical studies suggest that FNOs exhibit spectral bias toward low-frequency information, which may hinder the learning capability especially for certain PDEs with strong high-frequency oscillations. To address this limitation, we propose SirenFNO, a novel framework that leverages sinusoidal representation networks (SIRENs) to learn implicit neural representations and performs mode-wise kernel parameterization. Our SIREN parameterization learns a full-grid spectrum with a constant and discretization-independent parameter count, thereby eliminating the need for frequency truncation. We further extend SirenFNO with functional tensor decompositions to enhance parameter and learning efficiency. Empirical results show that our SirenFNO consistently outperforms FNO with approximately $4$ to $15$ times parameter reductions with preserved discretization invariance, and our functional decomposition variants obtain performance improvements with a maximum of $73$ times fewer parameters across multiple PDE benchmarks.

---

### SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment

Authors: Kaiwen Shi, Zheyuan Zhang, Yanfang Ye
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11512v1

Large language models increasingly express uncertainty through natural-language statements, yet these expressions often fail to reflect the model's sampled behavior. We study verbal uncertainty alignment as a distributional calibration problem: the appropriate uncertainty target for a prompt should be estimated from repeated model outputs rather than from an isolated response. However, group rollouts alone are insufficient, since the resulting target must provide a useful training signal. Existing targets only partially satisfy this requirement. We propose SAGE, Semantic-Answer Guided Entropy, a group-level uncertainty target that constructs an answer-conditioned uncertainty geometry over sampled responses. SAGE preserves categorical, numeric, and symbolic answer distinctions while maintaining a smooth and scale-preserving calibration signal. We further apply this target through Group-Uncertainty Preference Optimization, or GUPO, an uncertainty-channel training framework that supervises verbal uncertainty expressions rather than the full response. Experiments across factual, mathematical, and multiple-choice reasoning tasks show improved uncertainty ranking, lower calibration error, and reduced overconfidence.

---

### Continuous biome representations from Earth observation embeddings

Authors: Maxwell B. Joseph, Flávia De Souza Mendes, Dieu My T. Nguyen, Camile Sothe, Christopher B. Anderson
Published: 2026-06-09
Categories: q-bio.QM, q-bio.PE, stat.ML
arXiv: https://arxiv.org/abs/2606.11510v1

Biotic communities vary continuously across space, yet biome maps impose categorical boundaries that compress this variation, particularly at ecotones where transitional communities are ecologically distinct. Could Earth observation (EO) foundation models, which encode spectral, spatial, and temporal information with dense embeddings, convert discrete biome maps into continuous representations that better capture ecological variation? Here, we fit a linear classifier on Clay v1.5 satellite image embeddings to predict biome labels from a categorical map. The softmax output yields a continuous probability vector whose dimensions correspond to named biome classes. We evaluate this approach using six Brazilian biomes, 1.3 million embeddings, and 10,015 withheld forest inventory plots spanning 4,672 plant species. The continuous biome representation outperforms discrete biome labels for predicting species occurrence (mean per-species AUC 0.618 vs. 0.570 across 10 spatial cross-validation folds). Decomposing this gain shows that continuity in the graded probability output, rather than label reassignment, accounts for the improvement; the pattern holds across all distances from biome boundaries. The raw 1024-dimensional embedding remains the strongest predictor we tested (mean AUC 0.646 vs. 0.618), but the continuous representation recovers most of the embedding's gain over discrete labels. This simple approach provides a probabilistic replacement for categorical map labels, preserving their meaning while encoding graded variation that discrete maps suppress.

---

### Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction

Authors: Yifan Xue, Srimukh Prasad Veccham, Saee Paliwal, Tyler Shimko, Micha Livne
Published: 2026-06-09
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2606.11508v1

Accurate prediction of absorption, distribution, metabolism, and excretion (ADME) properties is critical to drug discovery, but remains challenging because ADME endpoints are noisy, interdependent, and often data-limited. We propose a molecular graph-transformer pretraining framework that combines chemistry-specific self-supervision with contrastive mutual information machine learning (cMIM). Our method encodes molecular graphs into latent variables, reconstructs SMILES strings from the graph-derived latent codes, and augments the contrastive objective with domain-specific self-supervised chemistry tasks. Rather than treating these tasks as auxiliary regularizers with separately tuned loss weights, we formulate reconstruction, contrastive discrimination, and chemistry-specific supervision as unit-weighted log-probability factors in a single probabilistic latent-variable objective. For fine-tuning, we propose a multi-task GNN readout architecture with task-specific multilayer perceptron heads, preserving shared representation learning while mitigating negative transfer and improving the modeling of heterogeneous, nonlinear task relationships. Across Biogen, ExpansionRX, and ChEMBL-MT, the resulting Contrastive KERMT pretraining improves over the KERMT baseline by 7.6%, 9.9%, and 9.5% respectively (averaged over significantly-improved endpoints). Adding ADME-adjacent molecules to the pretraining corpus further improves transfer, and the contrastive component sharpens chemically meaningful latent neighborhoods.

---

### SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining

Authors: Abdalmalek Aburaddaha, Venkatraman Narayanan, Keval Thaker, Samir A. Rawashdeh
Published: 2026-06-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.11507v1

Mining hard, safety-critical scenes from driving logs is bottlenecked by the absence of difficulty labels, and no single proxy, collision risk, trajectory ambiguity, or semantic rarity suffices to find such scenes on its own. We present SceneMiner, a unified, camera-only bird's-eye-view pipeline that emits complementary mining signals from a frozen vision-language backbone in a single forward pass, with no LiDAR or radar: a retrieval embedding for text-prompted scenario search, a multi-label scene-tag distribution, and a continuous physics-based risk score (a motion forecast is a byproduct, not a contribution). Building such a multi-head model exposes our central finding, a failure mode we term cross-task interference: adding or upgrading one head shifts a shared activation stream and degrades weight-frozen sibling heads, so freezing parameters alone is insufficient. Our contribution, identity-preserving multi-task fine-tuning, removes this interference by zero-initializing every new sub-module and freezing every parameter that feeds the shared stream. The mining heads are thereby preserved bit-identically while training only ~102k parameters. The tagging head reaches mAP 0.4614 (micro-F1 0.5557) on 20 scene tags by pooling each scene into 32 visual tokens, and the embedding head supports text-prompted retrieval, validated qualitatively. Code is available at: https://anonymous.4open.science/r/sceneminer_anonymous-64E5

---

### On the Study of Biometric Spoofing Detection using Deep Learning

Authors: Kumar Kartikey, Nikos Komninos
Published: 2026-06-09
Categories: cs.CV, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2606.11505v1

Biometric systems are increasingly deployed in security applications; however, they remain vulnerable to spoofing attacks, in which attackers exploit counterfeit biometric data to gain unauthorized access. This research evaluates the effectiveness of state-of-the-art machine learning models, MobileNetV2, DenseNet-121, Inception-v3, and Spoof Trace Disentanglement (STD) in detecting spoofing attacks within facial recognition systems. Using the CelebA-Spoof dataset, the study evaluates model effectiveness using metrics such as accuracy, precision, recall, and F1 Score. Cross-dataset validation is carried out on the MSU-MFSD dataset to assess generalizability. The results show MobileNetV2 as the most efficient model, achieving 92% accuracy while balancing computational effectiveness, making it appropriate for real-life applications. Inception-v3 shows moderate robustness, while DenseNet-121 and STD struggle with generalization. The findings highlight the need for advances in domain adaptation and hybrid architectures to enhance biometric security systems.

---

### When Role-playing, Do Models Believe What They Say?

Authors: Benjamin Sturgeon, David Africa, Sid Black
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.11502v3

Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models behave, with models selecting the most appropriate persona for a given context. Does such role-playing merely change the model's outputs, or does it also affect what the model internally represents as truthful? We study this question using the role-play of characters whose beliefs differ from the modern consensus, and induce personas with a number of different methods: prompting, in-context learning (ICL), supervised fine-tuning (SFT), and Open Character Training (OCT), and Emergent Misalignment (EM). We measure belief internalization across these approaches with truth probes and with behavioral tests, finding a broad spectrum of belief internalization. Prompting, ICL, and SFT change what the model says with little representational change. EM creates a large, broad shift in the model's truth representation, and OCT a smaller shift that is clearest on the larger model. Understanding when training changes a model's worldview rather than merely its behavior may become increasingly important as AI systems are entrusted with greater autonomy and influence.

---

### FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI

Authors: Mo Wang, Wenhao Ye, Junfeng Xia, Minghao Xu, Hongkai Wen, Quanying Liu
Published: 2026-06-09
Categories: eess.IV, cs.CE, cs.IT, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2606.11500v1

The success of large-scale deep learning models in neuroscience is fundamentally constrained by severe data heterogeneity. Native fMRI data aggregated from diverse sources exhibit substantial variation in both spatial and temporal resolutions. Consequently, most existing frameworks rely on lengthy, rigid preprocessing pipelines that enforce uniformity across datasets. This practice introduces two critical limitations: (1) potential degradation of subject-specific anatomical information; (2) significant computational overhead, often requiring hours of processing per subject. Here, we propose FlexiBrain, a resolution-agnostic voxel-level encoding framework for native fMRI based on Mamba-JEPA. FlexiBrain defines patch sizes in real-world physical units and employs a dynamic patch resizing, thereby bypassing destructive spatial standardization while enabling direct ingestion of data in native space. We instantiate the framework using an efficient Mamba-JEPA backbone to model high-dimensional 4D fMRI signals. Across five diverse downstream neuroscience tasks, FlexiBrain consistently outperforms recent state-of-the-art methods, achieving gains of up to 12 percentage points without external data augmentation. Importantly, FlexiBrain functions as a seamless plug-in module, substantially reducing preprocessing costs and accelerating the development of robust voxel-level fMRI foundation models. Code is available at https://github.com/OneMore1/FlexiBrain.

---

### Hubs or Fringes: Pretraining Data Selection via Web Graph Centrality

Authors: Vedant Badoni, Danqi Chen, Xinyi Wang
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.11499v1

The performance of modern language models depends critically on pretraining data composition. Yet existing data selection methods rely on auxiliary classifiers for document scoring or mixture optimization, adding computational overhead and dependence on labeled data. We propose WebGraphMix, a lightweight data selection framework that computes structural centrality scores over the Common Crawl host-level web graph and uses them to vary the proportion of central versus peripheral documents in the pretraining mixture. We hypothesize that central hosts expose models to reusable abstractions, while peripheral hosts encode specialized, long-tail knowledge. WebGraphMix computes centrality scores efficiently at web scale, requiring no model training, labeled data, or downstream supervision. We integrate WebGraphMix into the DataComp-LM pipeline and train models at 400M and 1B parameter scales with 8B and 28B tokens respectively, evaluating on 23 tasks ranging from factual knowledge to symbolic reasoning. Our experiments show that central and peripheral web regions encode complementary capabilities. Mixture combining both at a ratio of 1:1 achieves 41.4% on average, compared to 39.8% for uniform sampling. Combining structural scores with document-level quality classifier scores further improves performance to 43.8%. These findings demonstrate that web graph topology is a meaningful axis for pretraining data curation, capturing information that is largely orthogonal to existing content-based approaches.

---

### OmniLoc: A Geometry-Aware Foundation Model for Anchor-Free UE Localization Across Diverse Indoor Environments

Authors: Lei Chu, Yuning Zhang, Omer Gokalp Serbetci, Anushka Katiyar, Bassel Abou Ali Modad, Andreas F. Molisch
Published: 2026-06-09
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2606.11490v1

Indoor localization from wireless measurements remains challenging in large-scale deployments due to substantial variation in building geometry, the set of detectable access points (APs), and the heterogeneity of received signals. Existing learning-based methods often perform well only in limited settings and degrade under environmental shifts, making robust anchor-free localization across diverse indoor environments notoriously difficult. In this paper, we present OmniLoc, an environment-interactive foundation model for anchor-free user equipment localization across diverse indoor environments. To the best of our knowledge, OmniLoc is the first foundation-model-based approach built directly on wireless measurements for this task. OmniLoc is built on three key designs. First, a unified input tokenization module converts heterogeneous wireless measurements into a common representation that is more amenable to learning. Second, a geometry-aware Transformer performs AP-aware feature extraction by emphasizing dominant APs while aggregating complementary evidence from supporting APs. Third, a geometry-aware location estimation module conditions regression on geometric embeddings to produce geometrically consistent location predictions. We evaluate OmniLoc on both a large-scale in-house dataset and a public benchmark dataset. Results show that OmniLoc significantly outperforms existing methods, consistently improves existing backbones when its design components are integrated, and demonstrates strong generalization in cross-environment evaluations.

---

### Unbiased Derivative Estimation for Stationary Mean of Parameterized Markov chains

Authors: Jeffrey Wang, Chang-han Rhee
Published: 2026-06-09
Categories: math.ST, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2606.11487v1

We propose a new approach to unbiased estimation of the gradients of the stationary means associated with parametrized families of Markov chains. Our estimators are particularly efficient when the Markov chains have slow mixing rate. Our approach does not require a specific parametrization except for an oracle to evaluate the transition density and its gradient at a given data point without any additional knowledge about the density function itself. It makes our estimator suitable for parametrizations associated with neural networks. The estimator can potentially achieve large improvement in terms of efficiency. Numerical experiments confirm the good performance predicted by the theory.

---

### Building Social World Models with Large Language Models

Authors: Haofei Yu, Yining Zhao, Guanyu Lin, Jiaxuan You
Published: 2026-06-09
Categories: cs.SI, cs.CL
arXiv: https://arxiv.org/abs/2606.11482v1

Understanding and predicting how social beliefs evolve in response to events -- from policy changes to scientific breakthroughs -- remains a fundamental challenge in social science. Given LLMs' commonsense knowledge and social intelligence, we ask: Can LLMs model the dynamics of social beliefs following social events? In this work, we introduce the concept of the Social World Model (SWM), a general framework designed to capture how social beliefs evolve in response to major events. SWM learns state-transition functions for social beliefs by mining temporal patterns in social data and optimizing the evidence lower bound, without the need for explicit human annotations linking events to belief shifts, or for expensive census data. To evaluate SWM, we introduce a benchmark, SWM-bench, derived from real-world prediction markets, specifically Kalshi and Polymarket. SWM-bench includes over 12k data points for social belief prediction tasks spanning diverse domains such as politics, finance, and cryptocurrency. Our experimental results show that SWM significantly outperforms time-series foundation models, achieving state-of-the-art results on Kalshi data and demonstrating competitive performance on Polymarket data, while offering interpretable insights into the underlying mechanisms of social belief dynamics.

---

### Accurate and Resource-Efficient Federated Continual Learning

Authors: Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan, Rajgopal Kannan, Viktor Prasanna
Published: 2026-06-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.11480v1

Federated continual learning (FCL) must learn from distributed task streams under limited resources, such as communication, computation, memory, and label availability. Existing FCL methods often rely on repeated local optimization, replay, and full supervision. Analytic alternatives avoid iterative training and replay, but using high-dimensional random features to improve accuracy requires a second-order feature statistic, the Gram matrix, which has a quadratic communication cost in the random feature size $M$. We propose FedRAN, a resource-aware analytic FCL framework that replaces gradient-based updates with compact random feature statistics. Each client transmits a truncated-SVD summary of its Gram matrix, reducing the dominant second-order upload from quadratic to linear in $M$ for fixed rank. The server performs a two-level QR-SVD subspace merge, spatially across clients and temporally across tasks, and solves a ridge classifier in closed form. FedRAN further supports label scarcity through prototype-based pseudo-labeling. Across CIFAR-100, ImageNet-R, and VTAB datasets, FedRAN improves average accuracy by up to 4.8 percentage points over the strongest baseline, uses 30.6-121.8$\times$ less per-client communication than optimization-based FCL, and is 190.3$\times$ faster on average than gradient-based baselines; with only 20% labels, pseudo-labeling improves average accuracy by up to 6.61 points. These results show that FedRAN enables accurate and resource-efficient FCL under communication, computation, and label constraints. The source code is available at https://github.com/JebacyrilArockiaraj/Fed-RAN-SSL.

---

### Towards Fully Automated Exam Grading: Fairness-Aware Recognition of Handwritten Answers with Foundation Models

Authors: Hartwig Grabowski
Published: 2026-06-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.11477v1

Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a didactic narrowing towards closed question formats. A practical middle ground keeps paper-based, problem-oriented tasks but records the assessment-relevant answers as single capital letters in a table that a machine can read. The open question is whether this reading can be made accurate and, above all, fair enough for unsupervised grading. Earlier automated approaches reached only about 88%--91% recognition -- too low -- and failed on the cases that matter most: answers placed outside the cell, crossed out, or written in cursive. We show that general-purpose vision-language foundation models (VLMs), which interpret the page rather than match pixel templates, close this gap. On a benchmark of 61 anonymised exams (3141 answer positions) the best model reaches 98.4% accuracy, well above the previous baseline. Crucially, we centre the evaluation on fairness: we distinguish false negatives (a correct answer marked wrong, which disadvantages the student) from false positives, and a lightweight prompt that supplies the reference solution as context lowers the false-negative rate to 0.58%. Under an exemplary grading scheme only three of the 61 exams would be graded worse, all caught by a student self-review step. Fully automated, fairness-aware exam grading at scale is therefore defensible; we release the anonymised benchmark to support reproducibility.

---

### Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems

Authors: Shaifalee Saxena, Alexander Scheinker
Published: 2026-06-09
Categories: cs.LG, eess.SY, physics.acc-ph
arXiv: https://arxiv.org/abs/2606.11474v2

In this paper, we study Mahalanobis-guided latent out-of-distribution (OOD) detection for test-time RL controller switching in nonlinear time-varying systems. RL controllers can quickly control high-dimensional systems within the training distribution, but their performance can degrade when time-varying dynamics produce unseen observations. We consider a combined ES--DRL controller, where RL provides fast in-distribution actions and bounded extremum seeking (ES) provides robust model-independent control under OOD operation. The key challenge is deciding when to switch. We train a variational autoencoder (VAE) on in-distribution beam-profile observations and use Mahalanobis distance in the VAE latent space to detect OOD beam profiles at test time. This OOD decision sets a binary switch that selects either the RL controller or the ES controller. We evaluate the approach in safety-critical particle accelerator control. In this setting, spatial magnet motion creates OOD beam profiles that were not seen during RL training. Visualization of the VAE latent space shows that the proposed method identifies this OOD scenario and provides an interpretable signal for switching between RL and ES in the combined controller.

---

### CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching

Authors: Jamie Heredge, Mattia J. Villani, Pranav Deshpande, Akshay Seshadri, Niraj Kumar
Published: 2026-06-09
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2606.11473v1

Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass. However, the quadratically scaling self-attention mechanism in many PFN architectures makes inference prohibitive for very large training datasets. We propose CRUMB (Clustered Retrieval Using Minimised-MMD Batching), a three-stage inference wrapper that (i) clusters the test queries, (ii) selects a small, distributionally matched training subset for each cluster by greedily minimising the maximum mean discrepancy (MMD), and (iii) runs exact PFN inference on each reduced-context batch. CRUMB is architecture-agnostic and requires no retraining. On the 51-dataset TabArena benchmark, evaluated across three PFN architectures (TabPFNv2, TabICLv1, TabICLv2), we show that CRUMB outperforms similar state-of-the-art context selection strategies. We also show that CRUMB is resilient to covariate drift, as the MMD-minimisation step naturally helps align the training context distribution to match the current test batch distributions.

---

### Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems

Authors: Warren Fernando, Nikos Komninos
Published: 2026-06-09
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2606.11471v1

The expansion of the digital domain has resulted in a substantial increase in digital communication, with email emerging as one of the most prominent channels. The proliferation of email communication is apparent in both professional and personal contexts, thereby creating numerous vulnerabilities for malicious actors to exploit. Spam emails, a form of unsolicited correspondence often bearing malicious intent towards recipients, have been an ongoing challenge for email users since the inception of email technology, and this problem has been exacerbated by the growth of the digital landscape. Email spam filters are integral components of email clients, engineered to identify potentially harmful messages and alert users to their malicious content. Phishing, frequently the initial phase of malware-based attacks, is evolving rapidly, with malware becoming increasingly sophisticated over time. A widely adopted approach for detecting malicious activity within malware and spam domains is the application of machine learning. Our aim is to assess the impact of the evolution within the spam email domain on these machine learning-based detection systems and to explore strategies for mitigating associated performance degradation.

---

### The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

Authors: Avinash Anand, Mahisha Ramesh, Avni Mittal, Ashutosh Kumar, Rishitej Reddy Vyalla, Erik Cambria, Zhengkui Wang, Timothy Liu, Aik Beng Ng, Simon See, Rajiv Ratn Shah
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11470v2

Reasoning has become central to how Large Language Models (LLMs) are evaluated and interpreted, spanning Chain-of-Thought (CoT), mathematical problem-solving, multi-hop question answering, code generation, retrieval-augmented reasoning, tool use, and multimodal decision-making. In this survey, we introduce the Periodic Table of LLM Reasoning, a framework organizing 300+ recent papers by reasoning paradigm, methodological mechanism, evaluation setting, and failure mode. We classify LLM reasoning into nine paradigms: Chain-of-Thought, Multi-Hop, Mathematical, Commonsense, Visual and Temporal, Code and Algorithmic, Retrieval-Augmented, Tool-Augmented or Agentic, and Reinforcement Learning-based reasoning. For each, we review approaches, including prompting, architectural interventions, supervised fine-tuning, verifier-guided inference, reward modeling, retrieval, tool interfaces, agentic workflows, and benchmark design. We argue that LLM reasoning is not a single emergent capability but a family of scaffolded behaviors shaped by model scale, task structure, external memory, supervision, and evaluation protocols. We synthesize recurring failure modes, including hallucinated reasoning, brittle multi-step inference, spurious rationales, weak causal grounding, poor out-of-distribution generalization, benchmark contamination, and unreliable self-verification. Progress is difficult to compare across paradigms because gains may arise from prompting, retrieval, verifier design, or benchmark structure rather than general reasoning ability. The survey connects methods to their assumptions, strengths, and failure modes, providing a reference map of the field and a diagnostic framework for future work. We conclude that robust LLM reasoning will require meta-reasoning, multimodal and temporal grounding, adaptive tool use, and principled evaluation under distribution shift.

---

### The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

Authors: Avinash Anand, Mahisha Ramesh, Avni Mittal, Ashutosh Kumar, Erik Cambria, Zhengkui Wang, Timothy Liu, Aik Beng Ng, Simon See, Rajiv Ratn Shah
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11470v1

Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge. Although modern LLMs show progress in structured inference, multi-step problem solving, and contextual understanding, their reasoning behavior is often inconsistent and sensitive to prompting strategies, task design, and model scale. This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology to examine how reasoning capabilities emerge in LLMs and where they fail. We make three main contributions. First, we introduce a structured taxonomy of LLM reasoning research, covering Chain-of-Thought reasoning, multi-hop reasoning, mathematical reasoning, common sense reasoning, visual and temporal reasoning, code and algorithmic reasoning, retrieval-augmented reasoning, tool-augmented and agentic reasoning, and reinforcement learning-based reasoning. Second, we analyze methodological trends across these paradigms, including prompting methods, model architectures, training objectives, reward modeling, and evaluation benchmarks. Third, we synthesize recurring limitations and failure modes, such as reasoning hallucinations, brittle multi-step inference, weak causal abstraction, and poor cross-domain generalization. By organizing a rapidly expanding literature, this survey offers a unified view of the current capabilities and limitations of reasoning in LLMs. We also identify emerging research directions, including meta-reasoning, self-evolving reasoning frameworks, multimodal reasoning, and socially grounded reasoning. Overall, this work aims to serve as a reference for developing more robust, interpretable, and generalizable reasoning systems in future language models.

---

### Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more

Authors: Spencer Compton, Jerry Li
Published: 2026-06-09
Categories: cs.DS, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2606.11469v1

We study the task of density estimation, where we hope to accurately estimate a probability density from $n$ samples. A textbook method for density estimation in total variation distance is the minimum-distance estimator approach, where we conclude both the algorithm and the analysis merely from bounding the VC dimension of a particular concept class (the so-called Yatracos class). While this technique has originally yielded sharp guarantees primarily for total variation distance, in this work we extend the minimum-distance estimator approach for learning within Hellinger distance. Our main observation is that we may produce an analogous recipe for Hellinger (where we only require bounding the VC dimension of a related concept class) by drawing connections to recent results yielding reverse data processing inequalities. This recipe is flexible enough to accommodate fast algorithms originally designed for total variation distance; by modifying the approach of Acharya et al. (2017) we conclude the first near-linear time algorithm for learning classes including univariate mixtures of log-concave densities and mixtures of Gaussians (with arbitrary variances), with near-optimal sample complexity.

---

### PT-WNO: Point Transformer with Wavelet Neural Operator for 3D Point Cloud Semantic Segmentation

Authors: Nhut Le, Maryam Rahnemoonfar
Published: 2026-06-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.11466v1

Point cloud semantic segmentation requires architectures that capture both fine-grained local geometry and broad global scene structure. Transformer-based networks have demonstrated strong performance by focusing on detailed local feature aggregation; however, global context is conveyed primarily through skip connections across encoder-decoder stages, which we argue is insufficient for full scene understanding. We hypothesize that augmenting skip connections with a learnable global feature extraction module allows the network to acquire scene-level knowledge before descending into local detail, leading to richer and more contextually grounded representations. To this end, we propose Point Transformer with Wavelet Neural Operato (PT-WNO), which integrates a shared Wavelet Neural Operator (WNO) branch alongside the skip connections of a point cloud transformer backbone. At each encoder-decoder transition, point features are projected onto a dense 3D volumetric grid where the WNO captures multi-scale global spectral context through learnable wavelet decomposition and reconstruction. These global features are fused back into the network via lightweight adapters, complementing rather than replacing the existing skip connections. Experiments on four large-scale 3D point cloud benchmarks demonstrate the effectiveness of PT-WNO. On S3DIS (Area 5), PT-WNO achieves 71.59% mIoU, outperforming the Point Transformer v3 (PTv3) baseline by +1.03 points. On DALES it achieves 81.05% mIoU (+1.47 over the baseline). On ScanNet~v2, PT-WNO obtains 76.19% mIoU, remaining competitive with the baseline (76.36%).

---

### LSTM-Based Detection of Structural Breaks in Property Insurance Loss Reserving: A Climate-Informed Approach

Authors: Thomas Mbrice, Shashwat Panigrahi
Published: 2026-06-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.11463v1

Accurate loss reserving is foundational to insurer solvency, yet accelerating climate driven catastrophes systematically violate the stability assumptions on which traditional actuarial methods depend. This white paper presents a research program testing whether Long Short Term Memory (LSTM) neural networks can detect and adapt to these structural breaks faster and more accurately than Chain Ladder, Bornhuetter Ferguson, and Cape Cod methods. Using 15 plus years of regulatory development triangle data from Florida and Louisiana, enriched with NOAA hurricane intensity indices and sea surface temperatures, we hypothesize a targeted improvement of 15, 20% in reserve accuracy for catastrophe exposed years, a threshold grounded both in the prior neural network reserving literature and in the formal convergence results developed here. Beyond empirical validation, we develop a theoretical framework grounding LSTM structural break detection in probabilistic terms, providing formal performance guarantees that compensate for the limited number of catastrophe events in the test period. We document the research design, methodology, expected contributions, and a candid assessment of limitations.

---

### APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection

Authors: Fei Wang, Si Si, Cho-Jui Hsieh, Inderjit S. Dhillon
Published: 2026-06-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.11459v1

Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While evolutionary algorithms have emerged as the dominant paradigm, they suffer from a critical bottleneck: data efficiency. Current methods treat the development dataset as a static benchmark, wasting significant compute budget on uninformative data. In this work, we introduce APEX (Automatic Prompt Engineering eXpert), a novel framework that optimizes the data usage alongside the prompt search. APEX dynamically stratifies the dataset into Easy, Hard, and Mixed tiers based on the optimization lineage. By prioritizing the Mixed tier, which identifies the data where the LLM has mixed performance, we identify two high-leverage subsets: the addressable frontier for generating informative mutations and the rank-sensitive frontier for distinguishing candidate quality. We evaluate APEX across three diverse benchmarks: IFBench, SimpleQA Verified, and FACTS Grounding. Under a fixed budget of 5,000 evaluation calls, due to its data efficiency, APEX outperforms the initial prompt by an average of 11.2% on Gemini 2.5 Flash and 6.8% on Gemma 3 27B, demonstrating that a data-centric approach is key to efficient and effective prompt optimization.

---

### AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable

Authors: Meysam Alizadeh, Fabrizio Gilardi, Mohsen Mosleh, Enkelejda Kasneci
Published: 2026-06-09
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2606.11456v1

The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions. We argue these worries target two empirically separable layers: a design layer of methodological choices, and a verdict layer in which a decision rule maps estimates to a substantive claim. We test both by running 20 independent executions of Claude Code and Codex on a prominent immigration and social-policy against a many-analysts human baseline. At the design layer, Codex matches human methodological diversity and Claude Code produces nearly three times as many specifications; both agents' effect estimates remain broadly aligned with the human consensus, and no agent model exactly matches any human model. A prompt-induced anti-immigration researcher prior reorganizes each agent's methodological decisions but, unlike for biased human analysts in the same data, does not shift aggregate estimates or final verdicts; nor do agents reroute along the methodological axes humans use to bias their estimates. At the verdict layer, an explicit confirmatory prompt flips Claude Code's verdicts from 10% to 90% support while leaving its coefficient distribution essentially unchanged, operating through rule omission rather than rule softening. AI agents can rival or exceed human methodological diversity at the design layer while remaining vulnerable at the verdict layer. In our setting, the locus of AI bias is not estimation but interpretation.

---

### Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition

Authors: Shengkai Sun, Zhiyong Cheng, Zefan Zhang, Jianfeng Dong, Zhihui Li, Meng Wang
Published: 2026-06-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.11450v1

Recently, masked skeleton reconstruction models have emerged as strong action representation learners, driving significant progress in self-supervised skeleton-based action recognition. However, existing state-of-the-art methods must predict an exceedingly large number of spatiotemporal patches, significantly prolonging training time. Besides, by treating all spatiotemporal regions equally during reconstruction, these models are distracted from learning the critical motion patterns that underlie action semantics. To address these challenges, we propose Adaptive Masked Reconstruction (AMR), a faster and stronger pre-training framework. We first decouple the decoder from the encoder, enabling flexible prediction of larger spatiotemporal patches and dramatically reducing reconstruction complexity. Given that larger patches contain more complex information, which is challenging to predict and consequently degrades performance, we accordingly introduce an adaptive guidance module. This module identifies regions of high motion informativeness, guiding the model to focus on the most discriminative parts of each patch and alleviating reconstruction difficulty. Experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that AMR not only accelerates pre-training substantially but also improves downstream recognition accuracy, surpassing current state-of-the-art approaches.

---

### AI Coding Agents Can Reproduce Social Science Findings

Authors: Meysam Alizadeh, Mohsen Mosleh, Fabrizio Gilardi, Atoosa Kasirzadeh, Joshua Tucker
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11447v1

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

---

### 3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling

Authors: Ahmad Al-Kabbany
Published: 2026-06-09
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2606.11446v1

This research introduces a framework for incorporating Concept Bottleneck Models (CBMs) into 3D generative architectures to address the inherent 'semantic gap' in deep geometric learning. As deep models become central to 3D content creation, explainability shifts from a peripheral feature to a fundamental requirement for trust and accountability in safety-critical domains such as healthcare and manufacturing. CBMs provide an intrinsic interpretability solution by constraining latent representations to align with human-defined concepts, yet their application to unstructured 3D data remains largely unexplored. We design, implement, and validate a formal 3D-CBM architecture that maps raw geometric inputs, including point clouds and meshes, into a multi-tiered taxonomy of interpretable primitives and functional attributes. The framework further identifies strategic datasets, such as PartNet and ShapeNet, specialized for concept-based supervision. Experimental results from a 3D part-manipulation proof-of-concept experiment demonstrate the framework's efficacy, achieving a concept prediction accuracy of 88.8\% and a Chamfer Distance of 0.0115. Critically, the model enables precise test-time intervention, allowing for the interactive correction of structural errors. This work establishes a foundation for semantically-steerable 3D generation and invites further exploration into collaborative human-in-the-loop design systems.

---

### Forecasting Future Behavior as a Learning Task

Authors: Mosh Levy, Yoav Goldberg, Asa Cooper Stickland
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.11445v1

Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs. For large reasoning models (LRMs), this conventional route is particularly difficult to follow: explanation methods for single token generations do not naturally generalize to long trajectories, and the trajectories themselves are often not faithful when read as natural language. We propose an alternative that bypasses the explanation step: treat behavior forecasting as a learnable task and train Behavior Forecasters that operates on a single reasoning trajectory to make the same forecasts one would typically seek from an explanation. The forecaster's training data is obtained by querying the LRM with no human annotation, and its inference is done in a single forward pass. We instantiate this approach on two tasks: how likely the LRM is to repeat its answer on re-runs, and how removing parts of the input changes its answer. We evaluate this approach on both tasks across three diverse reasoning datasets and find that trained Behavior Forecasters are more accurate than GPT-5.4 and Claude Opus-4.6 reading the same trajectories as naive readers, at a small fraction of their inference cost. We find that fine-tuning the backbone end-to-end and initializing it from the target LRM are each necessary for strong performance. These results show that the reasoning trajectory carries information about the LRM's future behavior that goes beyond what naive reading conveys.

---

### INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration

Authors: Ahasan Kabir, Jiaqi Xue, Mengxin Zheng, Qian Lou
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.11440v1

Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and model features. However, these methods do not consider the runtime state of the serving infrastructure. On shared GPU clusters under concurrent load, this infrastructure blindness causes systematic resource underutilization: preferred models accumulate deep request queues while equally capable alternatives sit idle. In multi-agent pipelines, where each query triggers multiple sequential model calls, these delays then compound across every downstream step. Closing this gap is challenging because the relevant infrastructure signals (queue depths, KV-cache pressure, latencies) are dynamic and noisy, and they must drive three different decisions: planning, per-step routing, and scheduling. We introduce INFRAMIND, a framework that makes the entire multi-agent stack infrastructure-aware. An infra-aware planner conditions topology and role selection on real-time system load and remaining budget, biasing toward simpler graphs under congestion and richer ones at low load. An infra-aware executor then observes per-model queue depths, cache utilization, and response latencies at each agent step to decide which model to call and how deeply to reason; a budget-aware scheduler further reorders each model's queue so that urgent requests are served first. Cast as a hierarchical constrained MDP and solved end-to-end via reinforcement learning, the system learns to balance quality against latency automatically. Across five benchmarks, INFRAMIND delivers up to +7.6 pp accuracy over the prior baseline at low load with up to 7x lower latency, and sustains up to 99.9% SLO compliance under high load where every baseline drops below 50%.

---

### The Power of Test-Time Training for Approximate Sampling

Authors: Noah Golowich, Ankur Moitra, Dhruv Rohatgi
Published: 2026-06-09
Categories: cs.DS, cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2606.11437v1

Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the rise of generative AI, as sophisticated sampling procedures from LLMs have been proposed to solve challenging reasoning problems. The efficacy of such sampling algorithms is limited, however, by the relationship between the LLM and the particular sampling task at hand, which has motivated the framework of test-time training (TTT). TTT works by updating a model's weights in response to partial generations and reward feedback received at inference time, thus adapting to the particular problem. In this work, we propose a formalization for TTT as the problem of producing a sample from a given probability measure $μ^\star$ belonging to a known class ${F}$ of distributions, given an oracle $\hat μ$ which yields approximate density estimates for $μ^\star$. This is closely related to the problem of reducing sampling to approximate counting studied in seminal works of Jerrum, Valiant & Vazirani (1986) and Jerrum & Sinclair (1989): namely, when ${F}$ is the class of all distributions, it coincides exactly with the aforementioned counting-to-sampling reduction. In this paper, we first show a quadratic lower bound on the query complexity of sampling from $μ^\star$ given query access to $\hat μ$ (for sufficiently large classes ${F}$), thus showing that the random walk approach proposed by Jerrum & Sinclair (1989) and refined by Hayes & Sinclair (2010), is optimal. This answers an open question posed by Hayes & Sinclair. We then show that this lower bound can be circumvented if the size of ${F}$ is bounded appropriately. As we discuss, this latter result can be viewed as an abstraction of TTT, and thus represents a starting point for the development of a principled theoretical framework for TTT.

---

### Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

Authors: Kexin Ding, Yang Zhou, Can Jin, Feng Tong, Mu Zhou, Dimitris N. Metaxas
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11435v1

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications. Consequently, the field is undergoing an emerging paradigm shift from isolated skill creation to automated, evaluation-driven skill evolution. In this survey, we systematically examine the landscape of skill evolution and evaluation beyond foundational skill creation. We categorize evolution into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, showing how each element contributes to improving skill utility and reliability. We also provide an analysis of six skill-centric benchmark categories, identifying structural gaps in benchmark coverage, trade-offs, and metric richness to advance skill research. Finally, we identify open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe. The project URL is https://github.com/Cassie07/AgentSkill_Survey

---

### Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

Authors: Shira Vansover-Hager, Matan Schliserman, Ofir Schlisselberg, Tomer Koren
Published: 2026-06-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.11431v1

Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training. This raises a basic robustness question, crucial to reproducibility and reliability: how sensitive are MD dynamics to their inputs? We focus on initialization, often itself a pretrained or previously aligned model. Quadratic-regularized MD, including GD and Mahalanobis geometries, is well-known to be stable for convex smooth objectives. We show a sharp contrast: once the regularizer is non-quadratic, MD can be exponentially more sensitive to initialization than GD, even with a well-conditioned regularizer in Euclidean norm. We give a three-dimensional construction with a convex, smooth objective and a strongly convex, smooth, well-conditioned regularizer where an initial $\varepsilon$ perturbation is quickly amplified to $\min\{\text{polylog}^{-1}(1/\varepsilon), \varepsilon e^{Ω(ηT)}\}$ after $T$ iterations of MD with step size $η$. For canonical KL-regularized MD on the simplex, we show that even linear objectives can amplify an initial $\varepsilon$ perturbation exponentially fast in high-dimensional or near-boundary regimes. Finally, we show that adding a Bregman regularization term toward an anchor point can stabilize the dynamics while largely preserving the optimization guarantees, and that the choice of anchor is crucial: anchoring at the initialization only partially mitigates the instability, whereas anchoring at a fixed point yields a more stable mechanism.

---

### Towards a Bridge Layer Between Bibliographic and Formalized Mathematical Knowledge

Authors: A. Mayeux
Published: 2026-06-09
Categories: cs.DL, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2606.11430v3

Mathematical knowledge is split between bibliographic databases (e.g., MathSciNet, zbMATH Open) and formal proof libraries (e.g., Lean's mathlib), preventing unified access to published results and their formalizations. We propose a relational bridge-database that aligns publication metadata with formal artifacts, providing an interoperability layer between mathematical literature and machine-verifiable proofs. We introduce a paper-level formalization score that measures how much of a publication is covered in formal systems, together with a correctness profile recording what machine verification has established about each printed statement: certified, corrected, uncorrected, open, or untested. As a feasibility study, we show how such scores can be estimated via cross-document alignment between informal texts and Lean formalizations, enabling large-scale analysis of formalization coverage. We further outline a concrete construction pathway: multi-source scoring over heterogeneous formalization artifacts, an agentic collection workflow with direct author submission, a dual validation policy, algorithmic then human, and a global formalization score of indexed mathematics. This framework is a step toward integrating bibliographic and formal mathematical ecosystems.

---

### Towards a Bridge Layer Between Bibliographic and Formalized Mathematical Knowledge

Authors: A. Mayeux
Published: 2026-06-09
Categories: cs.DL, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2606.11430v2

Mathematical knowledge is split between bibliographic databases (e.g., MathSciNet, zbMATH Open) and formal proof libraries (e.g., Lean mathlib), preventing unified access between published results and their formalizations. We propose a relational bridge-database that aligns publication metadata with formal artifacts, providing an interoperability layer between mathematical literature and machine-verifiable proofs. We introduce a paper-level formalization score that measures how much of a publication is covered in formal systems. As a feasibility study, we show how such scores can be estimated via cross-document alignment between informal texts and Lean formalizations, enabling large-scale analysis of formalization coverage. This framework is a first step toward integrating bibliographic and formal mathematical ecosystems into scalable, machine-actionable knowledge graphs linking publications to formal proof objects.

---

### Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains

Authors: Zilai Wang, Natarajan Balaji Shankar, Mohan Shi, Kaiyuan Zhang, Abeer Alwan
Published: 2026-06-09
Categories: eess.AS, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2606.11429v1

Speech foundation models often struggle in low-resource domains due to domain mismatch and data scarcity. We propose Gumbel-BEARD, a domain adaptation framework that automates Whisper encoder layer selection via an end-to-end trainable hard Gumbel-Softmax selector. It enables self-supervised adaptation with a BEST-RQ objective that dynamically adapts to target acoustic characteristics without manual tuning. Experiments on the MyST child speech corpus demonstrate efficiency and scalability: with 10 h of labeled data for fine-tuning, our method matches a fully supervised baseline trained on the complete 133 h labeled set. We establish new state-of-the-art word error rates (WERs) of 8.21% using Whisper-medium on MyST and 11.06% using Whisper-small on the OGI Spontaneous dataset. Evaluation on CORAAL further confirms robustness to adult dialectal domain shifts, with up to 6% relative WER reduction, highlighting the generalizability of our approach to diverse low-resource conditions.

---

### JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

Authors: Ge Shi, Jun Yin, Donglin Xie, Fangyi Liu, Yucan Li, Menglin Liu
Published: 2026-06-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2606.11425v1

Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries. We propose JailbreakOPT, a tool-assisted framework for improving iterative single-turn jailbreak prompt optimization. JailbreakOPT organizes diverse atomic jailbreak prompts into an attack tool library and composes them through a unified intra-episode optimization abstraction to generate stronger standalone attack prompts. To reuse experience across attack episodes, JailbreakOPT further frames tool selection as a contextual bandit problem and applies contextual Thompson sampling to guide exploration and exploitation based on past outcomes. Experiments across multiple target LLMs and attack goals show that JailbreakOPT improves attack success rate (ASR) while reducing the number of attacks until success (No.A) compared with atomic single-turn attacks and existing iterative optimization baselines. This paper may contain offensive or harmful content.

---

### SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing

Authors: Sai Ashish Somayajula, Marianne Menglin Liu, Chuan Lei, Fjona Parllaku, Daniel Garcia, Rongguang Wang, Syed Fahad Allam Shah, Ankan Bansal, Sujeeth Bharadwaj, Tao Sheng, Sujith Ravi, Dan Roth
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11424v1

Natural language interfaces to databases aim to translate user questions into executable SQL, yet remain brittle in real-world settings where questions are underspecified and schemas are large and ambiguous. Ambiguity across user questions, database schemas, and model interpretations are central failure modes in NL2SQL, leading to misaligned intent, incorrect schema grounding, and erroneous SQL generation. Existing approaches rely on human clarification or treat ambiguity as a schema representation problem, but these do not scale nor resolve ambiguity autonomously. We propose SOMA-SQL to automatically resolve ambiguity via targeted synthetic query log and ambiguity-driven probing. SOMA-SQL constructs synthetic query log to ground schema interpretation and guide candidate SQL generation; it then executes targeted probing queries, driven by a structured ambiguity taxonomy and candidate disagreements, to produce disambiguation evidence for final SQL selection and repair. This active approach to ambiguity discovery and resolution generalizes across unseen schemas and query distributions without human-in-the-loop. Experiments on six public benchmarks demonstrate that SOMA-SQL improves execution accuracy by 13.0% on average over state-of-the-art baselines, with gains of up to 16.7% on ambiguous questions.

---

### Context-Aware Multimodal Claim Verification in Spoken Dialogues

Authors: Chaewan Chun, Delvin Ce Zhang, Dongwon Lee
Published: 2026-06-09
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2606.11420v2

Spoken factual claims often occur within multi-turn conversations, where surrounding dialogue can provide context unavailable from the claim alone. Yet most fact-checking research evaluates isolated text, leaving conversational audio under-studied. We introduce MAD2, a synthetic Multi-turn Audio Dialogues benchmark for spoken claim verification with 1,000 two-speaker dialogues, 1,230 sentence-level check-worthy candidate annotations, and approximately 10 hours of audio. We also propose calibrated multimodal fusion of a context-aware audio encoder and a dialogue-aware text model. Adding dialogue context improves verification across settings, although the gains vary by scenario. Past-only context often approaches local offline performance, suggesting its usefulness when future context is unavailable. Fusion achieves its highest mean advantage over text with full-dialogue context, but does not consistently or significantly outperform text across settings. Under full-dialogue context, exploratory subgroup results show greater performance variation across dialogue scenarios for text and fusion, but across spread styles for audio.

---

### Context-Aware Multimodal Claim Verification in Spoken Dialogues

Authors: Chaewan Chun, Delvin Ce Zhang, Dongwon Lee
Published: 2026-06-09
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2606.11420v1

Every day, millions absorb claims from podcasts and streams that no fact-checker ever sees. Spoken misinformation is built through conversation, where credibility comes not from facts alone but from how claims are framed, reinforced, or left unchallenged across turns. Yet fact-checking has focused on isolated text, leaving dialogue audio under-studied. We introduce MAD2, a new Multi-turn Audio Dialogues benchmark for spoken claim verification, containing 1,000 two-speaker dialogues with 3,368 check-worthy claims and approximately 10 hours of audio, and propose calibrated multimodal fusion of a context-aware audio encoder and a dialogue-aware text model. Across settings, adding dialogue context improves verification, but the gains depend on scenario type. Using only preceding context often matches offline performance, supporting live-moderation settings, and audio contributes most when transcript-based models are destabilized by additional context. Overall, conversational structure matters more for verification than misinformation framing.

---

### Signed Compression Progress on a Sealed Audit is Goodhart-Resistant

Authors: Ayush Mittal, Dhruv Gupta
Published: 2026-06-09
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2606.11417v1

Compression progress is a long-standing proposal for intrinsic motivation: reward an agent when its world model becomes better at predicting or compressing experience. The folk claim is that this reward is "credible" because it is paid only for learning. We make this precise and prove it. If intrinsic reward is the signed decrease of a fixed sealed-audit loss, r_t = E(theta_{t-1}) - E(theta_t), then cumulative reward telescopes exactly to endpoint audit improvement, so no policy can push reward up indefinitely while true audit performance stagnates or degrades. For finite audit panels the same result holds with a sharp false-positive budget: cumulative empirical reward is at most true audit improvement plus 2 Delta_n(F, delta), the uniform audit deviation of the model class. This is horizon-free: adaptivity over time costs nothing once the sealed panel uniformly controls the class. The theorem also identifies the failure modes: the guarantee disappears if progress is clipped, scored on the agent's own stream, exposed to a high-capacity model on a reusable panel, or applied to a neural class that makes Delta_n vacuous. We give a Lean 4 mechanization of the structural core (telescoping, the finite-audit bound, finite Gibbs, and the entropy floor) and an experiment suite on ARC-TGI grid-transformation generators with adaptive holdout attacks. Experiments confirm the theory: finite-audit deviation scales as n^{-0.527}; signed progress resists clip-farming, stream leakage, and noisy-TV curiosity; naive reusable audits are exploitable by black-box scalar feedback, while standard release defenses keep the attack below the 2 Delta_n threshold. Signed compression progress on a sealed audit is an accounting signal of genuine improvement.

---

### MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation

Authors: Yukuan Zhang, Mengxin Zheng, Qian Lou
Published: 2026-06-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2606.11416v1

Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Party Computation (MPC) software do not yet exist, and directly transplanting general-purpose benchmarks such as SWE-bench fails on three structural fronts: (i) MPC repositories are dominated by generic Python infrastructure rather than cryptographic logic; (ii) high-value MPC fixes lack the standardized tests rigid extraction pipelines require; and (iii) standard fail-to-pass evaluation is insufficient for code that must also be cryptographically safe. MPC is increasingly deployed for privacy-preserving machine learning, biomedical collaboration, and secure analytics. Existing MPC-specific code-synthesis efforts cover only operator-level or single-framework tasks; evaluating LLM agents on real repository-level MPC repair instead demands MPC-aware data curation and a verifier matched to the security and numerical-fidelity guarantees MPC programs must obey neither of which existing benchmarks provide. We introduce MPC-Patch-Bench, a repository-level benchmark organised around two frameworks. (1)The Data Curation Framework combines a domain-specific curation agent that filters raw pull requests through three cryptographic layers with a human-AI completion engine that synthesizes missing problem statements and Fail-to-Pass/Pass-to-Pass tests, yielding 205 fully verified instances. (2)The MPC Verifier provides dedicated security and numerical-fidelity checks via dynamic differential testing against plaintext oracles and MPC-specific static analysis rules that flag unsafe reveals, insecure arithmetic, and illegal public/private casts. The strongest evaluated LLM functionally resolves only 22.9% of MPC-Patch-Bench tasks; the MPC Verifier further reduces verified resolution to 17.1%, with up to 40% of functionally-passing patches rejected for cryptographic or numerical-fidelity violations.

---

### Spatially Masked Regression Reveals Local and Distributed Predictability in Electrophysiological Recordings

Authors: Maryam Ostadsharif Memar, Nima Dehghani
Published: 2026-06-09
Categories: q-bio.NC, cs.LG, physics.data-an, q-bio.QM
arXiv: https://arxiv.org/abs/2606.11415v1

Neural recordings are often interpreted as local measurements, yet the signal at any one sensor can also reflect structured activity distributed across the broader network. This raises a basic question: to what extent does an electrode's signal reflect local versus distributed information in the underlying system? More specifically, how much of an electrode's activity is carried by its immediate neighborhood, and how much is embedded more broadly across the array? We address this with a Spatially Masked Regression (SMR) framework that reconstructs each electrode's timeseries from the remaining electrodes while excluding a configurable neighborhood around the target. By progressively increasing this mask, spatial locality becomes an experimental control for quantifying how much predictive information survives after nearby channels are withheld. We apply SMR to intracranial EEG with heterogeneous electrode coverage and to scalp EEG with standardized montages over sensorimotor cortex. Using distance correlation between original and reconstructed signals, we find strong within-subject reconstruction in both modalities, substantial residual predictability even when local neighbors are excluded, and markedly stronger cross-subject transfer in EEG than in iEEG. Masking shows that nearby electrodes contribute strongly to reconstruction but do not account for all of it, indicating that individual channels reflect both local redundancy and broader distributed structure. Surrogates that preserve selected marginal or spectral properties while disrupting phase structure or temporal ordering substantially reduce performance, supporting the conclusion that SMR depends on structured temporal and cross-channel organization rather than on marginal statistics alone. These results position SMR as an interpretable framework for quantifying the balance between local and distributed information in recordings.

---

### Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

Authors: Malikeh Ehghaghi, Boglárka Ecsedi, Marsha Chechik, Colin Raffel
Published: 2026-06-09
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2606.11409v1

Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly. In practice, the computational expense of different attack strategies can vary by orders of magnitude. Consequently, ASR at a fixed budget can obscure the true effort required to jailbreak a model, thereby making it hard to determine whether an attack's cost justifies its payoff to the attacker. We propose a compute-aware evaluation framework based on computational pressure, measured in cumulative floating-point operations (FLOPs), as a proxy for adversarial effort. We introduce risk-compute curves, which map compute budgets to attack risk, and derive two metrics that summarize the average pressure required for a given attack to succeed. Across ten models spanning three families and four different stages in language model training and alignment, evaluated with three attack strategies (gradient-based, iterative refinement, and template-based) on two jailbreak robustness benchmarks, we find: (1) alignment training has non-monotonic effects on compute-space robustness; (2) scaling model size reduces gradient-based attack effectiveness but has limited impact on cheaper template-based attacks; (3) gradient-based attacks optimized on a surrogate model can transfer to a separate target model, providing a way to reduce attacker costs; (4) compute cost varies by up to ${\approx}5{\times}$ across harm categories within a single model; and (5) safety-aligned RL increases aggregate cost while leaving some categories disproportionately accessible. We release our framework to enable compute-aware risk assessment and evaluation.

---

### GraphGP: Scalable Gaussian Processes with Vecchia's Approximation

Authors: Benjamin Dodge, Philipp Frank, Susan E. Clark
Published: 2026-06-09
Categories: stat.CO, astro-ph.IM, stat.ML
arXiv: https://arxiv.org/abs/2606.11402v1

Gaussian processes are a powerful tool for modeling continuous fields, but their naive $\mathcal{O}(N^3)$ computational cost and $\mathcal{O}(N^2)$ memory requirement often limit their practical use. Vecchia's approximation is a sparse precision matrix approximation for stationary, decaying kernels that conditions each point only on its $k$ nearest neighbors. We present GraphGP, a GPU algorithm for Vecchia's approximation that scales to nearly a billion parameters with linear time and memory requirements, handling arbitrary point distributions over a large dynamic range. Our key contributions are (1) a bit-reversed k-d tree ordering that allows efficient neighbor searches while also maximizing batch parallelism, and (2) a differentiable CUDA implementation, which is substantially faster and more memory efficient than our pure JAX baseline. GraphGP provides the building blocks for inference, including forward generation, inverse application, log-determinant, and kernel parameter derivatives.

---

### Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

Authors: Tsung-En Lin, Hung-Yi Lee
Published: 2026-06-09
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2606.11400v1

Large Audio-Language Models (LALMs) excel at audio understanding but expose little about where in an audio signal they attend. We introduce instruction-based vector steering, which constructs a steering vector by contrasting activations from differently instructed prompts while keeping the audio fixed. Through a systematic probe of LALM attention, we find that - unlike standard prompting or audio-based steering - this intervention significantly redistributes the temporal attention allocated to audio tokens, concentrating it on acoustically relevant regions. We then show that this attention shift is behaviorally meaningful: in a controlled three-event setting, reading out the temporal position of maximal steering-induced attention change recovers the location of a queried sound event without any training, attaining 60.87% and 68.72% overlap with ground-truth intervals on Qwen2-Audio and Audio Flamingo 3, far above direct prompting (31.84%, 46.75%) and random baselines (27.74%). Our results characterize a mechanistic property of instruction-based steering in LALMs and provide a training-free probe for the latent temporal structure these models encode.

---