# Research Papers — 2026-07 · bundle page 22 of 222 > Full-text markdown of papers #1051–1100 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/22 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/21.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/23.md) ### H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases Authors: Shusen Zhang, Junyi Hu, Ye Feng, Ziteng Wang, Zhaoyuan Pan, Guosheng Dong, Xiaojun Yuan, Jiangshou Hong, Xiangzhi Wang Published: 2026-07-29 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.00065v2 Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing representations lie at two extremes: single-vector retrievers often over-compress local relevance signals, while token-level late interaction retains every tokenizer subword at substantial indexing, storage, and scoring cost. This mismatch raises a natural question: can context-dependent phrases provide a useful retrieval unit between global vectors and tokens? We introduce H+ Embedding, a unified multi-granularity retriever that predicts variable-length phrase partitions, preserves uncovered tokens as singletons, and applies importance-guided unit selection with weighted MaxSim interaction. Across 16 scientific, medical, and bilingual tasks, its phrase retrieval branch exceeds the global retrieval branch by 6.91 macro nDCG@10. It also nearly matches Token while using 13.7% fewer document vectors and outperforms content-independent grouping rules under moderate vector budgets. Context-dependent phrase interaction therefore provides an intermediate quality-cost point between global compression and token-level interaction for practical retrieval systems. --- ### MPP-GNN: Subject-Adaptive Community Detection for fMRI-Based Alzheimer's Disease Classification Authors: Yang Zhang, Xiao Zhou, Jonathan Warrell, Avram Holmes, Xuan Zhang, Mark Gerstein Published: 2026-07-29 Categories: cs.LG, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2607.28681v1 Functional magnetic resonance imaging (fMRI) is a widely used technique for studying the brain. Recent methods that utilize graph neural networks (GNNs) for analysis of brain functional connectivity have shown great potential for the classification of brain disorders, such as Alzheimer's disease (AD). However, these methods often assume a preset number of functional modules across all subjects, which overlooks inter-subject variability. In addition, the discovered modules are rarely used to directly guide the learned connectivity patterns. Here, to address these issues, we propose a Meta Probabilistic Pooling GNN (MPP-GNN). We frame the model's task as a coupled, bilevel optimization that performs adaptive graph partitioning hierarchically to discover subject-specific modules and then uses the discovered brain modules as an explicit prior to guide edge refinement and representation learning. We validate MPP-GNN on two public datasets for AD classification, achieving the highest AUC in comparison to established baselines for both datasets. Furthermore, our analysis demonstrates that MPP-GNN shows significant alignment with the canonical functional-network organization defined by the Yeo brain atlas and reveals a network-level dedifferentiation pattern for AD. --- ### TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking Authors: Yixin Peng, Kehao Li, Stefan Decker Published: 2026-07-29 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.28680v2 Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipelines that retain either compact or extensive table content as contextual evidence, and then formulate entity linking as a language generation task for instruction-tuned models; recent systems further incorporate explicit reasoning to disambiguate challenging mentions. However, their training supervision is usually static: fixed preference data cannot adapt to the residual errors of an evolving model, while variations in reasoning length can bias sequence-level preference learning. To address these limitations, we present TELLER: Table Entity Linking through Learning from Errors and Reasoning. We first retrieve and rank Wikidata candidates and retain reduced table evidence in the prompt. The direct-answer path applies iterative direct preference optimization and refreshes its preference data with residual errors from the updated model. The reasoning path uses filtered and compressed chain-of-thought rationales for supervised fine-tuning, followed by our iterative length-normalized regularized preference optimization. On the TableInstruct entity-linking subset, the direct-answer path improves accuracy from 94.35\% to 94.50\%; on the MammoTab V2 evaluation set, it improves accuracy from 87.59\% to 88.20\%. The reasoning path improves accuracy from 92.90\% to 92.95\% on TableInstruct and from 79.09\% to 81.85\% on MammoTab V2, while maintaining high rates of complete reasoning generation. These results show that iterative preference learning benefits both concise entity prediction and explicit reasoning. --- ### TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking Authors: Yixin Peng, Kehao Li, Stefan Decker Published: 2026-07-29 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.28680v1 Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipelines that retain either compact or extensive table content as contextual evidence, and then formulate entity linking as a language generation task for instruction-tuned models; recent systems further incorporate explicit reasoning to disambiguate challenging mentions. However, their training supervision is usually static: fixed preference data cannot adapt to the residual errors of an evolving model, while variations in reasoning length can bias sequence-level preference learning. To address these limitations, we present TELLER: Table Entity Linking through Learning from Errors and Reasoning. We first retrieve and rank Wikidata candidates and retain reduced table evidence in the prompt. The direct-answer path applies iterative direct preference optimization and refreshes its preference data with residual errors from the updated model. The reasoning path uses filtered and compressed chain-of-thought rationales for supervised fine-tuning, followed by our iterative length-normalized regularized preference optimization. On the TableInstruct entity-linking subset, the direct-answer path improves accuracy from 94.35\% to 94.50\%; on the MammoTab V2 evaluation set, it improves accuracy from 87.59\% to 88.20\%. The reasoning path improves accuracy from 92.90\% to 92.95\% on TableInstruct and from 79.09\% to 81.85\% on MammoTab V2, while maintaining high rates of complete reasoning generation. These results show that iterative preference learning benefits both concise entity prediction and explicit reasoning. --- ### Multi-Agent Planning with Spatio-Temporal and Topological Constraints using STL-GO Authors: Sheryl Paul, Vidisha Kudalkar, Anand Balakrishnan, Lars Lindemann, Alberto Speranzon, Jyotirmoy V. Deshmukh Published: 2026-07-29 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.28679v1 Multi-agent planning problems arise in a variety of engineering applications, such as multi-robot wildfire fighting and unmanned aerial inspection in factories. A particular challenge is the existence of spatio-temporal (i.e., when and/or where an agent should do what) and topological constraints (i.e., how agents should interact), as typically formalized via the notion of graphs. Over the last years, various frameworks have been proposed that can capture such constraints via spatio-temporal logics. We focus here on spatio-temporal logic with graph operators (STL-GO), a recent formalism that supports reasoning about multiple agents and their topologies, such as sensing, communication, and task topologies. In this paper, we consider the problem of planning multi-agent paths that satisfy constraints written in STL-GO. This problem is particularly challenging due to the need of encoding multiple, potentially time-varying graphs via the graph operators inherent to STL-GO. We present two encodings of this problem, one based on mixed-integer programming (MIP) and another based on satisfiability modulo theory (SMT), with soundness guarantees. We provide a unified interface for specifying agent constraints, their graph topologies, and the STL-GO specification, enabling seamless use of both methods and facilitating direct comparison between them. We evaluate both encodings on a multi-UAV search-and-rescue benchmark, ablating over team size and graph complexity, highlighting the expressiveness of the proposed encodings under dynamic multi- graph interactions. --- ### ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding Authors: Xinkui Zhao, Enbo Chen, Yifan Zhang, Chang Liu, Guanjie Cheng, Naibo Wang, Yueshen Xu Published: 2026-07-29 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.28678v1 Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity cues under aggressive compression and segment-wise processing. They also rely heavily on vector similarity retrieval, which can surface semantically related yet identity-mismatched evidence, leading to entity confusion, error propagation, and hallucinated answers. We propose ViSAGE, a multimodal agentic memory framework that constructs self-correcting, entity-centric memories. Specifically, ViSAGE anchors entity identity via cross-modal binding over long temporal ranges. It then applies bidirectional memory refinement to propagate delayed identity evidence, retroactively unifying historical records and improving future reasoning. We also introduce multi-agent cross-verification to assess retrieved evidence under an identity-evidence alignment onstraint, enabling abstention instead of unsupported answers when evidence is missing. Extensive results demonstrate that ViSAGE consistently outperforms the strongest baseline, achieving 5.9% higher accuracy. --- ### Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support Authors: Shayndhan Sivanathan, Shravan Nageswaran, Mehdi Zadem, Ryaan Sultan, Nicolas von Mallinckrodt, Max Solovyev, Alexey Matyushkin, Sumon Sadhu, Gabriele C DeLuca, Sanjeeva Jeyaretna, James Hillis, Manoj Ramachandran et al. Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.28677v1 LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning. These developments have accelerated the use of LLMs for symptom assessment and clinical decision support in diagnostic and treatment guidance, administrative documentation, and rules-based alert enhancement. This Perspective concerns the most consequential of these applications: the autonomous triage of self-presenting, undifferentiated patients, with little or no clinician in the loop. For that task, the evidence of safety does not yet exist. The gap is not in medical knowledge but in the fidelity of clinical evaluation: a model optimized to continue the most probable text is not optimized to act safely when the safe answer is the improbable must-not-miss diagnosis. Safe triage is not the selection of the most likely diagnosis; it is a sequential decision under asymmetric cost, in which the single catastrophic miss outweighs many false alarms, and the decisive signal may be one the patient has not volunteered - and that the model has not been trained to seek. The core deficit is therefore one of information gathering under uncertainty. Under incomplete histories, LLM systems may fail to show the behaviors safe triage requires: broadening the differential; seeking the missing red flag; lowering the threshold for escalation; deferring judgement until sufficient information is obtained; and escalating concern where high-harm diagnoses remain unexcluded. These modes of failure for LLMs can be difficult to detect considering that evaluations to date often use complete, well-curated, confidence-gated simulations. The application of LLMs under these conditions may be amplified by assistant-like behaviors and positive bias, including credulity, agreeableness, and miscalibration - when these are not constrained by clinical triage logic. --- ### SciDataSailor: Deep Scientific Data Exploring Authors: Jiyong Rao, Yicheng Qiu, Chi Zhang, Chunfeng Song, Runkai Zhao Published: 2026-07-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.28098v1 Scientific datasets are commonly organized as hierarchical repositories containing heterogeneous and interdependent files, making their inspection, integration, and analysis labor-intensive and reliant on domain expertise. Although large language model (LLM) agents have advanced substantially in planning, reasoning, and tool use, existing research has largely overlooked their ability to interact with real scientific data assets through executable environments. We introduce Deep Scientific Data Exploration, an agentic task paradigm in which agents navigate repositories, interpret heterogeneous files and schemas, execute analyses, integrate cross-file evidence, and produce conclusions grounded in executed observations. To operationalize this paradigm, we present SciDataSailor, a framework for synthesizing tool-interactive trajectories by balancing broad exploration with targeted exploitation. SciDataSailor instantiates trajectory synthesis as Monte Carlo Tree Search (MCTS) with four task-specific mechanisms: difficulty-stratified exploration seeds, dual-feedback first-play urgency, hierarchical strategy-to-tool action generation, and entropy-guided branching. Using this framework, we construct SciDataSailor-SFT-2K for supervised fine-tuning and SciDataSailor-Bench for evaluation, with the latter comprising 627 meta-information summarization tasks and 586 scientific question-answering tasks across 27 datasets spanning the life, earth, and physical sciences. --- ### HOMER: Huber-of-Means for Efficient and Robust Estimation in Hilbert Spaces Authors: Kisung You, Boram Cho Published: 2026-07-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.27532v1 Heavy tails weaken high-confidence control for the empirical mean. Geometric median-of-means (MOM) also lacks a threshold that moves toward mean efficiency. We propose \emph{HOMER}, or Huber-of-Means for Efficient and Robust Estimation. HOMER aggregates block means through a radial Huber center. Its canonical and pseudo-Huber forms bound each block score and interpolate between median-like robustness and the empirical mean. We establish a Hilbert-space majority theorem and a MOM-order deviation bound under a finite second moment. Canonical HOMER recovers the sample mean inside its quadratic region. Pseudo-HOMER approaches the sample mean as the threshold grows. It also admits asymptotic linearity and consistent sandwich covariance estimation around the population block-Huber target. Under a finite third moment, fixed finite-dimensional projections support mean inference at the usual parametric rate. This result requires growing block sizes and counts, with block sizes increasing faster. Heavy-tailed simulations show that HOMER remains stable when a minority of block summaries is displaced. On clean Gaussian data, both versions closely approach the empirical mean's efficiency. Finite-block sandwich intervals undercovered, especially for skewed functional data. Further studies show failure when contamination affects most blocks or compromises ordinary within-block means. --- ### When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment Authors: Xiao Yue, Guangzhi Qu Published: 2026-07-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27530v1 Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect, such as a class label or molecular property. Multiple heads can separate these aspects, but a change in the query head may alter retrieval even when the wrong text is sent to that head. Such behavior demonstrates architectural channelization, not necessarily semantic routing. We examine the conditions under which this distinction can be resolved. Our controlled version of MV-GTA uses deterministic, verifiable text segments; isolated text encoders; view-specific graph heads; and relevance derived from external labels or RDKit descriptors. Correct routing and per-sample derangements form a causal test of whether retrieval depends on content. On BBBP and BACE, correct routing improves label and property nDCG by 0.305 to 0.685 over deranged training. The expected graph head exceeds the best wrong head by 0.303 to 0.453. Topology does not specialize consistently across the two datasets. In a matched three-seed comparison, one joint model obtains mean topology, label, and property nDCG of 0.720/1.000/0.877; three separately trained Single specialists obtain 0.633/0.976/0.859. Property paraphrase augmentation also improves unseen-template nDCG by 0.140 and 0.147 over a matched-exposure canonical control. Consistency and hard-template extensions, however, reduce canonical retrieval in some settings. The evidence is therefore limited to explicit, externally grounded label and property routing and observed multi-interface consolidation. It does not establish free-form routing, consistent three-view specialization, statistical equivalence to specialists, or superior downstream prediction. --- ### Latent-Kernel Discrete Flow Maps for Few-Step Generation Authors: Mansoor Ahmed, Yue-Tsz Fan, Hemanth Venkateswara, Murray Patterson Published: 2026-07-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27529v1 Discrete diffusion and flow-matching models denoise a sequence over many steps, but to keep each step cheap, they factorize the transition across positions and decide every token independently. This makes few-step generation challenging for text when the target couples two positions, such as a subject and a verb that must agree. An independent update commits to them separately, and many function evaluations are spent repairing the mismatch. Existing few-step methods buy back the lost correlation by distilling or rectifying a slow teacher, and so inherit the teacher's quality ceiling. We ask instead whether a model can express correlated steps natively, and answer with Latent-Kernel Discrete Flow Maps (LKF), a from-scratch flow-map kernel that is a mixture of M factorized components tied by a single shared latent. Conditioned on the latent, each component is cheap, and the mixture is summed over the latent in closed form for small M. We show that a single step places mass on correlated completions with the same sampling time complexity as a factorized model, since one latent is drawn per sequence and reused across the entire denoising trajectory. We also show that the Masked Diffusion Language Model (MDLM) is a special case of our LKF model at M=1. The experiments for unconditional text generation on the One-Billion-Word (LM1B) and WikiText-103 benchmarks show that our LKF model learns strongly heterogeneous components and improves generative perplexity by 2.1x to 3.3x over the likelihood baselines without losing diversity. The gain grows with M, and at M=8, it surpasses distilled and rectified few-step samplers. The source code is available at: https://github.com/mansoor181/lkf.git --- ### ThreatForest: Multi-Agent Attack Tree Generation with Pluggable TTP Framework Mapping Authors: Cristian Leo, Anton Dykyi, Danny Cortegaca, Daniel Begimher, Prakash Jha Published: 2026-07-29 Categories: cs.CR, cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2607.27528v1 Threat modeling is essential for secure software development, yet manual analysis of cloud-native architectures is slow and demands scarce security expertise. We present ThreatForest, a multi-agent system that generates structured attack trees from source code repositories, maps attack steps to adversary tactics, techniques, and procedures (TTPs) from a pluggable set of frameworks (MITRE ATT&CK, CAPEC, and cloud-specific threat matrices), and synthesizes actionable mitigations. ThreatForest decomposes threat modeling into a multi-stage agent pipeline -- repository analysis, context refinement, threat generation, parallel attack-tree construction with TTP mapping and mitigation synthesis, and report generation -- orchestrated as a directed graph with deterministic verification gates, bounded retries, and three human-in-the-loop validation points. A domain-specific sentence-transformer maps each attack step to candidate techniques by cosine similarity; we show empirically that this embedding stage, not the surrounding pipeline, is the dominant accuracy bottleneck. We evaluate ThreatForest across seven application domains on a sixteen-dimension rubric, scored by a panel of independent LLM raters with an adversarial verification pass and expert review. Panel-measured quality reaches 0.63-0.68 (on a 0-1 scale) for threat statements, attack trees, and mitigations, but only 0.29 for embedding-only TTP mapping -- a gap stable across all seven domains that isolates the binding constraint. A controlled single-call baseline on the same model more than doubles mapping defensibility, pinning the limitation on the embedding encoder rather than the multi-agent design. To our knowledge, ThreatForest is the first end-to-end system that turns a code repository into TTP-mapped attack trees with evidence-based mitigations across adversary frameworks, with a reusable framework for benchmarking such systems. --- ### Hierarchical Reranking for Scalable Financial RAG System Authors: Joohyun Lee, Sungwoo Hong Published: 2026-07-29 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.27523v1 Analyzing financial documents such as 10-K filings, tabular disclosures, and macroeconomic reports demands expert reasoning and extensive time. However, existing Retrieval-Augmented Generation systems often struggle to process hybrid text-table structures or the massive scale of financial documents. To address these challenges, we propose Hierarchical Reranker, a RAG framework designed to improve retrieval performance and generative reliability across large-scale financial datasets. The system integrates three key innovations: Pre-Retrieval Optimization, enhancing query clarity and search efficiency through normalization, keyword expansion, and table transformation; Hierarchical Reranker Architecture, improving retrieval precision through a two-stage ranking mechanism; and Long-Context Management, preserving reasoning accuracy through adaptive input partitioning and fusion under extensive contexts. Across multiple benchmarks, including FinQA, FinanceBench, and ConvFinQA, the proposed system achieved an NDCG@20 score of 0.7918 and demonstrated superior factual consistency. Its robustness was further validated by achieving second place in the ACM-ICAIF '24 FinanceRAG Challenge. This work presents a deployable, domain-optimized RAG pipeline that enhances both the accuracy and scalability of financial reasoning, paving the way for automated audit reporting and quantitative investment analysis. The source code will be made publicly available on GitHub upon acceptance. --- ### Expanding Data-Agnostic Pivotal Instances Selection Models with Proximity Trees and Ensemble Learning Authors: Alessio Cascione, Mattia Setzu, Cristiano Landi, Paolo Maria Mancarella, Riccardo Guidotti Published: 2026-07-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.27522v1 As decision-making processes grow more complex, machine learning tools have become essential for tackling business and societal challenges. However, many existing methods rely on decision-making procedures that are difficult to interpret. Since humans naturally make decisions by comparing new cases with a few representative examples, we aim to design an approach that selects such pivots to construct an interpretable predictive model. Inspired by decision trees, we propose a hierarchical, interpretable-by-design pivot selection model based on the similarity between pivots and input instances. Our method functions both as a pivot selection technique and a standalone predictive model. Extending beyond single pivots, we incorporate pairs of pivots that are used by proximity and oblique trees, as well as ensembles, which enhance the versatility and effectiveness of our proposal. Additionally, our approach is data modality-agnostic, leveraging pre-trained networks for data transformation. Experiments across diverse datasets, including tabular data, text, images, and time series, demonstrate the effectiveness of our approach, outperforming alternative instance selection strategies and achieving competitive results against state-of-the-art interpretable models while maintaining a minimal number of pivots. --- ### Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks Authors: Jeff Mohl, Nelson Gardner-Challis, Magda Dubois, Harry Coppock, Benjamin Allan-Rahill, Kaelan Yim, Damian Sójka, James Mann, Justin Olive Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27518v1 Capabilities of frontier models are often assessed using agentic benchmarks. To trust these results, benchmarks must accurately measure what they claim to and be free from invalidating flaws. Previous manual audits of benchmarks such as SWE-Bench-Verified have uncovered several validity issues in transcripts. However, manual review is difficult to scale, and it is unclear whether automated methods can reliably surface flaws that compromise benchmark validity. In this paper, we developed AI scanners to detect four types of validity issues: ground truth access, tool failure, guessing vulnerability, and answer format ambiguity. We produced grading rubrics for each to instruct human labeling, and evaluated the scanners against human labels on a held-out test set of Inspect Evals benchmarks. Our scanners identified several verified quality issues in five widely used benchmarks, including cases unlikely to be caught by random manual inspection. Not all cases were identified, and scanner performance varied substantially across benchmarks, criteria and models. We highlight several open challenges to be addressed to improve scanners for stronger quality assurance claims, including broader standardization gaps in the evaluation field that degrade scanner performance. Together, these results serve as a proof of concept for using automated transcript analysis to audit benchmark quality more broadly. --- ### Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models Authors: Germans Savcisens, Samantha Dies, Courtney Maynard, Tina Eliassi-Rad Published: 2026-07-29 Categories: cs.CL, cs.MA, cs.SI arXiv: https://arxiv.org/abs/2607.27512v1 Large language models (LLMs) are increasingly deployed in multi-agent environments. However, the processes by which beliefs form and propagate among interacting LLMs remain poorly understood. We introduce CoevolveSim, a framework for studying belief diffusion within networked LLM populations. CoevolveSim allows us to isolate and study three factors: domain specialization, social-role assignment, and social network structure. Within this framework, generalist and specialist LLM agents exchange and revise beliefs. In each round, an LLM agent observes a summary of its neighbors' beliefs before updating its own. We run 1,280 controlled simulations spanning four scenarios, two network structures, and 20 medical-indication statements. We find that persona-style role assignment and network structure reshape individual belief revision but have minimal effect on population-level consensus. In contrast, introducing (finetuned) specialist LLMs more than doubles the shift in consensus and gives rise to consistent asymmetries in exerted influence. We further show that simple persistence-based opinion-dynamics models reproduce collective outcomes in all-generalist LLM populations, whereas heterogeneous LLM populations require population-level belief composition to reproduce consensus and agent identity to predict individual belief transitions. Our results indicate that realistic simulation of belief diffusion in multi-agent LLM systems requires a diverse set of underlying LLMs, not persona prompting alone. --- ### Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response Authors: Elle Lazarski, Jaime Fernández Fisac Published: 2026-07-29 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.27508v1 Assistance games formalize human-robot collaboration under asymmetric information: the human knows the goal, while the robot must infer it from observation and interaction in order to assist effectively. In general, computing optimal assistance game strategies online is intractable, since exact solutions require planning in a POMDP. We identify a class of assistance games in which pragmatic-pedagogic reasoning resolves goal uncertainty in a single time step, rendering the full-horizon game exactly solvable by a tractable best-response procedure. Within this class, we show that mainstream inverse optimal control exhibits an inference ceiling that hinders alignment, while pragmatic-pedagogic reasoning overcomes this barrier by immediately disambiguating goals through actions that look equivalent under task execution alone. Finally, we validate our theoretical results and proposed method on a simple collaborative block-building example. --- ### Sparsity Induced Identifiability in Matrix Tri-Factorisation Authors: Tingting Mu Published: 2026-07-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27507v1 Matrix factorisation is a fundamental tool for exploiting low-dimensional structure in high-dimensional data, with applications such as data compression, denoising, structure discovery, interpretable representation learning, and dimensionality reduction. Compared to conventional two-factor models, matrix tri-factorisation provides greater modelling flexibility, while sparsity constraints often improve both interpretability and recovery performance. Although the role of sparsity has been extensively studied for two-factor matrix factorisation, rigorous theoretical guarantees for general real-valued matrix tri-factorisation remain largely unexplored. To address this gap, we establish, to the best of our knowledge, the first rigorous theoretical study for sparsity-induced identifiability in general real-valued matrix tri-factorisation. Our analysis is enabled by a novel decomposition strategy that transforms the original problem into two coupled auxiliary factorisation problems, while preserving the structural information necessary to the recovery of the original factor matrices from the observations. Building upon this decomposition, we derive recovery guarantees and structural consistency results that characterise how coefficient sparsity influences the sufficient recovery conditions, convergence behaviour, spectral approximation error, high-probability bounds, and structure preservation. Comprehensive Monte Carlo experiments validate the proposed theory and demonstrate close agreement between the theoretical results and empirical observations. --- ### Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models Authors: Shreyas Subramanian, Mecit Gungor, Vikram Elango Published: 2026-07-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27506v1 Language and embedding models used in RAG systems are conventionally assumed to require large-scale pretraining and explicit grounding supervision. We present B1ade, an efficient RAG architecture comprising two purpose-built components: a compact embedding model and a purpose-built SLM. B1ade-embed, a 335M parameter retrieval model constructed via parameter-free fusion of five pretrained encoders achieves top MTEB scores among sub-500M models with zero additional training, and B1ade-1B, an SLM trained on low-cost GPUs using Group Relative Policy Optimization (GRPO) on 723M tokens (2.2M examples) of curated context-question pairs with rewards that optimize only answer similarity. Our central finding is emergent attribution: despite receiving no explicit supervision for source citation, B1ade-1B cites retrieved passages in 42.4% of responses, exceeding the attribution rate of its training distribution by 5.5 percentage points. This demonstrates that grounding behavior can emerge as an accuracy-maximizing strategy under RL training, without explicit reward engineering. On standard QA benchmarks, B1ade-1B achieves 81.82% on PopQA, 65.8% on PubMedQA, and 51.09% on FEVER. In end-to-end RAG evaluation, B1ade-1B achieves an average score of 0.654 across correctness, completeness, coherence, and faithfulness, a 10.8% improvement over the SFT, while closing the gap with models 1.5x its size. These results show that strategic model composition and reward design suffice for resource-efficient RAG, without large-scale pretraining. --- ### A Lightweight Foundation Model for Collider Physics with Multi-Domain Adaptation Authors: Liangyu Wu, Qibin Liu, Alexander Yue, Julia Gonski Published: 2026-07-29 Categories: cs.LG, hep-ph arXiv: https://arxiv.org/abs/2607.27501v1 We present a lightweight approach to foundation modeling (\textbf{NEXUS}) that leverages pre-trained learning from collider physics data towards out-of-domain tasks in other scientific datasets, using a fully connected autoencoder model with approximately 3 million parameters. The model pre-trains with no supervision over a large-scale collision dataset from the Large Hadron Collider modeled by charged particle track features. Downstream tasks for collider analyses, such as kinematic regression and event classification, are developed on pre-trained model weights and achieve improved accuracy with only small labeled datasets when compared to equivalent architectures trained from scratch. The benefits of pre-training are additionally investigated through latent space interpretation and application to other domains, including gravitational waves, flood forecasting, and neural activity. Furthermore, the relative computational simplicity of NEXUS is demonstrated compared to transformer approaches at comparable scale, opening the door to power-efficient inference and real-time or edge applications of foundation models in scientific experiments. --- ### A dataset of rated conceptual arguments Authors: Emery Cooper, Caspar Oesterheld, Linh Chi Nguyen, Alexander Kastner, Ethan Perez Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27499v1 Large language models have improved rapidly on tasks with verifiable answers, such as mathematics and programming. Much less is known about their ability to reason about what we call conceptual questions: questions for which no ground truth is realistically accessible and no widely accepted resolution methodology exists, but on which progress can still be made by debating arguments. Most philosophical questions are of this kind, as are central components of questions in AI safety, decision theory, and social choice. Our approach is based on the view that while bottom-line conclusions on such questions are hard to evaluate, individual contextualized arguments can be evaluated far more reliably. We therefore introduce a dataset of 951 argumentative critiques of 442 position texts, spanning topics from AI safety and decision theory to ethics and politics, with 1,458 ratings by six expert raters along dimensions including centrality, strength, correctness, and clarity. We propose two scoring functions and benchmark a range of models. Performance tracks general capability rankings. --- ### SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge Authors: Lucio M. Dery, Benedict Aaron Tjandra, Siavash Samiei, Adhiguna Kuncoro, Zohar Yahav, Jiajun Shen, Arthur Szlam Published: 2026-07-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.27497v1 Agentic systems driven by large language models (LLMs) regularly feature two key mechanisms to autonomously solve complex problems: synthesizing text-based knowledge and procedures from past experiences and building parametric (weight-space) skill libraries for recurring sub-goals. To date, research has largely treated these as orthogonal pursuits: either organizing textual knowledge through composition and reflection, or consolidating parametric skills via weight-space merging. Consequently, the seamless integration of text and model weights for targeted performance improvements remains largely unexplored. This work bridges this modality gap by treating model weights as an additional modality that an LLM can natively reason over. We instantiate parametric learning via prefix-tuning and augment an LLM to ingest both prefix weights and rich textual data which capture relationships to a target capability. Our augmented LLM, which we call SkillSmith, synthesizes these inputs to perform instruction-steered parametric synthesis, directly outputting new prefix weights that manifest the target skill. We demonstrate that our approach significantly outperforms both text-only and weight-space-only baselines, unlocking performance gains that are out of reach for uni-modal (text-only or weight-only) adaptations. --- ### MedLLM: An Open Medical Language Model at the Sub-Billion Scale Authors: Maxx Richard Rahman, Asim Ahmed, Mihan Mohagheghzadeh, Wolfgang Maass Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27490v1 Open medical language models have converged on a single scale: every widely used system runs at 7B parameters or more, leaving the sub-billion regime uncharacterized. We present MedLLM, an open 0.1B-parameter medical language model trained through a fully open three-phase pipeline: general pretraining with curriculum sequence-length scheduling, domain fine-tuning on MedFineWeb, a reference-guided medical corpus we release that is selected from general web data by embedding similarity to medical question-answering (QA) data, and preference-aligned fine-tuning combining SFT with direct preference optimization (DPO). Across medical benchmarks, MedLLM shows a pattern visible only at sub-billion scale: medical competence does not degrade uniformly under compression but splits by task type. On context-grounded QA it comes within $2.9$pp of a medically adapted 7B model and surpasses the instruction-tuned and general-purpose 7B baselines; on knowledge-recall QA it stays near the task floor on clinical-vignette MedQA yet significantly exceeds every 7B and sub-7B baseline on MedMCQA, indicating that where recall fails the constraint is model capacity rather than adaptation. This dissociation is masked at 7B, where both capabilities are present, and surfaces only when capacity is scarce. --- ### INCLAIR: Inception-Based Longitudinal Clinical Anomaly Detection with Informed Reasoning Authors: Maxx Richard Rahman, Wolfgang Maass Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27487v1 Detecting anomalies in longitudinal clinical profiles is clinically important but difficult: abnormal evidence is often sparse, patient histories have unequal length, and expert explanations are costly. We propose INCLAIR, a framework that scores each observation against multiple historical contexts, aggregates evidence at the profile level, and generates grounded natural-language explanations under limited expert supervision. Under stated within-profile exchangeability assumptions, the complete mean subsequence score takes an order-$l$ U-statistic form, yielding a variance decomposition and an incomplete-subset approximation that controls combinatorial inference cost independently of profile length. The same analysis shows that mean aggregation attenuates localized anomalies by a factor set by the anomaly support and profile length, motivating validation-selected top-$k$ pooling. Across three clinical datasets, INCLAIR consistently outperforms state-of-the-art baselines. We further validate practical relevance through a case study on longitudinal steroid profiles, comparing INCLAIR's predictions and explanations against domain-expert assessments supported by DNA analysis. The results show that INCLAIR enables clinically actionable anomaly detection under limited expert supervision. --- ### Skill Use or Skill Theater? Evaluating the Reasoning Backroom in Skill-Augmented Language Agents Authors: Jinwei Hu, Yi Qi, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang Published: 2026-07-29 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.27484v1 Reusable skills are becoming a standard interface for extending language agents with task procedures. Yet evaluators usually infer skill use from visible reasoning or the agent's own attribution. These signals show what the agent appears to use, not whether the skill changed its decision. We ask whether skill-augmented agents exhibit a \textbf{Reasoning Backroom}, a systematic gap between stated skill use and intervention-measured influence. We introduce BACKTRACE, an evaluation framework that pairs each skill-conditioned answer with a matched no-skill counterfactual, intervenes on skill meaning, wording, identity, content, and assignment, and elicits attribution only after the answer is committed. We instantiate the framework as BACKROOMBench, a verified testbed spanning controlled logic and competition mathematics, multiple skill conditions, single-agent and multi-agent settings, and diverse model families. Our evaluation reveals a pervasive provenance failure. Across models and domains, stated skill use often remains stable while causal reliance and signed utility vary, producing both silent uptake and performative use. Behavioral effects follow procedural content more reliably than displayed skill identity, whereas stated attributions respond strongly to artifact availability. Observational detectors based on direct skill-use claims, text mentions, trace similarity, and an LLM judge do not identify which decisions actually depend on the skill. In multi-agent systems, skill influence can survive communication even after its source is lost, while no-skill teams still name skills and sources that were never supplied. These findings establish the Reasoning Backroom as a general AI provenance problem whose audit requires intervention. --- ### Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Authors: Kevin Guan Published: 2026-07-29 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.27482v1 A temporally drifting data stream may pass through discrete regimes rather than changing continuously. We ask whether such regimes are recoverable from the weights of models trained on the stream, using a hidden Markov model (HMM) fit to the chronologically ordered trajectory of those weights. We study this question in two domains known to drift over time: multimodal misinformation detection, using the Fakeddit dataset; and sentiment analysis, using the Yelp dataset. We train classifiers on consecutive temporal windows and fit an HMM to the trajectory of their aligned weights, recovering latent states that partition each timeline into coherent phases. On both datasets, classifiers generalize better to data from windows sharing the state of their training window than to windows across state boundaries. This within-state transfer advantage survives a control for temporal proximity and modestly exceeds the advantage recovered by a naive partition into contiguous states of equal size. Although the states are estimated solely from model weights, they correlate more strongly with shifts in the data's class distribution than with the weight-space geometry used to estimate them. After class divergence and lag are residualized out, the within-state advantage exceeds its permutation null on both tasks, indicating that the states recover structure relevant to transfer beyond the data distribution. Every effect replicates on both tasks but is attenuated on Yelp, whose label distribution is more temporally stable. --- ### Schreier-Coset Graph Rewiring Authors: Aryan Mishra, Randy Martinez, Lizhen Lin Published: 2026-07-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27479v1 The information flow in the graph neural networks (GNNs) is fundamentally constrained by over-squashing, where structural bottlenecks impede long range information propagation. Graph-rewiring methods, which modify graph topology, have been extensively used to alleviate this. However, existing approaches often introduce prohibitive structural and computational bottlenecks, fail to preserve the critical properties of original graphs, and increase the edge counts massively. We introduce a novel method Schreier-Coset Graph Rewiring , a group-theoretic rewiring method that augments the input graph with a Schreier-Coset graph derived from a special linear group. Our method provides theoretical guarantees, a graph that exhibits spectral gap and a bounded effective resistance, creating a low-resistance bypass for long-range communication. Empirical evaluations demonstrate that SCGR reduces effective resistance by 5-40% across various learning tasks, effectively mitigating connectivity bottlenecks while maintaining competitive accuracy. --- ### Entropy-Smooth Convex Optimization Cannot Be Accelerated Authors: Jacob M. Aguirre, Dmitrii M. Ostrovskii Published: 2026-07-29 Categories: math.OC, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2607.27476v1 We prove an $Ω(L/T)$ lower bound for the convergence rate of minimization in the class of functions that are convex and $L$-smooth relative to negative entropy on the standard $d$-simplex, valid for every first-order method when $d = Ω(T^2)$. In particular, this shows that mirror descent is optimal up to a logarithmic factor in this class. This may be surprising due to the fact that accelerated methods are readily available under the assumption of smoothness in $\ell_1$-norm. While Dragomir et al. (Mathematical Programming, 2022) have already showed that acceleration might be impossible under relative smoothness, their prox-function is pathological and constructed together with the hard instance. In contrast, we show non-acceleration for a specific prox-function with particularly favorable structure. We also extend the result to the quantum setting, proving the same lower bound in the class of functions $L$-smooth relative to negative von Neumann entropy on the spectrahedron of $d \times d$ Hermitian positive-semidefinite matrices with unit trace. --- ### OneShot: Index-in-Ranking with Neural Scoring for Large-Scale Retrieval Authors: Ziwei Li, Shuyao Li, Xufeng Cai, Xue Zou, Yiming Ma, Huiting Lu, Wujie Yan, Zhichen Zhao, Yang Lu, Zhe Wang, Rui Luo, Zhengyu Su et al. Published: 2026-07-29 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.27475v2 In modern recommendation systems, retrieval serves as a primary stage responsible for filtering billions of candidate items down to thousands prior to refined ranking. To make this massive search effective and efficient, the system relies on ranking accuracy and indexing efficiency. However, these two objectives are traditionally misaligned: while the former optimizes for the alignment between ranking predictions and user behavior, the latter optimizes for a structural grouping of item representations which enables fast search among billions of candidates. Thus, despite extensive efforts to scale up interaction modeling for retrieval, they remain fundamentally limited by the structural misalignment between the ranking objectives and the proximity-learned index. In this work, we address this long-standing dichotomy by proposing a new holistic retrieval framework, OneShot. It is an end-to-end, in-model index learning framework that natively aligns index learning with ranking objectives. Using this joint learning as a structural foundation, OneShot pushes the boundaries of retrieval expressiveness by scaling interaction modeling with neural scoring beyond the persistent dot-product bottleneck. OneShot is fully deployed in Instagram's industrial short-video recommendation system, driving significant wins in user daily sessions, engagement, and time-spent. Additionally, OneShot achieves a $20\%$ recall gain at the operational ranking volume and a 10x efficiency improvement at an equivalent recall level. --- ### IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks Authors: Mengqi He, Jing Zhang Published: 2026-07-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27465v1 Semantic segmentation models are vulnerable to transferable adversarial perturbations, yet evaluating transfer attacks on dense prediction models can be computationally expensive. Existing ensemble attacks often rely on multiple surrogate models, increasing the computation cost, even harder for segmentation. This paper studies an efficient single-source alternative for transferable attacks on semantic segmentation. We formulate transferable attack composition as a chained computation over differentiable attack components, allowing the expensive source-model gradient computation to be shared. To reduce the update instability introduced by chained composition, we further use an integrated-gradient-style path-averaged direction as an empirical stabilization heuristic. Experiments on Pascal VOC and Cityscapes evaluate the resulting transferability efficiency trade-off across CNN- and transformer-based segmentation models. IGME achieves competitive transferability compared with single-source baselines and favorable runtime compared with model-ensemble attacks, while requiring access to only one source model. --- ### FADEx: Feature Attribution and Distortion-based Explanation of Dimensionality Reduction Authors: Lucas Greff Meneses, Evandro S. Ortigossa, Claudio Silva, Luis Gustavo Nonato Published: 2026-07-29 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2607.27463v1 Dimensionality Reduction (DR) is a fundamental tool for high-dimensional data exploration, reducing the complexity of latent spaces of machine learning models, and assisting in the explanation of complex opaque models. However, non-linear DR techniques often function as opaque transformations themselves, making it challenging to understand how individual features influence instance positioning in the reduced space. This lack of transparency complicates the analysis and interpretation of structural patterns, hindering the ability to reason about the organization of high-dimensional data based on the projected layout. In order to address this challenge, dimensionality reduction explanation methods have shown promise in improving the understanding of the observed groups and cluster structures. Unfortunately, existing DR explanation approaches tend to suffer from limitations such as multiple attributions per feature and restricted applicability to specific dimensionality reduction methods, which hinder their use. In this work, we propose FADEx, a novel local per-instance feature attribution method that leverages local linear approximation via first-order Taylor expansion and Singular Value Decomposition to provide explanations. FADEx computes the local linear models via weighted least squares, eliminating the need for out-of-sample data mapping, making it agnostic to the DR method, while simultaneously providing local feature attributions and distortion analysis. Through qualitative and quantitative evaluations, comparisons with existing methods, and case studies, we demonstrate FADEx's effectiveness and versatility in providing explanations and analytical resources for analyzing the behavior of DR methods. The results indicate FADEx yields robust and reliable explanations, outperforming existing approaches in several aspects. --- ### VAmoS Bench: Voice Agent Simulation Bench Authors: Joshua Meyer, Sahar Shayegan, Ritiz Tambi, Ali Khan, Sun Kim, Victor Shih, Mehdi Jamei, Andi Partovi Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27453v1 Production voice agents span cascaded, speech-to-speech, and hybrid architectures. Voice-agent benchmarks typically measure component quality and conversational properties such as word error rate, latency, naturalness, and turn-taking. Fewer measure whether the agent handled a phone call correctly on its own. Contact centers refer to this as ``containment'': the share of phone calls the automated system resolves without handing off to a human. On some phone calls the right outcome is refusal or a redirect. To address this gap, we introduce VAmoS Bench, the Voice Agent Simulation Bench. It measures complete voice-agent systems end to end in a stateful customer-support task. The agent is Riley, a credit-card support representative for a fictional bank who can freeze, cancel, replace, or activate a card. Each of 100 scenarios supplies a simulated caller with a private goal and a seeded PostgreSQL backend. The platform uses each scenario to populate and activate an isolated simulation in which the caller reaches Riley over audio; roughly one-third apply adversarial pressure. The agent can use five tools that execute real SQL against the backend. Each scenario also defines binary assertions. A grader evaluates them against the complete trace of what the caller and agent said and what the agent did, including tool invocations, arguments, and returned rows. This catches an agent that claims to have changed a card without updating the database, as well as one that makes the right database change while disclosing protected information. This first benchmark version focuses on financial services. Its evaluation protocol supports an evolving leaderboard: additional voice agents can be evaluated on the same version, while later versions can expand the tasks and scenarios. --- ### Neural Network-Assisted CLEAN for Channel Modeling in Low-SNR Regimes Authors: Chaofan Deng, Linyu Sun, Jaeho Lee, Arijit Raychowdhury Published: 2026-07-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27450v1 Accurate multipath parameter estimation is critical for modern wireless communication systems, particularly in challenging low-SNR environments. Traditional Maximum Likelihood Estimation algorithms, such as CLEAN, provide high-resolution parameter extraction but suffer from prohibitive computational complexity due to exhaustive grid search. Conversely, purely data-driven deep learning approaches lack physical grounding and struggle to generalize across variable multipath densities and off-grid parameters. To address these limitations, this paper proposes Neural Network-Assisted CLEAN (NN-CLEAN), a hybrid framework that embeds a multi-head residual network directly into the iterative CLEAN extraction loop. By replacing the exhaustive grid search with rapid, parallelizable forward passes while delegating residual subtraction to exact mathematical models, NN-CLEAN isolates physical multipath parameters without accumulating non- physical errors. Extensive Monte Carlo simulations demonstrate that NN-CLEAN achieves estimation accuracy exceeding 96% at 5 dB SNR, matching the traditional Grid-Search CLEAN (GS- CLEAN) baseline, while providing a massive reduction in computational complexity and substantially outperforming subspace methods and standalone one-shot neural networks. Crucially, NN-CLEAN exhibits a near-flat scaling in execution runtime and memory consumption as batch sizes increase. This highly efficient parallelization establishes NN-CLEAN as a robust, real- time solution for channel estimation in MIMO systems. --- ### Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems Authors: Xu Zheng, Zhuomin Chen, Chaohao Lin, Hua Wei, Haifeng Chen, Wei Cheng, Dongsheng Luo Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27443v1 Large Language Model~(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks. However, they often struggle with long-horizon interactive tasks common in domains, such as embodied AI. The complexity and vast action spaces in these settings lead to compounding errors, where a single suboptimal action can derail an entire trajectory, causing the agent to exhaust its limited step budget on inefficient or unrecoverable paths. To overcome this without costly fine-tuning, we draw inspiration from software debugging, where execution logs are analyzed to preemptively catch errors. We propose \textit{Trajectory Graph Copilot}, a novel framework that acts as a ``copilot'' for LLM agents by diagnosing potential action errors before they are executed. At its core,\textit{Graph Debugger} models historical trajectories as a probabilistic graph and uses a Graph Neural Network to identify sequential action patterns that frequently lead to failure. Functioning as a proactive diagnostic sandbox, our method provides early warnings on potentially flawed actions, prompting the agent to self-correct. This pre-action error diagnosis prevents costly mistakes, significantly enhancing the agent's ability to complete long-horizon tasks successfully. The extensive experiments on four benchmarks with three LLM agents demonstrate a $14.69\%$ pass ratio improvement on average. --- ### Comparison of a Parametric Physics-Informed Neural Network and a Tensorial Reduced-Order Model for the Shallow-Water Dam-Break Problem Authors: Anton Myshak, Md Rezwan Bin Mizan, Ilya Timofeyev Published: 2026-07-29 Categories: math.NA, cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2607.27433v1 We develop two parametric data-driven reduced models: a physics-informed neural network (PINN) and a non-intrusive tensorial reduced-order model (TROM), and apply both approaches to the parametrized one-dimensional shallow-water dam-break problem. Both reduced models do not require time integration and learn a direct solution map from space, time, and dam-break parameters to the physical state. We present a detailed comparison for out-of-sample and extrapolated parameter values. In addition, we demonstrate that it is essential to introduce shock-aware collocation to improve the robustness of the PINN model. --- ### SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups Authors: Yikun Bai, Binghang Lu, Yikai Liu, Elaheh Akbari, Soheil Kolouri, Linxuan Wang, Ping He, Shuchan Wang, Ruqi Zhang, Guang Lin Published: 2026-07-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.27431v4 Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and flow-matching models produce high-quality backbones on SE(3)^N, but inference requires numerically integrating an ODE over hundreds of network evaluations, each involving a Lie group exponential map - a bottleneck for high-throughput design campaigns. We introduce SE(3)-MeanFlow, a few-step generative framework that extends MeanFlow from Euclidean space to the Lie group geometry of protein frames. Working natively in the Lie algebra so(3) and in R^3, we derive closed-form average-velocity identities for rotations and translations, giving simulation-free training targets. We further introduce an SE(3) alpha-Flow objective that removes the Jacobian-vector product from the rotation branch and serves as a warm-up stage, after which training switches to a small-t stabilized MeanFlow loss that is used for the remainder of pretraining and for rectification-based post-training. In protein backbone generation, SE(3)-MeanFlow matches or exceeds flow-matching baselines that use several times more sampling steps, and its advantage widens in the few-step regime, where rectification lets it lead at every matched budget - at a modest cost in diversity. --- ### SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups Authors: Yikun Bai, Binghang Lu, Yikai Liu, Elaheh Akbari, Soheil Kolouri, Linxuan Wang, Ping He, Shuchan Wang, Ruqi Zhang, Guang Lin Published: 2026-07-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.27431v3 Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and flow-matching models produce high-quality backbones on SE(3)^N, but inference requires numerically integrating an ODE over hundreds of network evaluations, each involving a Lie group exponential map - a bottleneck for high-throughput design campaigns. We introduce SE(3)-MeanFlow, a few-step generative framework that extends MeanFlow from Euclidean space to the Lie group geometry of protein frames. Working natively in the Lie algebra so(3) and in R^3, we derive closed-form average-velocity identities for rotations and translations, giving simulation-free training targets. We further introduce an SE(3) alpha-Flow objective that removes the Jacobian-vector product from the rotation branch and serves as a warm-up stage, after which training switches to a small-t stabilized MeanFlow loss that is used for the remainder of pretraining and for rectification-based post-training. In protein backbone generation, SE(3)-MeanFlow matches or exceeds flow-matching baselines that use several times more sampling steps, and its advantage widens in the few-step regime, where rectification lets it lead at every matched budget - at a modest cost in diversity. --- ### Rethinking Artificial Intelligence in Medical Imaging: Assumptions, Reality, and Reframing Authors: Arman Rahmim, Nourhan Bayasi, Xiaoxiao Li, Babak Saboury, Fereshteh Yousefirizi Published: 2026-07-29 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2607.27428v1 Medical imaging has served as primary proving ground for clinical artificial intelligence (AI), yet a decade of intense research has not translated into proportionate bedside impact. We argue that this gap is not primarily a product of insufficient algorithmic performance, inadequate regulation, or limited explainability. Rather, it reflects a structural misalignment, between how AI systems are designed and evaluated, and how clinical decisions are made. This Perspective identifies six interconnected dimensions of this misalignment: the dominance of pixel-only models in a multimodal clinical world; the erosion of physician trust through opaque and inflexible systems; the unfulfilled promise of foundation models in data-sparse medical domains; the persistent bottleneck of non-shareable, under-curated datasets; the gap between validated algorithms and deployable clinical platforms; and the failure of prediction-centric AI to generate actionable clinical guidance. For each dimension, we reframe the problem and propose a path forward, culminating in a vision of agentic, physician-aligned AI that extends, rather than replaces, clinical judgment. --- ### Adaptive Nyström for Gaussian Process Regression Authors: Lulu Kang Published: 2026-07-29 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.27427v1 Gaussian Process Regression (GPR) is a robust framework for uncertainty quantification, yet its $O(n^3)$ complexity limits its scalability. Low-rank Nyström approximations can reduce this burden to $O(nm^2)$, but their accuracy depends heavily on the selection of landmark points. We propose an adaptive Nyström approach that greedily selects landmarks to minimize the trace residual of the kernel approximation error. Unlike static approximations, our method interleaves landmark expansion with hyperparameter optimization, allowing the selection process to adapt as the covariance structure is refined. Numerical experiments on five benchmark functions demonstrate that this method significantly outperforms random landmark selection in both accuracy and stability. It achieves predictive performance comparable to exact GP inference while maintaining linear scaling with respect to the sample size, providing a principled and efficient framework for large-scale computer experiments. --- ### Good Rankers, Bad Objectives: Bilinear Contrastive Critics under Expressive Policy Search Authors: Ayushman Singh, Siddharth Aphale Published: 2026-07-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27422v1 Good action rankings do not make a contrastive critic safe to maximize. These critics increasingly act as value-like objectives for best-of-$K$ selection, planning, and critic-guided generation. Unbounded bilinear scores can let large embedding norms inflate off-support values, but cosine bounding does not remove the failure. A controlled support decomposition attributes most raw bilinear regret to norm drift. Cosine and hybrid critics nevertheless select off-support actions from most pools and incur comparable regret. Contrastive scores are weakly calibrated or inverted in the top score decile across four OGBench navigation tasks, and they fail to order fixed-query actions by value. Bellman-trained TD-Q succeeds, including in a parameter-matched function-class control. Realized costs depend on the task: simulator rollouts reveal single-step selection costs on PointMaze and the exact-$Q^*$ toy but well-powered nulls on AntMaze and HumanoidMaze, where the controller can self-correct. A training/readout decomposition traces the lost ordering to the cosine training objective; raw-trained embeddings retain weak ordering after inference-time normalization. Candidate maximization can therefore exploit false positives caused by norm drift, score saturation, or in-support misranking. Contrastive critics remain useful compatibility rankers on navigation and manipulation tasks, but action selection requires a value-calibrated scalar. --- ### Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models Authors: Parishruthi Ganesh, Gerry Dozier, Cheryl Seals Published: 2026-07-29 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.27421v1 Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints. We present a systematic zero-shot evaluation of 41 open-weight language models spanning 15 families and the 135M--9B parameter range across eight English single-label intent-classification datasets. A ninth dataset, ATIS, uses five labeled demonstrations and is reported as an auxiliary five-shot result. The evaluation includes standard benchmarks, a large-scale voice-assistant corpus, and production-derived e-commerce datasets. Beyond exact-match accuracy, we analyze confidence calibration, robustness to realistic input perturbations, statistical reliability of model rankings, deployment efficiency, and benchmark saturation. Our results show that instruction-tuned 3B models can outperform several evaluated 7B base models, that differences among leading models on MASSIVE are statistically indistinguishable under pairwise McNemar tests, and that widely used benchmarks such as SNIPS have become saturated and no longer meaningfully discriminate among current open-weight models. Instruction tuning's effect on confidence calibration is inconsistent rather than uniformly harmful. These findings provide practical guidance for selecting and evaluating open-weight language models for intent classification. --- ### Dimensionality and Measurement Precision in HLE's Multiple-Choice Subset Authors: Mayank Sharma, Savira Nadela, Tyler Matteson Published: 2026-07-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.27420v1 Humanity's Last Exam (HLE) is widely used to evaluate frontier language models. HLE organizes its questions into eight subject-domain categories, whose subscores are often interpreted as evidence of distinct capabilities. However, no study has assessed whether these labels correspond to empirically separable latent constructs, nor whether the benchmark effectively differentiates between models of similar ability. We evaluate 29 LLMs on the text-only multiple-choice subset of HLE ($J = 428$ items) and apply psychometric methods to assess both the dimensionality of the benchmark and the distribution of its measurement precision. Fitting a two-parameter logistic IRT model, we find convergent evidence that HLE measures a single general reasoning factor: McDonald's $ω_h = 0.998$, domain labels explain only 3.5\% of item response variance, within- and between-domain residual correlations are nearly identical (Cohen's $d = 0.016$), and domain-specific ability estimates are near-redundant with the total score ($r \geq 0.81$). A separate analysis of the test information function reveals that measurement precision concentrates at moderate ability levels and drops sharply above $θ= 0$, where frontier models sit. These findings suggest that HLE's domain subscores do not warrant distinct capability interpretations and that the benchmark's ability to discriminate among the strongest models is limited. --- ### Context-Informed Ship Trajectory Prediction via Conditional Attention Authors: Yuan Guan, Chandler Squires, Timothy Hu, Pradeep Ravikumar Published: 2026-07-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27418v1 Long-term ship trajectory prediction is a fundamental capability for maritime safety and autonomous navigation. While recent Transformer-based architectures have improved forecasting horizons, they predominantly rely on historical kinematic states, treating vessel motion as an isolated system. In reality, maritime navigation is profoundly modulated by extrinsic factors like weather and constrained by static vessel characteristics. Existing multimodal approaches fundamentally model the joint distribution over states and contexts, treating environmental variables as peer features rather than encoding the directional physical dependence of vessel dynamics on environmental conditions. In this work, we propose the Conditional Informer, a novel encoder-decoder architecture that formulates trajectory prediction as a conditional generation task. We employ a dedicated Conditional Attention mechanism where the vessel state explicitly queries environmental contexts through cross-attention, encoding the physical prior that weather modulates - but is not generated by - vessel dynamics. Furthermore, to address the intermittency of real-world data, we introduce a Modality Masking training strategy to prevent catastrophic degradation during sensor fallback. Extensive experiments on AIS and ERA5 data demonstrate that our approach outperforms kinematic and concatenation-based baselines by 15.4% in prediction accuracy when context is available. Crucially, Modality Masking prevents shortcut learning, reducing fallback error by nearly an order of magnitude compared to unconstrained models. --- ### Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs Authors: Xu Zheng, Chaohao Lin, Zhuomin Chen, Weijieying Ren, Haifeng Chen, Wei Cheng, Dongsheng Luo Published: 2026-07-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27415v1 Recent advancements in inference-time scaling have significantly unlocked the complex reasoning capabilities of Large Language Models~(LLMs). However, for agents, these approaches suffer from a critical inefficiency, operating in a stateless manner and engaging in redundant search processes. Existing memory mechanisms largely rely on the reasoning capabilities of LLMs, leading to prohibitive computational costs. In this paper, we propose a novel framework, \textit{GAMER}~(Graph-based Action-centric Memory with Episodic Reasoning), that bridges the gap between inference scaling and episodic memory. Our approach models historical reasoning as a dynamic \textit{Action-Centric Graph}. By decoupling the memory mechanism from LLMs, our method can save token/money usage by providing less memory context than memory mechanism baselines. To extract knowledge from the graph effectively, we use a dual-stream Temporal Difference learning mechanism to estimate the positive~(suggestion) and negative~(avoidance) value of action nodes based on past successes and failures. During the inference phase, this learned value function optimizes decision-making bi-directionally, so that positive values provide action suggestions, while negative values indicate high-risk actions. By performing efficient searches on the graph, our method significantly improves the efficiency of inference scaling. Experiments on multiple benchmarks demonstrate that \textit{GAMER} achieves superior performance by \textbf{20.81\%/6.17\%} for success/progress rate compared to vanilla baselines. --- ### SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements Authors: Pengyu Xue, He Yang Yuan, Xin Wang, Junkai Chen, Haonan Zhang, Boyuan Chen, Zishuo Ding, Zhenhao Li, Weiyi Shang Published: 2026-07-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.27409v1 Although coding agents have achieved impressive performance on correctness-oriented benchmarks, their ability to make behavior-preserving non-functional improvements (NFIs) remains underexplored. In real-world software development, developers continuously improve software quality without changing observable behavior, yet existing benchmarks primarily evaluate functional correctness and provide limited support for assessing these non-functional improvements. In this paper, we present SWE-NFI, a benchmark for evaluating coding agents on NFIs beyond functional correctness. Our benchmark contains 188 tasks constructed from real merged pull requests in open-source Python projects. We operationalize developer-oriented NFIs into 92 executable rules and develop a comprehensive evaluation suite that combines functional correctness testing with rule-based NFI evaluation. We evaluate state-of-the-art commercial and open-source coding agents. Although the best-performing agent achieves a 70.0\% functional correctness rate, all evaluated agents generally fall short of human developers in overall NFI capability. The gap is particularly evident for structural code improvements, where agents' NFI scores range from 0.0 to 1.3, compared with 1.5 for the human reference. Our benchmark and findings provide a reproducible foundation for evaluating and advancing coding agents beyond functional correctness. --- ### Benchmarking LLM Competence on Logical Inference over Probability Operators Authors: Nayera Hasan, Jack Greff, Alvin Grissom Published: 2026-07-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27405v3 Both expressions of uncertainty and inferences are ubiquitous in natural language, and valid inferences over natural-language expressions of uncertainty are necessary for not only everyday conversations but also for high-stakes domains such as medicine and law. While large language models are increasingly evaluated on logical reasoning tasks, disentangling principled, symbolic reasoning from clever surface-level pattern matching is fraught with difficulty. We introduce a benchmark for reasoning over probability operators--inference over sentences with gradable epistemic modals (e.g., probably, might, must) containing 14,320 procedurally-generated English prompts across fifteen inference templates, systematically varying question form, negation strategy, and surface content. Evaluating 29 models, we find that most show answer biases independent of the logical form, a systematic preference for Yes or No. We summarize this with a competence floor: the worse of a model's accuracy on Yes-correct and No-correct items. Only 9 of 29 models exceed random chance. We also test variations in question form, verb phrases/activity, and both the gender and origin of names used in the prompts, finding biases across every axis. --- ### ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders Authors: Yixuan Duan, Wei Qiu Published: 2026-07-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.27404v1 Existing benchmarks for electrocardiogram foundation models primarily evaluate downstream predictive performance, providing limited insight into whether their internal representations can be faithfully decomposed, clinically interpreted, or reproduced across independent analyses. We introduce ECG-InterpBench, a benchmark designed to systematically evaluate the interpretability of ECG foundation-model representations. ECG-InterpBench uses sparse autoencoders as standardized measurement instruments and matches their capacity across models to enable controlled comparisons. We evaluate six frozen ECG foundation models across five standardized encoder depths, five matched dictionary widths, and three random seeds, producing a 450-cell interpretability atlas comprising 75 exactly matched six-model comparison blocks. The benchmark evaluates complementary dimensions of representation interpretability, including sparse reconstruction fidelity, single-feature accessibility and coverage of 49 clinically meaningful ECG measurements, and cross-seed feature reproducibility. The evaluation further quantifies patient-sampling uncertainty, depth- and seed-dependent variation, and sensitivity to the sparsity parameterization. The benchmark reveals that ECG foundation models exhibit distinct interpretability profiles. A matched replication on MIMIC-IV-ECG confirms that reconstruction fidelity and clinical accessibility identify different leading models. The benchmark is accompanied by executable evaluation code, standardized manifests, cell-level metrics, and reproducibility audits. ECG-InterpBench complements performance-centered ECG benchmarks by providing a capacity-controlled and reproducible framework for comparing ECG foundation models across distinct dimensions of representation interpretability. --- ### AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes Authors: Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Abul Hasnat, Md. Rafiul Biswas, Wajdi Zaghouani, Firoj Alam Published: 2026-07-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27393v1 Hateful memes are a growing form of multimodal online harm, where hostile intent is often conveyed through the joint interpretation of images, text, cultural references, and implicit targets. While hateful meme detection has advanced in high-resource languages, Arabic remains underexplored, with existing meme resources focusing mainly on propaganda or coarse harmful-content labels. We introduce AHA-Memes (Arabic HAteful Memes), which is, to our knowledge, the first large-scale Arabic hateful meme benchmark with fine-grained, multi-label annotations. The dataset includes 5K manually annotated memes using a taxonomy that captures hate types, i.e., attack strategies. We further provide ~66K silver-labeled memes to support future studies. We benchmark text-only, image-only, and late-fusion multimodal models, as well as few-shot in-context learning (ICL) and open- and closed-weight Vision-Language Models (VLMs) under zero-shot and fine-tuning settings. Our results establish strong baselines and highlight key challenges in culturally grounded Arabic hateful meme detection. We release the dataset, annotation guidelines, and evaluation scripts to support future research. WARNING: This paper contains examples that may be disturbing to readers. --- ### FunL2O: LLM-Guided Feature Function Design for Learning to Optimize Authors: Bingheng Li, Junyang Cai, Yupeng Zhang, Bistra Dilkina, Jayant Kalagnanam, Dzung T. Phan Published: 2026-07-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.27389v1 Learning-to-optimize (L2O) methods accelerate repeated optimization by training models to predict solutions, warm starts, branching decisions, or other forms of solver guidance. A critical yet largely overlooked component of these pipelines is the feature function that maps problem instances to inputs for machine learning models. Existing L2O methods typically rely on hand-crafted features, making representation design manual and largely fixed across domains. We introduce FunL2O, the first unified framework for automating feature design through LLM-driven program evolution for L2O. In a FunSearch-style loop, an LLM proposes executable feature functions, while a fixed evaluation process retrains the original L2O model and measures downstream optimization performance. We evaluate FunL2O on linear and quadratic programming tasks involving solution prediction and warm-starting, as well as on mixed-integer optimization tasks using GNN-guided backdoor branching and Predict-and-Search. Across continuous and discrete optimization tasks and four LLMs, the evolved features consistently outperform hand-crafted representations. These results establish LLM-driven feature evolution as a general and effective approach to automating representation design in L2O. --- ### Beyond the Bidirectional Promise: Re-evaluating the Robustness of Diffusion Language Models Authors: Saurabh Yadav, Badri Narayana Patro, Vijay Srinivas Agneeswaran Published: 2026-07-29 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.27386v1 Diffusion Language Models (DLMs) offer a compelling alternative to autoregressive (AR) generation by enabling bidirectional context and iterative refinement. However, their reliability under natural input noise and adversarial attacks remains under-explored. To address this, we systematically evaluate DLM robustness and calibration against AR baselines, using two parameter-matched pairs (LLaDA-8B vs. LLaMA-3-8B and Dream-7B vs. Qwen2.5-7B) across 32 natural perturbation conditions, adversarial gradient probes, and mechanistic hidden-state analyses. This paired design effectively isolates architecture-intrinsic properties from weight-dependent behaviors. We find a nuanced robustness profile: while highly stochastic DLM loss landscapes naturally resist gradient-based adversarial suffixes, they provide no guaranteed defense against natural noise, proving that everyday robustness is weight-dependent rather than inherently architectural. Furthermore, DLMs exhibit systematic overconfidence, presenting a practical deployment hazard. Most crucially, mechanistic probing reveals that all models perfectly encode input corruption, isolating behavioral fragility entirely to a decoder routing failure. Consistent with this diagnosis, we show that surface-level prompt patching fails to improve over noisy baselines. Ultimately, DLM robustness cannot be patched on; it must be fundamentally integrated into the iterative decoding loop. ---