# Research Papers — 2026-06 · bundle page 94 of 260 > Full-text markdown of papers #4651–4700 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/94 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/93.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/95.md) ### The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Science Authors: Belinda Mo Published: 2026-06-18 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.26064v1 AI systems are becoming autonomous research agents that generate hypotheses, design experiments, and produce discoveries at scales beyond human oversight. As seen by increased submissions to ML venues, the verification gap between scientific output and our ability to check it is already widening, and autonomous agents make it worse by magnitudes given human-agent asymmetry. We argue that science must evolve its verification infrastructure, as it has before with peer review. However, while historical adaptations assumed human contributors who could be questioned and sanctioned, AI agents break this assumption. We propose criteria for an adapted verification infrastructure that emphasizes observable-by-default workflows, scalable verification, and clear attribution. We argue that without adaptation, ML and any scientific domain using agents face dangerous failures: experimental results that no person can verify, optimization for metrics over understanding, and accountability vacuums that erode scientific trust. --- ### Masked Distillation: Internalizing the Chain-of-Thought in Language Models Authors: Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati Published: 2026-06-18 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.22629v2 Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate traces dominate latency, memory usage, and serving cost, even though the final answer correctness is not causally related to the trace correctness and the trace length is not a reliable indicator of the problem complexity. This raises a natural question: can the computation expressed in these intermediate tokens be internalized into the parameters of a language model, enabling it to produce answers directly (or with much shorter intermediate traces)? We introduce \textit{masked distillation}, a knowledge-distillation framework in which a student LLM is trained to predict only the solution tokens conditioned on the question, while a reasoning teacher provides feedback on the student's responses after conditioning on the question and its own CoT trace. We instantiate this framework in two settings: (i) a \textit{self-distillation} setting, in which the same model serves as the teacher in thinking mode and as the student in non-thinking mode, and (ii) a \textit{dual-model} setting, in which a larger reasoning teacher supervises a separate smaller non-thinking student over the solution tokens. By treating intermediate tokens as a scaffold which reasoning models use to fit over the solution tokens, We additionally vary the length of intermediate-token scaffolding the student is supervised on, interpolating between full internalization (the student emits only the solution) and no internalization (the student emits the full trace before the answer). We evaluate the framework through controlled experiments on two reasoning domains: GSM8K (grade-school arithmetic) and Countdown (a number-puzzle search task). --- ### Masked Distillation: Internalizing the Chain-of-Thought in Language Models Authors: Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati Published: 2026-06-18 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.22629v1 Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate traces dominate latency, memory usage, and serving cost, even though the final answer correctness is not causally related to the trace correctness and the trace length is not a reliable indicator of the problem complexity. This raises a natural question: can the computation expressed in these intermediate tokens be internalized into the parameters of a language model, enabling it to produce answers directly (or with much shorter intermediate traces)? We introduce \textit{masked distillation}, a knowledge-distillation framework in which a student LLM is trained to predict only the solution tokens conditioned on the question, while a reasoning teacher provides feedback on the student's responses after conditioning on the question and its own CoT trace. We instantiate this framework in two settings: (i) a \textit{self-distillation} setting, in which the same model serves as the teacher in thinking mode and as the student in non-thinking mode, and (ii) a \textit{dual-model} setting, in which a larger reasoning teacher supervises a separate smaller non-thinking student over the solution tokens. By treating intermediate tokens as a scaffold which reasoning models use to fit over the solution tokens, We additionally vary the length of intermediate-token scaffolding the student is supervised on, interpolating between full internalization (the student emits only the solution) and no internalization (the student emits the full trace before the answer). We evaluate the framework through controlled experiments on two reasoning domains: GSM8K (grade-school arithmetic) and Countdown (a number-puzzle search task). --- ### ExecuGraph: A Multi-Agent, Execution-Grounded Framework for Reliable Backend Code Synthesis with Large Language Models Authors: Sai Deekshith Lekkala, Jothi Prabha Appadurai, Rohith Reddy Bellibatlu, Manpreet Singh Published: 2026-06-18 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.20499v1 Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability. We present ExecuGraph, a multi-agent framework that places execution-based validation at the center of backend code synthesis. Six specialized agents (Planner, Code Generator, Logical Reviewer, Evaluator, Optimizer, and Explainer) are coordinated by a typed directed workflow with a bounded retry budget, implemented on LangGraph with locally hosted models (Ollama) and an optional retrieval layer for algorithmic technique recall. A subprocess-isolated sandbox with a wall-clock timeout guards every evaluation. We evaluate on a curated 30-problem DSA suite (internal-30), HumanEval (n=64), and an APPS-introductory subset, contrasting ExecuGraph against a single-agent one-shot baseline and a single-agent execution-retry baseline (a Reflexion-style ablation that isolates the contribution of multi-agent decomposition). On internal-30, the three conditions are statistically indistinguishable (n=30; paired Wilcoxon p=0.59 MF vs. SO, p=0.08 SR vs. SO); 95% bootstrap confidence intervals on all pairwise mean differences include zero. On HumanEval, multi-full edges ahead by +3.1 pp. The strongest signal is cross-model: with DeepSeekCoder V2 Lite, graph-category accuracy improves from 57.5% (oneshot) to 80.0% (multi-full), a +22.5 pp jump that supports a scaling hypothesis: the value of multi-agent decomposition grows with base-model capability. The framework's primary contribution is methodological: a single codebase that collapses by configuration into one-shot, execution-retry, and per-agent ablation conditions, enabling controlled measurement of each lever's marginal contribution. A per-agent ablation, retry-budget sweep, error-class taxonomy, and test-source audit are reported. --- ### Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior Authors: Ali khalil, Aly M. Kassem, Mohamed Abdelrazek, Santu Rana, Negar Rostamzadeh, Golnoosh Farnadi Published: 2026-06-18 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.15286v1 We investigate whether harmful chain-of-thought (CoT) traces from compromised language models can transfer unsafe behaviour and be distilled into reusable jailbreak attacks. Using an emergent-misalignment organism and a refusal-ablated jailbroken organism, we transplant harmful CoTs into $29$ open-source and $5$ closed-source targets. Transferred traces raise harmful-response rates above $80\%$ on the most vulnerable open-source models, while semantically mismatched CoTs fail entirely. LLooM concept mining identifies four recurring components of harmful reasoning: proceduralisation, ethical decoupling, evasion, and target--vulnerability framing. Distilling these patterns into reusable system prompts produces effective black-box jailbreaks, outperforming direct CoT transplantation on strongly aligned models by up to an order of magnitude, including a $10\times$ improvement on GPT-4.1 AdvBench. Reasoning-enabled models are more than twice as vulnerable, and output-side safeguards such as Llama-Guard~3 frequently miss harmful generations. Our results show that harmful reasoning transfers at both the trace and pattern levels, motivating defences that evaluate reasoning context in addition to final outputs. --- ### Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods Authors: Michal Moshkovitz, Suraj Srinivas, Lesia Semenova, Nave Frost, Cyrus Rashtchian, Valentyn Boreiko, Shichang Zhang, Himabindu Lakkaraju, Cynthia Rudin, Jennifer Wortman Vaughan Published: 2026-06-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.14123v1 Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: research has not yet established methodologies for integrating explanations into end-to-end, human-in-the-loop systems. This position paper argues that the machine learning community must pivot from ad-hoc XAI methods toward addressing foundational & structural challenges, including unclear problem formulations, underspecified evaluation objectives, and the absence of pipelines for explanation-driven feedback. We support this claim through an analysis of recent ICML, NeurIPS, and ICLR papers and a survey of XAI practitioners, revealing recurring issues that limit cumulative progress. We conclude by outlining a practical checklist designed to shift XAI toward a more human-centered, action-oriented paradigm. By emphasizing foundational clarity over the development of ad-hoc methods, we hope to provide a roadmap for integrating explanations into actionable, feedback-driven AI systems. --- ### Explainable Artificial Intelligence For The Detection and Characterisation of Stage B Heart Failure Authors: Ahmed M Salih, Emer Brady, Ranjit Arnold, Gaurav Gulsin, Huiyu Zhouyb, Anvesha Singh, Gerry McCanna Published: 2026-06-18 Categories: cs.CY, cs.LG arXiv: https://arxiv.org/abs/2606.30665v1 Stage B heart failure is characterized by asymptomatic structural or functional cardiac abnormalities. Identifying individuals at this stage is clinically important, as early detection may enable targeted interventions to prevent progression to symptomatic disease. Explainable artificial intelligence (XAI) may support early detection, transparent risk stratification, and selection of clinically actionable interventions. This review examines the use of XAI in detecting and characterizing stage B heart failure. A literature search of Web of Science, Scopus, and PubMed was conducted on 27 March 2026. Studies were included if they applied AI with XAI techniques to stage B heart failure. After screening, 20 studies were included. Data on modalities, outcomes, demographic reporting, and XAI methods were extracted and synthesized. SHAP was the most commonly used method, followed by LIME, saliency maps, and Grad-CAM; however, XAI adoption was inconsistent, with some studies relying on limited or ad hoc interpretability approaches. Notably, none compared explanations across sex or ethnic subgroups, despite evidence of subgroup differences in disease burden. Evaluation of XAI outputs was often insufficient: some studies did not assess explanations, while others relied only on literature-based comparisons, introducing potential bias. These limitations suggest explainability was not systematically validated or leveraged to support robust and fair clinical inference. XAI shows promise for improving transparency in stage B heart failure identification, but current implementations remain limited. Key gaps include limited consideration of sex and ethnicity, absence of subgroup-specific analyses, inconsistent evaluation, and lack of external validation, all of which constrain generalisability and clinical adoption. --- ### Code evolution for link prediction in complex networks Authors: Alexey Vlaskin, Eduardo G. Altmann Published: 2026-06-18 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2606.26132v1 The problem of predicting links in complex networks appears in different disciplines and has led to a variety of ingenious human-designed methods. We use this rich program space to explore the performance and behavior of automated code-evolution systems tasked to obtain machine-designed methods for link prediction. Despite being trained on limited data, algorithms evolved through code evolution outperform human-designed methods (with an average AUC score of 0.915 vs. 0.783, computed over 580 networks) and show improved computational efficiency, allowing them to be applied to networks with millions of links. The discovered methods follow approaches that have been employed in human-designed methods, but contain key innovations in the selection and combination of node- and link-features. This illustrates the role modern large language models and genetic algorithms can play in algorithmic innovation and scientific discovery more generally. --- ### A Unified Framework for Runtime Verification and Model-Based Diagnosis in LOLA Authors: Raik Hipler, Martin Leucker, Patrick Rodler Published: 2026-06-18 Categories: cs.SE, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2606.23720v1 We present an integrated framework that unifies runtime verification and model-based diagnosis within the stream specification language LOLA. By encoding system descriptions, component health states, and observations into a single stream-based formalism, the approach enables continuous, online fault localization directly alongside fault detection, without requiring separate toolchains. The framework supports both time-invariant and transient faults, and naturally accommodates nondeterministic observations. --- ### Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet Authors: Milan Miletić, Julie Kallini, Ekaterina Shutova Published: 2026-06-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.20993v1 Multilingual language models often exhibit performance disparities across languages that can arise as early as the tokenization stage. Widely-used subword tokenization approaches favor high-resource languages, and tokenizer-free methods still yield longer sequences for scripts with a higher bytes-per-character ratio. To address these shortcomings, we propose to use the International Phonetic Alphabet (IPA) as a language-agnostic input representation for multilingual tokenizers. IPA provides a compact symbol inventory, greater cross-lingual character overlap, and a more balanced byte-per-character distribution across languages. We train matched pairs of text vs. IPA subword tokenizers across 24 languages and 14 scripts and demonstrate that IPA tokenizers consistently improve tokenization quality, especially for non-Latin scripts, and generalize more effectively to unseen languages and scripts. --- ### Text-to-Image Generative AI for Modeling and Simulation: Methods, Opportunities, and Applications Authors: Philippe J. Giabbanelli Published: 2026-06-18 Categories: cs.ET, cs.AI arXiv: https://arxiv.org/abs/2606.20991v1 Text-to-image generation is a form of generative artificial intelligence (GenAI) that converts textual descriptions into images. Most applications of GenAI in modeling and simulation (M&S) have focused on large language models for documentation, coding, or explanation. By contrast, the potential of image generation remains largely unexplored. This tutorial introduces text-to-image generation to the M&S community and details how it can support several M&S tasks, including communicating conceptual models, visualizing simulation outcomes, generating educational materials, and interfacing heterogeneous models in multi-scale simulations. The tutorial combines conceptual guidance with practical workflows, explaining how modern image generators operate, how prompts and simulation outputs can be translated into visual scenes, and how practitioners can integrate these tools into reproducible local pipelines. By focusing on transferable principles rather than specific tools, the tutorial equips M&S practitioners with the knowledge needed to evaluate, adopt, and adapt text-to-image generation in their simulation workflows. --- ### Physics-Guided Fully Convolutional Spatiotemporal Learning Toward Digital-Twin-Enabled Microstructure Evolution Prediction Authors: Michael Trimboli, Wenxi Liu, Xianqi Li Published: 2026-06-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.20983v1 Understanding and predicting microstructure evolution is central to materials design, yet purely data-driven spatiotemporal learning models often suffer from limited physical consistency and degraded long-term prediction accuracy. In this work, we introduce a physics-guided fully convolutional spatiotemporal learning framework for microstructure evolution prediction. Unlike prior self-supervised approaches, the proposed method explicitly incorporates governing physical equations into the training objective, thereby encouraging the learned dynamics to remain consistent with known thermodynamic and kinetic laws. This physics-guided formulation improves predictive accuracy, long-horizon stability, and robustness across spatial resolutions and temporal prediction settings. Extensive experiments for spinodal decomposition demonstrate that incorporating physics-guided residual regularization leads to more faithful reproduction of microstructural morphology, statistics, and evolution trends compared with purely data-driven baselines. The proposed framework preserves the scalability and computational efficiency of fully convolutional architectures while bridging the gap between high-fidelity physics-based simulations and data-driven surrogate modeling, offering a reliable and efficient surrogate-modeling step toward digital-twin-enabled microstructure evolution prediction. --- ### Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City Authors: Adrian Cespedes, Marcelo Chincha, Dunant Cusipuma, Victor Flores-Benites, David Ortega, Arturo Deza Published: 2026-06-18 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.20980v2 As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how well will these systems generalize in new settings, in particular out-of-distribution (OOD) edge-case scenarios in new geographies? In this paper, we study this open question by providing a full factorial analysis with human drivers of Lima, human drivers from New York City, and VLMs and showing them dashcam footage collected from Lima and New York City -- prompting them with a variety of questions under a Visual Question Answering (VQA) paradigm. In particular, we pick these two cities as they are highly challenging driving locations where no Self-Driving Car company currently operates in, and ask questions that span 4 categories: Factual, Ratings, Counterfactual and Reasoning. We find that Humans and VLMs diverge in their responses -- though this is modulated by the type of questions asked, and that Humans answer similarly independent of where they are from (Lima/NYC). To our surprise, we did not find a strong difference in terms of answers (Humans or VLMs) that was modulated by geography, likely due to their high out-of-distribution nature. Our dataset is available at: https://huggingface.co/datasets/Artificio/robusto-2 --- ### Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City Authors: Adrian Cespedes, Marcelo Chincha, Dunant Cusipuma, Victor Flores-Benites, David Ortega, Arturo Deza Published: 2026-06-18 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.20980v1 As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how well will these systems generalize in new settings, in particular out-of-distribution (OOD) edge-case scenarios in new geographies? In this paper, we study this open question by providing a full factorial analysis with human drivers of Lima, human drivers from New York City, and VLMs and showing them dashcam footage collected from Lima and New York City -- prompting them with a variety of questions under a Visual Question Answering (VQA) paradigm. In particular, we pick these two cities as they are highly challenging driving locations where no Self-Driving Car company currently operates in, and ask questions that span 4 categories: Factual, Ratings, Counterfactual and Reasoning. We find that Humans and VLMs diverge in their responses -- though this is modulated by the type of questions asked, and that Humans answer similarly independent of where they are from (Lima/NYC). To our surprise, we did not find a strong difference in terms of answers (Humans or VLMs) that was modulated by geography, likely due to their high out-of-distribution nature. Our dataset is available at: https://huggingface.co/datasets/Artificio/robusto-2 --- ### How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs Authors: Honjar Xing, Jefferson Lin, Henry Lieberman Published: 2026-06-18 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2606.20978v1 Programming by Demonstration (PbD) offers a human-centered way to author procedural knowledge for LLM agents: users communicate what they want by showing rather than by writing prompts or code, making agent authoring accessible to non-programmers. The natural output of a PbD recording is a flat action log, but how this log is organized before being passed to the agent is an open design question with significant consequences for plan quality. We propose grouping recorded actions into labeled, hierarchical subgoals and evaluate the effect of this organizational structure in a controlled experiment. Across 85 web automation tasks, we compare a zero-shot baseline against four demonstration formats that share identical action sequences but differ in structure. On 43 natural-language tasks with vague descriptions, hierarchically grouped demonstrations improve pass rates from 76.7\% to 90.7\% (paired permutation test $p{=}0.034$; win-loss 6:0), while flat demonstrations show a smaller, non-significant improvement. On 42 tasks with precise descriptions, no format provides any benefit, confirming that the hierarchical advantage arises specifically when descriptions leave procedural details ambiguous. Ablation shows that subgoal grouping alone drives the effect: preconditions, postconditions, and parameter annotations add no measurable benefit. These results offer a concrete design recommendation for PbD pipelines and, more broadly, for any system that feeds procedural context to an LLM agent: segment action sequences into named subgoal groups rather than presenting flat step lists. --- ### Detecting Satellites in Radio-Frequency Data via Semi-Supervised Learning Authors: Cade W. Trotter, Maksim E. Eren, Justin C. Holmes, J. Brent Parham, David Ewing, Boian S. Alexandrov, Gian Luca Delzanno Published: 2026-06-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.20976v1 Radio-frequency (RF) monitoring is essential for space domain awareness, but it often generates large, variable, and sparsely populated datasets with few labels. These observations can capture satellites, space debris, and the ionospheric background, yet interpreting them typically requires specialized subject-matter expertise. Supervised deep learning methods can perform well on labeled RF data, but they require many annotated examples and may need careful retraining as RF conditions change. Semi-supervised approaches offer a practical alternative for limited-data settings by using unlabeled observations to reveal latent patterns that experts can interpret. In this paper, we present a semi-supervised RF detection and classification workflow for satellite monitoring that combines Non-negative Matrix Factorization with automatic model determination (NMFk), expert-guided cluster interpretation, and classifier-based prediction. We first represent RF observations as a non-negative feature matrix and apply NMFk to estimate the number of clusters that best captures patterns in the unlabeled data. Subject-matter experts then assign physical meaning to the resulting clusters, including satellite detections, ionospheric environmental conditions, and other RF event categories. Finally, we train a classifier on these interpreted clusters to evaluate performance on a test set and categorize future observations. This pipeline reduces reliance on large pre-labeled datasets by pairing unsupervised factorization with expert interpretation, enabling an interpretable and transferable methodology for detecting, observing, and classifying behavior in RF data. --- ### UNITY: Attention Flow Networks for Adaptive Conditioning in Diffusion Authors: Aryan Das, Koushik Biswas, Moloud Abdar, Vinay Kumar Verma Published: 2026-06-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.20971v2 We introduce UNITY, a Universal-to-Specialized adapter for efficient and scalable composite conditioning in diffusion based image generation. Unlike prior methods that train separate adapters for each conditioning modality, UNITY jointly learns shared semantics across multiple conditioning types and subsequently specializes without modifying the underlying architecture. The proposed two stage training paradigm consists of a Universal Stage that captures cross modal representations across all conditioning modalities using half of the total training steps, followed by a Specialization Stage that refines modality specific features using the remaining training budget. At the core of UNITY are the Morphable Attention Flow (MAF) Network and Morph Wrapper modules, which enable channel aware and spatially adaptive feature alignment through learnable flow fields and attention based fusion. This constant complexity formulation supports flexible operation under both single and composite conditioning settings while significantly reducing inference latency and memory consumption. Extensive experiments across multiple datasets demonstrate that UNITY achieves state of the art image fidelity while maintaining superior memory efficiency. Code: https://github.com/arya-domain/UNITY --- ### CogniRoute: Learning to Route Social Evidence in Omni-Modal Models Authors: Yifan Shen, Pei Tian, Xinzhuo Li, Bowen Fang, Shujun Xia, Bingxuan Li, Ana Jojic, Wenming Ye, Xu Cao, James Matthew Rehg, Ismini Lourentzou Published: 2026-06-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.20970v1 Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially pronounced in social video question answering, where the answer may hinge on a gesture, vocal tone, temporal cue, or mismatch between what is said and what is visually expressed. We introduce CogniRoute, a schema-guided Mixture-of-Experts framework for social omni reasoning. CogniRoute uses a training-only cognitive schema that factorizes each example by cross-modal relation, reasoning demand, and temporal scope, and aligns global routing signatures with this structure during supervised fine-tuning. We further introduce route-aware reinforcement learning, which jointly optimizes token generation and expert allocation using rewards for answer correctness, modality-consistent reasoning, and cognitive temporal grounding. To support training and evaluation, we construct OmniSocialBench, a diagnostic social video QA resource with 118K structured training examples, grounded reasoning traces, schema labels, temporal evidence spans, and a manually verified evaluation split. CogniRoute achieves 59.38\% average accuracy on OmniSocialBench, improving over the strongest proprietary baseline by 15.33 percentage points and the strongest open-source omni baseline by 26.77 points, with the largest gains on questions requiring audio-visual coordination, conflict resolution, and temporally grounded social inference. --- ### AutoACSL: Synthesizing ACSL Specifications by Integrating LLMs with CPG-Based Static Analysis Authors: Han Zhou, Yu Luo, Dianxiang Xu Published: 2026-06-18 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.20969v1 Generating formal specifications for C programs remains a challenge in formal verification due to the manual effort, expertise, and semantic precision required. While recent advancements in large language models (LLMs) offer promise in automating specification synthesis, current approaches often lack semantic depth and produce unverifiable or incomplete contracts. To address these limitations, we introduce AutoACSL, a novel framework that integrates LLM prompting with semantic features extracted from Code Property Graphs (CPGs). AutoACSL performs static analyses to extract key semantic elements, including arithmetic operations, loop and recursion structures, and return value propagation, which are encoded into structured prompts. These prompts enable the LLM not only to generate normal behavioral specifications but also to include constraints that prevent inputs leading to runtime errors. AutoACSL employs a feedback-driven synthesis loop, where candidate specifications are verified using Frama-C/WP and refined iteratively until verification succeeds or a termination condition is met. Evaluated on 604 programs drawn from diverse datasets, AutoACSL achieves a 98% specification generation success ratio and a 96% full proof ratio when paired with Gemini-3. Compared to a code-only baseline, AutoACSL improves the full proof ratio by 24.7% to 51.7% across four LLMs (GPT-o4 Mini, GPT-5.2, Grok-4.1, and Gemini-3), demonstrating that integrating large language models with CPG-based static analysis substantially enhances both generation robustness and verification effectiveness for automated ACSL specification synthesis. --- ### Formalizing Task-Space Complexity for Zero-Shot Generalization Authors: Jung-Hoon Cho, Heling Zhang, Siqi Du, Roy Dong, Cathy Wu Published: 2026-06-18 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2606.20967v1 Policies must operate across diverse conditions, yet a single policy is often conservative while fully adaptive schemes can be complex. We study zero-shot generalization in contextual dynamical systems and introduce a performance-centric, directional task dissimilarity--the signed divergence--that upper bounds the generalization gap from a source context to a target context. The signed divergence induces $\varepsilon$-tolerance sets that certify when a source policy class generalizes, and it yields a concrete notion of task-space complexity: the minimum number of source contexts needed so that every target context incurs at most $\varepsilon$ generalization gap. Under a mild local smoothness assumption on performance, the induced tolerance sets admit certified inner/outer balls and instance-dependent volume bounds on task-space complexity. In the finite-oracle setting, source selection reduces to set cover; a greedy strategy inherits the standard $H(n)$ approximation guarantee. Using a Mass-Spring-Damper system with linear-quadratic regulator (LQR) controllers and a nonlinear CartPole system with deep reinforcement learning controllers, we show that greedy selection achieves the same $\varepsilon$-coverage with fewer policies than uniform or random baselines. Our approach delivers a performance-based task similarity measure and practical certificates for building generalizable control with simple policies. --- ### Generative Responsible AI Data Evaluation Schema (GRAIDES) for AI Assurance in Local Government Authors: Ethan Knights, Christopher Conlan, Temilorun Gbolahan, Stephen Waterman, Gurpreet Muctor Published: 2026-06-18 Categories: cs.AI, cs.CY, cs.DB arXiv: https://arxiv.org/abs/2606.20963v1 Trust in the application of generative Artificial Intelligence (AI) relies on well-governed measurable evidence of performance and safety. In practice, however, evaluation data is often fragmented across systems, inconsistently structured and difficult to compare. We introduce the Generative Responsible AI Data Evaluation Schema (GRAIDES) as a lightweight open-source data model for centralising AI observability across popular vendors. Practical blueprints for code, architecture and statistical evaluation are shared as guidance about how to approach generative system assurance at the organisational level. Illustrative case study results are reported from Westminster City Council's AI catalogue with a focus on measuring human-model alignment including detecting systematic disagreement between evaluators. By framing evaluations as a data modelling problem, GRAIDES provides a practical pathway toward more consistent and reproducible benchmarking, tuning and assurance activities for generative AI systems. --- ### Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs Authors: Van-Tuan Tran, Shruthi Gowda, Merim Dzaferagic, Marco Ruffini Published: 2026-06-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.20961v1 Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains, but the state-of-the-art MR-LoRA method highly relies on the assumption that a MLLM-based router is necessary to process complex multimodal inputs. This paper revisits this claim on the MLLM-CL benchmark and argues for two claims. \textbf{First}, routing does not require an MLLM: a simple training-free, replay-free ptotypical routing method (\textsc{RePRo}), uses frozen pretrained features and task prototypes to match the MLLM-based router of MR-LoRA at far lower computational cost. \textbf{Second}, shared experts do not improve continual learning for MLLMs, despite their theoretical appeal. We show that these findings arise from two structural limitations of MLLM-CL: (1) its tasks are \textbf{highly separable} in representation space, and (2) its fixed task order makes conclusions \textbf{sensitive to a single curriculum} rather than robust across diverse continual-learning trajectories. As a result, the benchmark primarily rewards learning in isolation rather than genuine continual transfer. This motivates a new design for future benchmarks of continual MLLM learning, with overlapping task manifolds, multiple task orders, fine-grained domain shifts, and evaluation protocols that reward forward transfer as well as retention. --- ### Equilibrium with Internal Transfers Authors: Mingyang Liu, Gabriele Farina, Asuman Ozdaglar Published: 2026-06-18 Categories: cs.GT, cs.LG, econ.TH arXiv: https://arxiv.org/abs/2606.20960v1 Nash equilibrium (NE) arises from selfish utility maximization, yet its social welfare can be arbitrarily far from optimal. Moreover, computing an NE is intractable in general. We study augmented game models in which players use budget-balanced internal transfers to improve incentives before play. We first introduce \emph{Self-Enforcing Transfer Equilibrium} (SETE), where players commit to nonnegative peer-to-peer transfers that are paid only if the recipient does not deviate from a prescribed strategy. For polymatrix games, we show that every stationary point of the social welfare function, in particular any socially optimal strategy profile, can be sustained as a SETE. This induces a Nash equilibrium in the agent normal form of the corresponding augmented game. We further propose a polynomial-time algorithm and a decentralized learning dynamic to compute such product-form equilibria. We then introduce \emph{Mediated Self-Enforcing Transfer Equilibrium} (M-SETE), where a mediator makes both the payment schedule and the prescribed strategies binding offers. This additional enforcement resolves the agent-normal-form limitation: an M-SETE is a Nash equilibrium of the augmented game itself, not merely of its agent normal form, and any socially optimal strategy profile can be supported as an M-SETE in any finite game while preserving budget balance. Thus, internal transfers improve welfare and computation while preserving independent play on the equilibrium path. When full sequential-game stability is required, binding mediation provides the corresponding implementation. --- ### Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models Authors: Elias Hossain, Sourav Saha, Tasfia Nuzhat Ornee, Sanjeda Sara Jennifer, Umesh Chandra Biswas, Shubhashis Roy Dipta, Rajib Rana, Niloofar Yousefi Published: 2026-06-18 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.20959v3 Language models may encode both outdated facts and their newer replacements. We introduce Parametric Temporal Conflict (PTC), where the newer fact is present and recoverable, but the default forward pass prefers the outdated one. We release a deterministically verified benchmark of 8,746 Wikidata position-holder transitions and evaluate four open-weight language models across three families. A date-prefix prompt recovers the newer fact in 61-81% of PTC cases. Activation patching flips predictions in 72-85% of cases and localizes the preference to model-specific upper-layer regions. Residual-stream steering outperforms norm-matched random directions, indicating direction-specific representations. These results show that PTC reflects a localized representational preference rather than missing knowledge. Recovery is measured on oracle-identified conflicts because automatic detection remains unreliable. We release the benchmark, code, and statistics. --- ### A Gated Graph Neural Network Approach to Fast-Convergent Dynamic Average Estimation Authors: Antonio Marino, Claudio Pacchierotti, Paolo Robuffo Giordano Published: 2026-06-18 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2606.20955v1 Dynamic average estimation is a critical problem in multi-agent systems, enabling agents to collaboratively estimate time-varying signals using only local information exchange. Traditional model-based approaches often face challenges related to convergence speed and sensitivity to network topology changes. This paper introduces a novel learning-based solution leveraging Gated Graph Neural Networks (GGNNs) for fast-convergent dynamic average estimation in a fully distributed manner. Taking advantage of the inherent structure of GGNNs, the proposed method models the estimation process as a distributed autoregressor, ensuring rapid convergence while maintaining stability. We incorporate a regularization term during training to enforce convergence guarantees and introduce an encoding-decoding mechanism to reduce communication overhead without sacrificing accuracy compared to standard GGNNs. Extensive numerical experiments demonstrate that our approach significantly outperforms conventional model-based estimators in terms of both convergence speed and precision, making it a promising alternative for multi-agent applications that require dynamic average estimation. --- ### Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning Authors: Nusrat Jahan Lia, Aritra Mazumder Published: 2026-06-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.20954v2 Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an eviction policy drops a task-critical detail, for example an access token issued at login or a path the next call needs, the action fails. We present LRE (Learned Relevance Eviction), a kilobyte-scale, CPU-only, language-model-free scorer that learns which units of history are task-critical and keeps them by verbatim extraction. Under a matched-budget comparison, in our experiment, no baseline dominates LRE on the accuracy-cost plane. On agents, LRE recovers 93% of the aggregate accuracy of keeping the entire history (41.1 vs. 44.0) and exceeds it by 27% on the simplest tasks, while requiring zero compressor calls and cutting the worst-case peak prompt by 52%. A controlled study trace shows LRE completes tasks where the others loop, finishing one such task in 37% fewer calls than keeping everything and solving 14 tasks where no other run policy does. On conversational memory, LRE outranks dense and token-pruning encoders at zero neural cost while being 295-1569x smaller in size. In downstream evaluation, LRE gives the best budgeted answer quality on LoCoMo reading 68% fewer tokens. Its supervision can also be annotation-free: training only on the system's own behavior recovers 95% of the supervised scorer's effectiveness. We argue that, because memory eviction in LLM agents is a fidelity problem, it requires a deployable proactive policy where the future query is unavailable and exact state is decisive, and that cheap learned relevance can be sufficient. --- ### Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning Authors: Nusrat Jahan Lia, Aritra Mazumder Published: 2026-06-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.20954v1 Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an eviction policy drops a load-bearing detail, for example an access token issued at login or a path the next call needs, the action fails. We present LRE (Learned Relevance Eviction), a few kilobytes, CPU-only, language-model-free scorer that learns which units of history are load-bearing and keeps them by verbatim extraction. Under a matched-budget comparison, in our experiment, no baseline dominates LRE on the accuracy-cost plane. On agents, LRE matches the accuracy of keeping the entire history overall. On the simplest tasks, it exceeds that no-eviction baseline by 27%, while requiring zero compressor calls and reducing peak context size by up to 52%. A controlled study trace shows LRE completes tasks where the others loop, finishing one such task in 37% fewer calls than keeping everything and solving 14 tasks where no other run policy does. On conversational memory, LRE outranks dense and token-pruning encoders at zero neural cost. In downstream evaluation, LRE gives the best budgeted answer quality on LoCoMo reading 68% fewer tokens. Its supervision can also be annotation-free: training only on the system's own behavior recovers 95% of the supervised scorer's effectiveness. We argue that, because memory eviction in LLM agents is a fidelity problem, it requires a deployable proactive policy where the future query is unavailable and exact state is decisive, and that cheap learned relevance can be sufficient. --- ### Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering Authors: Sergei Trashchenkov Published: 2026-06-18 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2606.20950v2 Executable evaluation -- checking the consequences of an agent's actions with a program rather than grading its prose -- has become a prominent way to assess tool-using AI agents in software settings. Electric power engineering has not yet had an analogous benchmark: language-model use is still dominated by retrieval and text question answering, while agents acting on power-system artifacts remain mostly academic prototypes. We introduce the Power Systems Agent Benchmark, an executable benchmark for power-engineering agents. An agent receives a structured task and returns a structured solution; a deterministic evaluator recomputes the engineering quantities, checks operational constraints, and returns a feasibility flag, a normalized score, and explicit violations. The benchmark contains 41 task families across eight areas of power engineering, from power flow and protection to stability, microgrids, reliability, power quality, and forecasting. Each task is grounded in a citable source, standard, or documented engineering formulation. To resist contamination, held-out cases are synthesized on demand by per-family generators from private seeds: the construction is inspectable, but the instances remain private. In a reference evaluation with three command-line agents, the strongest score near the compact tier's ceiling, a smaller open model trails, and public and held-out performance are broadly consistent; a separate public-split grid with OpenCode and Aider probes harness effects. The reference evaluation doubles as quality control: unanimous failures flag candidate task or evaluator defects, and it exposed a latent evaluator bug missed by self-consistency checks. The evaluators are compact deterministic surrogates, but the task contract allows their internals to be upgraded to simulator-backed checks without changing how tasks are posed or solved. --- ### Scaling Diverse Language Generation for 3D Visual Grounding Authors: Austin T. Wang, Dongchen Yang, Angel X. Chang Published: 2026-06-18 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2606.20946v1 Developing robust models for 3D visual grounding (3DVG), the localization of entities in a 3D scene described in natural language, is important for enabling agents to correspond spatial language with objects in the physical world. However, the lack of diverse descriptions at scale prevents models from generalizing beyond simple linguistic patterns. Recent such attempts lack diversity in the constraint types and language used to ground objects. Captioning methods cannot precisely contrast objects, which is important for visual grounding. We therefore propose ViGiL3D++, a scalable, scene-agnostic method that generates diverse visual grounding queries by combining constraint sampling in scene graphs with the language generation of LLMs. We show that it has greater diversity over existing scaled datasets and improves model performance over several 3DVG benchmarks but also illuminates outstanding limitations of VLMs. --- ### Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention Authors: Vishesh Tripathi, Abhay Kumar Published: 2026-06-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.20945v2 Self-attention is central to Transformer performance and is often the most expensive part of the Transformer at long context lengths because its pairwise token interactions scale quadratically with sequence length. Standard dense attention also applies the same set of attention heads to every token regardless of token difficulty or information content. This uniform activation can waste compute, especially as sequences grow longer and attention cost increases rapidly. We propose Grouped Query Experts (GQE), a mixture-of-experts layer on top of grouped-query attention (GQA). Within each GQA group, a router selects k query-head experts per token while all key-value (KV) heads remain dense and unchanged. Thus, GQE keeps the KV cache benefits of GQA and reduces only the active query-head computation. On a fixed 30B token budget at the 250M parameter scale, GQE matches the all-active GQA baseline in downstream accuracy while activating half the query heads per token. --- ### Learning through Internalization Authors: Nikolaos Tsilivis, Nirmit Joshi, Marko Medvedev, Julia Kempe, Nati Srebro Published: 2026-06-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.20937v1 We study internalization processes, by which neural-network-based systems absorb an explicit computational procedure into their own weights, and how they facilitate learning. We investigate how transformers internalize the simulation of semiautomata by internalizing chain-of-thought (CoT) tokens, which classes of semiautomata are harder to internalize, and expose the flip side of internalization, that is, a progressive degradation of out-of-distribution performance. We then provide the first provable analysis of successful internalization: for the task of learning parities, we show that a simplified one-layer transformer provably first learns the target with explicit CoT supervision and then internalizes the autoregressive generation as CoT tokens are progressively removed, learning to directly compute the parity. This task is computationally hard to learn from data without CoT supervision. Finally, we discuss how learning through internalization relates to the \textit{Positive Distribution Shift} phenomenon recently introduced by~\citet{Med+26}. --- ### Comparing Transformers and Hybrid Models at the Token Level Authors: Yanhong Li, William Merrill Published: 2026-06-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.20936v1 Hybrid language models that mix attention and recurrent layers have shown promise: theoretically, recurrent layers ameliorate the limitations of pure transformers on state tracking, and empirically, hybrids can outperform pure transformers in loss and downstream evaluations \citep{waleffe2024empirical,merrill2026olmohybrid}. Yet it remains unclear which data or capabilities drive these gains, and to what degree they reflect the theoretical advantages motivating hybrid models. We address this question using the open weights from Olmo 3 \citep{olmo2025olmo3} and Olmo Hybrid \citep{merrill2026olmohybrid}: we compare the loss of a matched transformer and hybrid at the same target tokens under the same prefixes, stratifying the results by natural token tags, copy features, delimiter structure, and controlled synthetic probes. The hybrid has lower loss on most tag families, but the gains are not uniform: they are largest for open-class content words and smaller for many closed-class function words. Across prose, code, and markup, the hybrid's loss advantage is larger on opening delimiters than on the corresponding closing delimiters, and nearly vanishes on repeated $n$-grams. Synthetic probes show the same split: the hybrid is favored on pronoun-memory and entity-tracking tasks, whereas the transformer is favored on bracket-matching tasks that require choosing closing delimiters. These patterns suggest that the recurrent layers in hybrids improve predictions that leverage the semantic state of a document, whereas attention helps on tokens predictable by $n$-gram copying or syntactic bracket matching. We conclude with proof-of-concept filtered evaluations showing how token-level decompositions can sharpen pretraining diagnostics for hybrid architectures. --- ### Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study Authors: Anton Abramochkin, Radu Timofte, Dmitry Ignatov Published: 2026-06-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.20933v1 The choice of loss function and optimizer is an important decision, that shapes further model training. Yet automated architecture search pipelines (AutoML) benefits significantly more from the optimal pairing selection and vice versa. This paper investigates whether a single recipe is sufficient for heterogeneous architecture pools, or whether the optimal pairing varies across structurally diverse models. We conduct a systematic empirical study of all $3 \times 6 = 18$ combinations of six optimizers (SGD+Momentum, Adam, AdamW, RMSprop, Adagrad, Adadelta), paired with three loss functions: Cross-Entropy (CEL), Negative Log-Likelihood (NLL), and the recently introduced genetically evolved NGL loss across the base models presented in LEMUR heterogeneous architecture pool on six image classification datasets (CelebA-Gender, CIFAR-10, CIFAR-100, ImageNette, MNIST, SVHN). The 18 loss-optimizer configurations are applied to each of the 33 compatible base architectures taken from the LEMUR pool, resulting in 594 variants that were generated fully automatically by a source-level injection pipeline and evaluated under fixed hyperparameters, ensuring that observed accuracy differences are attributable solely to the loss-optimizer pairing. Our results confirm that no single pairing is universally optimal. Cross-Entropy with Adam or AdamW is the most robust choice across architecture families and datasets. NGL is a competitive alternative to CEL on standard convolutional classifiers, but only when paired with adaptive optimizers; it degrades substantially with SGD or accumulation-based methods. Adagrad and Adadelta consistently underperform under fixed hyperparameters regardless of loss function, highlighting their sensitivity to learning rate tuning. These findings provide actionable guidance for loss-optimizer selection within NNGPT Framework. --- ### Hierarchical Pooling for Sheaf Neural Networks Authors: Dionisia Naddeo, Carlo Abate, Pietro Liò, Nicola Toschi, Filippo Maria Bianchi Published: 2026-06-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.20932v1 Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction maps to measure compatibility across edges. Unlike standard graph diffusion, which encourages neighboring node features to become similar, sheaf diffusion promotes consistency through the restriction maps and can therefore model more general relationships between neighboring nodes. However, existing sheaf neural architectures mainly operate at a fixed graph resolution and do not provide a principled pooling mechanism for building hierarchical representations. In this paper, we introduce Hierarchical Sheaf Pool (HiSP), a sheaf-aware pooling framework based on local spectral coarsening. Given a partition of the graph, HiSP constructs each coarse stalk by projecting fine stalk-valued features onto the low-frequency eigenmodes of the cluster-internal sheaf Laplacian. These local modes define a cochain-level prolongation map, which allows the fine sheaf energy to be represented on the coarse space through a Galerkin operator. We further analyze the approximation induced by coarsening by separating truncation loss, due to discarded local modes, from realization loss, due to representing the projected operator as a coarse sheaf. Finally, we implement HiSP as a GNN pooling layer compatible with SNNs and provide a PyG implementation supporting batching, lifted sheaf Laplacians, and hierarchical architectures. --- ### Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification Authors: Sudipta Santra, Debtanu Datta, Saptarshi Ghosh Published: 2026-06-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.20929v1 Large Language Models (LLMs) are increasingly being adopted in the legal domain. However, despite their strong performance, LLMs are prone to generating incorrect or hallucinated outputs, raising serious concerns about their reliability in high-stakes domains such as law. Detecting the correctness of responses of LLM-based systems is therefore a critical challenge. In this work, we explore the potential of leveraging internal artifacts of LLM to detect the correctness of their predictions in legal-domain classification tasks. We develop approaches that utilize features derived from these internal artifacts to build downstream classifiers capable of identifying incorrect LLM outputs. We evaluate our approach on two representative legal classification tasks: bail decision prediction and statute violation prediction. Our experimental results demonstrate that LLMs' internal artifacts are reliable indicators for detecting incorrect predictions in legal classification tasks, and can be applied to enhance the reliability of LLM-based classification systems. --- ### ELDiff: When Evidential Learning Meets Text-to-Image Diffusion Authors: Qingtao Pan, Kai Ye, Zhihao Dou, Bing Ji, Shuo Li Published: 2026-06-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.20924v1 In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image synthesis. However, such consistency constraint is often underemphasized in the denoising process of diffusion models. Although token supervised diffusion models can mitigate this issue by learning object-wise consistency between the image content and object segmentation maps, it tends to suffer from the problems of segmentation map bias and semantic overlap conflict, especially when involving multiple objects. In this paper, we propose ELDiff, a new evidential learning-supervised T2I diffusion model, which leverages the advantages of uncertainty metric and conflict detection to enhance the fault tolerance of unreliable segmentation maps and suppress semantic conflicts, strengthening object-wise consistency learning. Specifically, a pixel evidence loss is proposed to restrain overconfidence in unreliable labels through evidential regularization, and a token conflict loss is designed to weaken the contradiction between semantics through optimizing a measured conflict factor. Extensive experiments show that our ELDiff outperforms existing training based and train-free based T2I diffusion models on SD v1.4, SD v2.1, SDXL, SD v3.5, and Qwen-Image, without requiring additional inference-time manipulations. Notably, ELDiff can be seamlessly extended to the existing training pipeline of T2I diffusion models. Code can be found at https://github.com/QingtaoPan/ELDiff. --- ### $Ω$: Operator-based Mixture Ensemble for Generative Assimilation Authors: Pouria Behnoudfar, Nan Chen Published: 2026-06-18 Categories: cs.LG, math.DS arXiv: https://arxiv.org/abs/2606.20920v1 Characterizing non-Gaussian posterior distributions in partially observed high-dimensional nonlinear systems remains a fundamental challenge in data assimilation. Ensemble Kalman filters rely on Gaussian approximations that can be inaccurate for strongly non-Gaussian posteriors, whereas particle filters suffer from severe scalability limitations. Recent score-based generative approaches improve posterior characterization but typically require supervised training with ground-truth posterior samples, which are unavailable in most practical applications. We introduce $Ω$ (Operator-based Mixture Ensemble for Generative Assimilation), a scalable framework that integrates conditional Gaussian surrogate modeling, unsupervised score learning, and generative sampling. The conditional Gaussian surrogate provides a nonlinear non-Gaussian baseline approximation while admitting closed-form conditional posterior distributions for the unresolved variables. First, $Ω$ exploits these closed-form conditional distributions to analytically recover the high-dimensional unobserved component, reducing computational cost and mitigating the curse of dimensionality. Second, $Ω$ learns only the residual discrepancy beyond an analytical baseline through denoising score matching using ensemble trajectories alone, eliminating the need for ground-truth posterior samples and substantially reducing the learning burden. Third, $Ω$ reconstructs the full non-Gaussian posterior distribution of both observed and unobserved variables via a Gaussian mixture representation, capturing multimodal, skewed, and heavy-tailed statistics. Finally, $Ω$ employs annealed Langevin sampling to iteratively refine ensemble members from the baseline toward the target posterior. $Ω$ is validated on several turbulent models with intermittency and extreme events, consistently improving posterior accuracy. --- ### GIM-ENDO: A Multimodal Endoscopic Image and Video Dataset for Gastric Intestinal Metaplasia Morphology and Pathology Authors: Mojgan Forootan, Mahziar Setayeshfar, Ali Darvishi, Mohammad Tashakoripour, Hamidreza Bolhasani Published: 2026-06-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.20919v4 Gastric intestinal metaplasia (GIM) is a precursor lesion to gastric dysplasia and adenocarcinoma whose early detection is crucial for intervening in the carcinogenesis cascade. Artificial intelligence (AI) holds considerable promise for real-time endoscopic detection and characterization of GIM. However, development of reliable AI models has been constrained by the absence of publicly available, histopathologically validated datasets that combine detailed endoscopic annotations, histological subtype (complete and incomplete), standardized grading systems, and normal mucosal patterns. GIM-ENDO was designed to fill this gap. The dataset comprises demographic data, endoscopic findings, histopathological results, and H. pylori status acquired using the Olympus EVIS X1 system with white-light endoscopy (WLE) and image-enhanced endoscopy (IEE), including narrow-band imaging (NBI) and magnifying NBI (M-NBI), along with images and video clips from 24 patients (22 GIM-positive, 2 normal controls). Annotations cover six primary IEE endoscopic signs -- light blue crest (LBC), marginal turbid band (MTB), white opaque substance (WOS), TV pattern (Fusion), atrophy, and map-like erythema (MLE) -- plus two additional endoscopic findings (AHP and GA) recorded where present. GIM subtypes (complete and incomplete) are annotated for all GIM-positive cases; OLGA and OLGIM staging are provided where complete histological sampling was available. The dataset is publicly accessible at https://doi.org/10.5281/zenodo.20707267. For the latest updates and further information regarding this dataset, readers are referred to the DataBioX website: https://databiox.com A short version of this work has been submitted to MICCAI 2026 Open Data Track. --- ### Short-Term Electricity Demand Forecasting for New England: A Comprehensive Machine Learning Benchmark with Weather, Calendar, and COVID-19 Indicators Authors: Reza Ghanavati, Behrooz Mosallaei Published: 2026-06-18 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2606.20918v2 Accurate short-term electricity demand forecasting is critical for reliable power system operation, energy market planning, and infrastructure optimization. This paper benchmarks ten machine learning models for daily electricity demand forecasting across the New England ISO (February 2020 - March 2023). The models span four families: tabular gradient-boosted trees (Random Forest, LightGBM, CatBoost, XGBoost), standalone neural architectures (LSTM, Transformer encoder), and hybrid Transformer+tree variants (Hybrid XGBoost, Hybrid LightGBM, Hybrid CatBoost, Hybrid RF). All models use meteorological data from six cities, calendar and holiday effects, autoregressive demand lags, and COVID-19 epidemiological variables. Hyperparameter optimization uses Optuna (300 trials, multivariate TPE, seed=42) under a leakage-free 70/15/15 chronological split. CatBoost achieves the best test performance: RMSE 8316 MWh, MAPE 1.87%, R-squared 0.917, followed by XGBoost (9066 MWh, R-squared 0.901), Hybrid CatBoost (9068 MWh, R-squared 0.901), and Hybrid XGBoost (9208 MWh, R-squared 0.898). Standalone neural architectures perform substantially worse (Transformer: 21294 MWh; LSTM: 22808 MWh), confirming the Transformer's role as a feature extractor rather than an end-to-end forecaster. An ablation on CatBoost shows that demand lags are the dominant predictor: removal degrades RMSE from 8316 to 11310 MWh (+36%), while weather and calendar features alone achieve an R-squared of 0.864. Removing COVID-19 features improves test RMSE by 1.7% while reducing training RMSE by 17.3%, a signature of temporal validity decay. SHAP analysis confirms this: 3 of 8 COVID features rank higher on the post-acute test set than during pandemic-active training, indicating the model over-applies stale pandemic patterns after behavioral adaptation was complete by August 2022. --- ### Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels Authors: Yuecheng Cai, Jasmin Jelovica Published: 2026-06-18 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2606.20916v1 Iterative design and optimization of large, complex structures require fast and accurate prediction of stress, displacement, and other fields. Finite element analysis (FEA) is computationally expensive for this task. Existing neural network surrogates often struggle with varying topologies and complex boundary conditions. This study proposes the novel Dual-Stream Heterogeneous Graph Neural Network (DS-HGNN) for full-field stress and displacement prediction in thin-walled structures, demonstrated on box beams made of stiffened panels. DS-HGNN operates on panel-level heterogeneous graph representations and introduces physics-guided edge states initialized from edge types, spatial information, and boundary kinematics. These states are updated through dual-stream message passing that separates longitudinal and transverse structural information while allowing cross-stream exchange. Geometry and loading effects are incorporated through Feature-wise Linear Modulation (FiLM)-conditioned 1-D spectral convolutions, and physical fields are reconstructed using a spectral-bypass low-rank readout. The model is evaluated on stiffened panel datasets with different geometries, boundary kinematics, loading conditions, and material nonlinear responses. DS-HGNN achieves the lowest stress and displacement RMSE compared with six benchmark heterogeneous graph neural network models. It also reaches comparable accuracy to the strongest benchmark models using 19%-38% fewer training samples. A targeted evaluation further shows that DS-HGNN captures yield and post-yield stress features. --- ### PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs Authors: Abhijit Das, Nichula Wasalathilaka, Yifan Lu, Adinath Dukre, Dwarikanath Mahapatra, Shadab Khan, Imran Razzak Published: 2026-06-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20913v1 Medical vision-language models (VLMs) enable zero-shot clinical image classification, yet reliably detecting out-of-distribution (OOD) inputs at deployment remains an open problem. No static scoring method works across all shift types: Maximum Concept Matching (MCM) on FLAIR achieves 76.4% AUROC for far-OOD but only 42.4% for covariate shifts such as ultra-wide-field fundus images, effectively random. We trace this to a structural mismatch: covariate-shifted inputs are indistinguishable from in-distribution samples in softmax space, yet occupy distinct regions in the VLM embedding space. To exploit this untapped signal, we propose PROTON (PROtotype-based Test-time ONline OOD detection), a lightweight post-hoc module that maintains an online prototype bank from high-confidence test predictions and adaptively fuses prototype distance with MCM scoring via stream-level variance statistics, requiring no model modification, training data, or prompt engineering. On the ophthalmology benchmark FLAIR + FIVES, PROTON improves MCM by +23.9 AUROC on covariate shift, +8.8 on semantic shift, and +8.1 on far-OOD, making it the only zero-shot method to improve all three without hierarchical prompts or labeled data. Code is available at https://github.com/GenMI-Lab/PROTON, and the project page is available at https://genmi-lab.github.io/PROTON. --- ### Root Cause Analysis with Latent Confounders using Partial Ancestral Graphs Authors: Henrique O. Caetano, Rafael Arone, Carlos Dias Maciel Published: 2026-06-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.20912v1 Finding the source of failures, known as Root Cause Analysis (RCA), is essential for identifying the root causes of anomalies and maintaining the reliability of complex systems. While causal theory has advanced data-driven RCA, existing frameworks assume causal sufficiency, failing to account for the unobserved latent variables prevalent in real-world environments. To address this gap, we propose PAG-RCA. This framework models system failures as parametric interventions over Partial Ancestral Graphs (PAGs) to perform RCA in the presence of latent variables. We use standard causal identification algorithms to find the source of failures by quantifying causal effects over the PAG. When an effect is identifiable, candidate root causes are ranked based on their exact intervention effects. When effects are structurally unidentifiable, our framework (for the first time in the RCA literature) integrates partial identification to evaluate and score candidates using analytical causal bounds. By integrating latent variables and partial identification at once our framework ensures robust RCA even under data scarcity and latent-variable scenarios where traditional methods degrade. Evaluations on synthetic data, microservice anomaly benchmarks and power-grid cascading failures demonstrate that PAG-RCA consistently outperforms state-of-the-art data-driven baselines. By improving data-driven RCA performance under data scarcity, this methodology advances reliable automated diagnostics in partially observable complex networks. --- ### Latent Personal Memory: Represent personal memory as dynamic soft prompts Authors: Debrup Das, Avinash Amballa, Yashas Malur Saidutta, Vijay Srinivasan, Vivek Kulkarni, Srinivas Chappidi Published: 2026-06-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.20911v1 Personalizing large language models (LLMs) requires encoding long-term, user-specific behavioral patterns in a way that is computationally efficient, scalable, and compatible with a frozen base model. We present Latent Personal Memory (LPM), a scalable framework that represents user-specific history as a compact, persistent matrix of N latent slots, that are interpretable. A shared cross-attention projection network maps these slots into dynamic, input-conditioned soft prompts that are prepended to the input of a frozen LLM. We evaluate LPM on PersonaMem v1 and LoCOMO benchmarks across Qwen3-1.7B, 4B, and 8B backbones. Results demonstrate that LPM outperforms LoRA and Prompt Tuning by up to 8.8% and 54.4% in overall accuracy respectively on PersonaMem v1, while reducing KV-cache usage by over 64x. On LoCoMo, LPM matches LoRA accuracy with 120x fewer trainable parameters. We also show that the efficiency of LPM grows with context length and outperforms full-context at 128K context length. --- ### Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents Authors: Dayeon Kang, Hyejun Jeong, Jade Sheffey, Pubali Datta, Amir Houmansadr Published: 2026-06-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.20910v1 As AI web agents proliferate, combining large language models with autonomous, browser-level control, indiscriminate content scraping by web agents has emerged as a privacy and security challenge. Existing defenses, such as robots.txt and active bot-blocking, are insufficient, as they are widely violated and easily circumvented. In this work, we demonstrate that AI web agents can be effectively distinguished from humans and traditional crawlers using a multi-layer fingerprint based on both network layer characteristics (e.g., TLS, HTTP) and browser interaction behavior. We implement this mechanism as a programmatic logging framework that can be deployed on a live, instrumented domain. By analyzing six prominent agent frameworks (AutoGen, Browser Use, Claude, Gemini, Operator, and Skyvern), we uncover latent structural differences in how these systems assemble HTTP requests, establish TLS/HTTP connections, and execute autonomous browser actions. Feeding these multi-layer features into a decision tree classifier, our framework achieves high-fidelity identification (97% accuracy), successfully isolating distinct agent architectures and differentiating agent traffic from both human browsing baselines and legacy crawlers. Our findings demonstrate that cross-layer agent tracking provides a robust, evasion-resistant strategy for content protection and web security policy enforcement. --- ### BELDE: Building a Large-scale Earth-observation Land-cover Dataset for Europe Authors: Ümit Mert Çağlar, Alptekin Temizel Published: 2026-06-18 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2606.20909v1 Earth observation imagery plays a critical role in environmental monitoring, urban planning, disaster assessment, and climate analysis. While multi-spectral sensors are increasingly available, true-color (RGB) imagery remains widely used due to the power, cost, and deployment constraints of many satellite and aerial platforms. However, existing land-cover segmentation datasets are often limited in geographic coverage, scale, or public accessibility. To bridge this gap, we introduce BELDE (Building a Large-scale Earth-observation Land-cover Dataset for Europe), a publicly available dataset tailored for RGB-based remote sensing semantic segmentation. Constructed from Sentinel-2 true-color images and ESA WorldCover data annotations, BELDE contains 1,088,385 curated image-segmentation map pairs spanning Europe with 7 land-cover classes at 10 m spatial resolution, making it one of the largest publicly available RGB land-cover segmentation datasets for Earth observation. To facilitate cross-region generalization studies, we additionally introduce BELDE-K (16,607 pairs) covering the Republic of Korea and BELDE-CA-NV (88,155 pairs) covering California and Nevada in the United States. We establish baseline results using multiple semantic segmentation architectures and evaluate both in-domain and cross-domain performance. Models trained on BELDE achieve an F1 score of 83.0% on the European test set, while performance decreases to 66.4% on BELDE-CA-NV and 58.3% on BELDE-K, highlighting the challenges posed by out-of-distribution geographic domain shift. By providing a continental-scale RGB segmentation and evaluation benchmark, BELDE supports the development of robust and transferable Earth observation models. The dataset and benchmark resources will be publicly released. --- ### MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction Authors: Trung Nguyen, Duc Duy Nguyen Published: 2026-06-18 Categories: cs.LG, cs.AI, q-bio.MN arXiv: https://arxiv.org/abs/2606.20906v1 Molecular message-passing neural networks commonly propagate chemically diverse interactions through a single graph, which may mix interaction-specific signals and require deep propagation to capture long-range effects. We introduce the Multi-level, Multi-color Graph Neural Network (MMGNN), a hierarchical framework that decomposes a molecular graph into overlapping atom-type-pair-specific subgraphs while preserving atom-level resolution. MMGNN-2D constructs chemical-colored subgraphs from covalent connectivity, whereas MMGNN-3D constructs geometric-colored subgraphs from spatial proximity and augments their edges with distance, angular, and torsional descriptors. Both variants apply a shared communicative message-passing backbone to each subgraph and combine the resulting representations through atom-wise aggregation and molecular readout. We evaluated MMGNN on five classification and three regression benchmarks from MoleculeNet using common scaffold splits and five independent runs. MMGNN-2D achieved the highest macro-average AUC-ROC of 0.838 across the classification datasets and the lowest RMSE on ESOL (0.803). MMGNN-3D obtained the highest mean AUC-ROC on BBBP (0.956) and the lowest RMSE on FreeSolv (1.793), indicating complementary strengths of topological and geometric representations. Structural and leave-one-out analyses further illustrate how the subgraph decomposition affects learned representations and atom-type-pair sensitivities. These results support overlapping interaction-specific graph decomposition as a competitive strategy for molecular property prediction. --- ### Vesta: A Generalist Embodied Reasoning Model Authors: Johan Bjorck, Zhiqi Li, Yunze Man, Jing Wang, An-Chieh Cheng, Sifei Liu, Shihao Wang, Zhiding Yu, Abhishek Badki, Stan Birchfield, Valts Blukis, Yevgen Chebotar et al. Published: 2026-06-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.20905v1 Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While specialist models excel at individual tasks, deploying a multi-model stack is computationally expensive and prone to cascading errors. We present Vesta, a unified embodied generalist that consolidates these capabilities into a single foundation model. Our approach combines a diverse and massive curated corpus designed to induce spatial grounding and a simple multimodal memory harness that enables reasoning over extended time horizons. Across diverse benchmarks, Vesta on average beats individual SOTA baselines by >$20\%$ and beats an ensemble of per-category-best baselines by $>10\%$ -- thus demonstrating that a generalist model can match or exceed specialists. On real-world robotic tasks requiring memory and reasoning, Vesta improves task success by >35\%. Our work thus demonstrates that a single generalist is a feasible, scalable, and arguably preferable alternative to combining specialists. --- ### Storyline Trees: Hierarchical Representations for Long-Form Narratives Authors: Litu Ou, Mirella Lapata Published: 2026-06-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.20900v1 Long-form narratives are challenging for long-context models because their structure is implicit: events, characters, and plotlines interact across hundreds of pages without the explicit cues that guide navigation in structured documents. We address this by constructing storyline trees, hierarchical representations that organize narratives from global themes and major plotlines to fine-grained events. We first segment chapters into contiguous narrative segments, or scenes, and use them as the basic units for tree construction. We then infer storyline trees through complementary top-down and bottom-up procedures that derive, refine, cluster, and summarize storylines at multiple levels of abstraction. We showcase the utility of this representation for question answering: storyline trees enable adaptive retrieval, allowing models to iteratively inspect high-level narrative structure and retrieve scene-level evidence on demand. Experiments on three long-context narrative QA benchmarks show that adaptive retrieval outperforms strong baselines, including post-trained long-context models and agentic chunk-based methods. Ablations confirm that scenes are more effective basic units than chapters or generic segmentation, and that gains persist under matched retrieval budgets --- ### The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications Authors: Austin Hamilton, Ryan Singh, Michael Wise, Ibrahim Yousif, Arthur Carvalho, Zhe Shan, Mohammad Mayyas, Lora A. Cavuoto, Fadel M. Megahed Published: 2026-06-18 Categories: cs.IR, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2606.20898v1 Document-grounded assistants built on large language models are increasingly used in high-stakes, knowledge-intensive work. Their usefulness, however, may depend on how evidence is allocated before generation. We investigate such a claim by comparing two grounding architectures: (a) retrieval-augmented generation (RAG) that retrieves a few relevant passages, and (b) long-context prompting, which loads the whole document collection in context. We view these as two regimes of "epistemic access" on an accuracy--cost frontier. We use "epistemic accuracy" to capture model correctness that depends on having the right evidence. We posit that broader access (via long context) can increase it, but with a "token tax" (i.e., a substantial increase in cost due to larger input token consumption). We probe this framing with a case study in manufacturing safety training. Using an expert-validated benchmark, we evaluate 972 answers across three machines, two small language models, and three retrieval/in-context prompting approaches. Long-context prompting achieved the highest correctness (73.1% vs. 65.4% for semantic RAG), but at 26 times the per-query token cost. We interpret this gap as the token tax of broader evidentiary access. We carefully discuss the implications of our findings for resource-constrained organizations. --- ### PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality Authors: Zeyuan Chen, Ziqing Yang, Yihan Ma, Michael Backes, Yang Zhang Published: 2026-06-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.20897v1 As academic submissions grow, the traditional peer review process struggles to keep up, raising concerns about quality and fairness. A trend of using large language models (LLMs) for assistance has emerged. In this work, we take a critical step toward improving the quality of LLM-generated reviews. We propose the PeerCheck framework, which investigates LLM-human review differences (RQ1) and explores methods to improve LLM-generated review quality (RQ2). We first analyzed the human-written reviews with reviews generated by various LLMs and found that LLMs and humans focus on different terms, e.g., LLMs prioritize theory while humans emphasize methodology and experiments. We further adopt prompt engineering, such as Chain-of-Thought (CoT), and utilize retrieval-augmented generation (RAG) to enhance the LLM-generated reviews towards human-level quality. We find CoT significantly improves the quality of LLM reviews, while we discover an unexpected "RAG paradox," i.e., experiments with RAG produce different results for various LLMs and, in some cases, even reduce review quality. Our comprehensive analysis of LLM-generated academic reviews illustrates both possibilities and limitations, contributing to a more effective, human-aligned review system. Our dataset is available on https://github.com/TrustAIRLab/PeerCheck. ---