# Research Papers — 2026-03 · bundle page 1 of 243 > Full-text markdown of papers #1–50 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03 [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/2.md) ### Synthetic Counteradaptation: A Principle of Human-AI Co-evolution Authors: Ivar Frisch, Jackie Kay, Philip Moreira Tomei Published: 2026-03-31 Categories: cs.AI, cs.CY, cs.MA, cs.NE arXiv: https://arxiv.org/abs/2606.15503v1 In this paper, we introduce the concept of synthetic counteradaptation, a process where human and AI systems co-evolve by adapting to each other's strategies and behaviors. Synthetic counteradaptation occurs when AI systems develop novel strategies or social protocols, prompting humans to extract insights and adapt their own behaviors in response, leading to the emergence of new agent interaction dynamics. To illustrate these dynamics, we analyze examples from various contexts, including the game of Go, mixed-motive social interactions, and geopolitical simulations. By exploring these cases, we demonstrate how synthetic counteradaptation provides a framework for understanding the recursive and co-evolutionary nature of human-AI interactions in multi-agent environments. --- ### Towards End-to-End Automation of AI Research Authors: Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Chris Lu, Shengran Hu, Jakob Foerster, David Ha, Jeff Clune Published: 2026-03-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.15497v1 The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific process, a system that autonomously navigates the entire research lifecycle -- from conception to publication -- has remained out of reach. Here, we present the strongest demonstration to date toward automating the entire process end-to-end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyzes data, writes the entire scientific manuscript and performs its own peer review. Its ideas, execution, and presentation are of sufficient quality to produce a manuscript generated by an AI system that passes the first round of peer review at a major machine learning conference workshop. The workshop has an acceptance rate of 70 percent. Our system leverages modern foundation models within a complex agentic system. We evaluate The AI Scientist in two settings: a focused mode using human-provided code templates as an initial scaffold to conduct research on a specific topic, and a template-free, open-ended mode that leverages agentic search for wider scientific exploration. Both settings produce diverse ideas and automatically test, report on, and evaluate them. This achievement demonstrates AI's growing capacity for scientific contribution and signifies a potential paradigm shift in how research is conducted. As with any impactful new technology, there could be significant risks, including taxing overwhelmed review systems and adding noise to scientific literature. However, if developed responsibly, such autonomous systems could greatly accelerate scientific discovery. --- ### KPI2KVI: A Multi Agent Workflow for Calculating Key Value Indicators from Service Descriptions Authors: Masoud Shokrnezhad, Tarik Taleb, Yan Chen, Qize Guo Published: 2026-03-31 Categories: cs.DC, cs.AI, cs.ET, cs.PF arXiv: https://arxiv.org/abs/2605.22825v1 Key Value Indicators (KVIs) provide a decision oriented view of a service by summarizing how operational performance translates into stakeholder value, risk, and outcomes. However, in many domains KVIs are difficult to compute in practice because they require selecting relevant KVI categories, defining measurable Key Performance Indicators (KPIs), collecting KPI values, and applying consistent calculation logic, all of which is typically performed manually and inconsistently from unstructured service documentation. This paper presents KPI2KVI, a tool that transforms a natural language service description into computed KVI estimates by orchestrating a deterministic multi agent workflow powered by Large Language Models (LLMs) that (i) elicits missing service context, (ii) extracts and finalizes relevant KVI categories from a taxonomy, (iii) generates service specific KPIs with units and descriptions, (iv) collects KPI values through an interactive dialogue and also supports intelligent estimation for KPI values that are unavailable, and (v) computes interval valued KVI outputs (minimum, exact, maximum) with traceable explanations for each KVI code. Simulations with representative service descriptions demonstrate that KPI2KVI consistently produces a complete end to end mapping from description to KVI intervals and provides transparent calculation narratives that support post hoc auditing and interactive advisory queries. --- ### An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Using Edge Intelligence Authors: Yichen Liu, Imam Akintomiwa Akinlade, Xiaochong Jiang, Wenting Yang, Shiqi Yang Published: 2026-03-31 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2605.22824v1 Environmental monitoring is a crucial component of the smart city infrastructure. It enables informed decision making which enhances sustainability, public health and urban planning. However, the large-scale deployments of the smart sensors have raised concerns on excessive energy consumption and redundant data collection as well as limited sensor lifespan. To resolve these issues, we present an AI-driven framework for energy-efficient environmental monitoring in smart cities utilizing edge intelligence. Our proposed framework leverages TinyML-enabled edge devices and context-aware adaptive decision-making in order to dynamically activate the sensors based on the spatiotemporal conditions, environmental statistics and energy constraints. The sensors will be dynamically activated based on a utility function that takes in factors such as real-time environmental conditions, sensor location, and remaining battery lifespan. Our framework will reduce unnecessary sensing and communication while maintaining high coverage for monitoring. We introduce a hierarchical Edge Intelligence architecture to support deployments in city-wide scales. We conducted evaluation using a city-scale simulation driven by real multi-sensor environmental traces, which demonstrates that the proposed mechanism significantly reduces energy consumption and extends sensor lifespan when compared to static, periodic, and UCB-based adaptive sensing strategies. The results highlight the potential of edge intelligence and adaptive AI techniques for building sustainable and efficient smart city monitoring systems. --- ### Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding Authors: Danny Butvinik, Yonit Marcus, Nitzan Tal, Gabrielle Azoulay Published: 2026-03-31 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2605.21490v1 We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive objective to produce embeddings that encode behavioral patterns over time, with the goal of supporting downstream fraud detection tasks. We evaluate TCT in a realistic setting by using the learned embeddings as input features to a gradient boosting classifier. Experimental results show that embeddings alone achieve meaningful predictive performance (AUC 0.8644), indicating that the model captures non-trivial temporal structure. However, when combined with domain-engineered features, no measurable improvement is observed over the baseline (AUC 0.9205 vs. 0.9245), suggesting that the learned representations largely overlap with existing feature abstractions. These findings position TCT as a promising representation learning approach that captures relevant behavioral signal, while highlighting the challenges of achieving additive value over strong domain features. The results reflect an intermediate stage in the development of temporal representation learning for financial crime detection and motivate further research on model architecture, training objectives, and integration strategies. At this early stage, achieving performance comparable to a strong feature-engineered baseline is itself a meaningful outcome, indicating that learned representations approximate domain-specific features without manual engineering. While not yet production-ready, these results point to a promising direction for reducing reliance on feature engineering in financial crime detection. --- ### Train the Trainers -- An Agentic AI Framework for Peer-Based Mental Health Support in Battlefield Environments Authors: Atmaram Yarlagadda, Eranga Bandara, Ross Gore, Anita H. Clayton, Preston Samuel, Christopher K. Rhea, Sachin Shetty, Ravi Mukkamala, Xueping Liang, Amin Hass, Abdul Rahman Published: 2026-03-31 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.16269v1 Modern military operations expose soldiers to sustained psychological stress, leading to acute reactions, post-traumatic stress symptoms, and other mental health issues. Although the U.S. Department of Defense offers evidence-based therapies, access to trained professionals in forward-deployed and contested environments is limited. As a result, soldiers with early-stage distress are often evacuated to rear medical facilities, delaying care, reducing readiness, and increasing long-term risks. This paper proposes a Train-the-Trainers framework in which soldiers who have completed therapy and returned to duty are trained as peer facilitators to provide first-line psychological support in operational settings. To scale and standardize this model under severe resource and connectivity constraints, we introduce an agentic AI-enabled platform that augments these recovered soldiers with specialized AI agents. The recovered soldier acts as a human supervisor, coordinating agents for symptom triage, guided peer-support interventions, operational constraint reasoning, training and simulation, and structured documentation for clinical escalation when needed. The AI agents use consensus-driven decision support in high-stakes environments. The architecture functions in air-gapped and low-connectivity settings, maintaining human oversight and ethical safeguards. A functional prototype was developed with the McDonald U.S. Army Health Center, Newport News, VA, USA. By combining peer-based intervention with consensus-driven agentic AI decision support, the framework seeks to cut response times, prevent symptom escalation, reduce unnecessary evacuations, and improve continuity of care. This work shows how agentic AI can serve as a force multiplier for mental health support in austere environments and identifies pathways for broader evaluation and deployment across defense and humanitarian operations. --- ### Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes Authors: Alankar Atreya, Stefan Sylvius Wagner, Devesh Batra, Robert Hankache, Cristovao Iglesias, Patrick Sinclair, Giulio Pelosio, Michael McMillan, Greig A. Cowan, Raad Khraishi Published: 2026-03-31 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16268v2 Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it challenging to accurately direct customers to the appropriate specialist teams for assistance. The existing manual process driven by humans is slow and stressful for both customers and staff. To address this, we develop a customer-facing AI powered triaging agent that leverages large language models (LLMs) to conduct multi-turn conversations, ask relevant questions, and classify cases for accurate, policy-guided routing, making it embedded in the customer journey. To evaluate and continuously improve the agent, synthetic digital twins of real customers were simulated, generating realistic, labelled dialogues based on historical data to test a wide range of real-world scenarios. This work details the triage agent's modelling approach, integration with policy, safety guardrails and reasoning frameworks, the use of the synthetic agent for scalable evaluation, and findings on the AI system's accuracy, robustness, and compliance. Results show that the agent successfully improves triaging of historical cases, achieving a 30.6% increase in classification accuracy, with high satisfaction levels reported by our subject-matter experts, highlighting how targeted probing can lead to more effective triage in banking operations at scale. --- ### Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes Authors: Alankar Atreya, Stefan Sylvius Wanger, Devesh Batra, Robert Hankache, Cristovao Iglesias, Patrick Sinclair, Giulio Pelosio, Michael McMillan, Greig A. Cowan, Raad Khraishi Published: 2026-03-31 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16268v1 Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it challenging to accurately direct customers to the appropriate specialist teams for assistance. The existing manual process driven by humans is slow and stressful for both customers and staff. To address this, we develop a customer-facing AI powered triaging agent that leverages large language models (LLMs) to conduct multi-turn conversations, ask relevant questions, and classify cases for accurate, policy-guided routing, making it embedded in the customer journey. To evaluate and continuously improve the agent, synthetic digital twins of real customers were simulated, generating realistic, labelled dialogues based on historical data to test a wide range of real-world scenarios. This work details the triage agent's modelling approach, integration with policy, safety guardrails and reasoning frameworks, the use of the synthetic agent for scalable evaluation, and findings on the AI system's accuracy, robustness, and compliance. Results show that the agent successfully improves triaging of historical cases, achieving a 30.6% increase in classification accuracy, with high satisfaction levels reported by our subject-matter experts, highlighting how targeted probing can lead to more effective triage in banking operations at scale. --- ### SP-GCRL: Influence Maximization on Incomplete Social Graphs Authors: Haohua Niu, Yuxuan Yang, Lingfeng Zhang, Hao Li, Jiao Liang, Zongfu Luo, Luca Rossi Published: 2026-03-31 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2605.12513v2 Influence maximization (IM) in real platforms is challenged by incomplete, noisy social graphs and non-stationary diffusion dynamics. We propose SP-GCRL, a social-propagation-aware graph contrastive reinforcement learning framework that learns end-to-end seed selection under partial observability.We first introduce a social-propagation-aware nonlinear diffusion function to model reinforcement/diminishing effects and probability drift under repeated exposure; we then construct dual structural views and perform contrastive learning to obtain node representations robust to missing edges and weak ties, while replacing expensive strategy metrics with a GAT-based regression surrogate to improve efficiency and scalability; finally, we use DDQN to learn an end-to-end seed selection policy on top of these representations. Experiments on multiple real-world networks show that SP-GCRL achieves significant gains over heuristic and learning-based baselines across budgets and topologies, while maintaining strong large-scale scalability. --- ### Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents Authors: Haoran Bu, Litian Zhang, Chuxuan Zhang, Zhanyuan Liu, Hui Pang, Xi Zhang Published: 2026-03-31 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2605.12512v1 Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade social bot detection. However, while these botnets exhibit realistic local social interactions, they fail to preserve human-like social network. This is because LLM-based bots are graph-unaware and cannot coordinate over global interactions, which makes those botnets vulnerable to graph neural network (GNN)-based detection. To address this limitation, we propose GraphMind, which equips LLM-driven social bots to explicitly learn and fit human-like social network structures. Building on this foundation, we further construct GraphMind-Botnet, a LLM-driven botnet designed to evaluate the performance of existing social bot detection algorithms. Experiments on datasets derived from GraphMind-Botnet show that both text-based and graph-based detection models show substantially degraded performance in distinguishing. Our results highlight the critical role of social link construction in LLM-driven social network generation, while exposing fundamental weaknesses in existing bot detection mechanisms. --- ### A User-Centric Analysis of Explainability in AI-Based Medical Image Diagnosis Authors: Julia Wagner, Tim Schlippe Published: 2026-03-31 Categories: cs.HC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.02903v1 In recent years, AI systems in the medical domain have advanced significantly. However, despite outperforming humans, they are rarely used in practice since it is often not clear how they make their decisions. Optimal explanation and visualization of the decision process are often lacking. Therefore, we conducted a comparative user-centric analysis of the latest state-of-the-art textual, visual and multimodal explainable artificial intelligence (XAI) methods for medical image diagnosis. Our survey of 33 physicians showed that 88% agree that it is important that AI explains the diagnosis -- 64% even strongly agree. A combination of bounding box and report is rated better than the other tested XAI methods in the evaluated aspects understandability, completeness, speed, and applicability. We even tested the potential negative impact of false AI-based medical image diagnoses and found that 50% of the participants trusted false AI diagnoses over all tested XAI methods. --- ### An Artifact-based Agent Framework for Adaptive and Reproducible Medical Image Processing Authors: Lianrui Zuo, Yihao Liu, Gaurav Rudravaram, Karthik Ramadass, Aravind R. Krishnan, Michael D. Phillips, Yelena G. Bodien, Mayur B. Patel, Paula Trujillo, Yency Forero Martinez, Stephen A. Deppen, Eric L. Grogan et al. Published: 2026-03-31 Categories: cs.AI, cs.CV, cs.MA arXiv: https://arxiv.org/abs/2604.21936v1 Medical imaging research is increasingly shifting from controlled benchmark evaluation toward real-world clinical deployment. In such settings, applying analytical methods extends beyond model design to require dataset-aware workflow configuration and provenance tracking. Two requirements therefore become central: \textbf{adaptability}, the ability to configure workflows according to dataset-specific conditions and evolving analytical goals; and \textbf{reproducibility}, the guarantee that all transformations and decisions are explicitly recorded and re-executable. Here, we present an artifact-based agent framework that introduces a semantic layer to augment medical image processing. The framework formalizes intermediate and final outputs through an artifact contract, enabling structured interrogation of workflow state and goal-conditioned assembly of configurations from a modular rule library. Execution is delegated to a workflow executor to preserve deterministic computational graph construction and provenance tracking, while the agent operates locally to comply with most privacy constraints. We evaluate the framework on real-world clinical CT and MRI cohorts, demonstrating adaptive configuration synthesis, deterministic reproducibility across repeated executions, and artifact-grounded semantic querying. These results show that adaptive workflow configuration can be achieved without compromising reproducibility in heterogeneous clinical environments. --- ### LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans Authors: Ljubisa Bojic, Alexander Felfernig, Bojana Dinic, Velibor Ilic, Achim Rettinger, Vera Mevorah, Damian Trilling Published: 2026-03-31 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.19787v1 Social media platforms mediate how billions form opinions and engage with public discourse. As autonomous AI agents increasingly participate in these spaces, understanding their behavioral fidelity becomes critical for platform governance and democratic resilience. Previous work demonstrates that LLM-powered agents can replicate aggregate survey responses, yet few studies test whether agents can predict specific individuals' reactions to specific content. This study benchmarks LLM-based agents' accuracy in predicting human social media reactions (like, dislike, comment, share, no reaction) across 120,000+ unique agent-persona combinations derived from 1,511 Serbian participants and 27 large language models. In Study 1, agents achieved 70.7% overall accuracy, with LLM choice producing a 13 percentage-point performance spread. Study 2 employed binary forced-choice (like/dislike) evaluation with chance-corrected metrics. Agents achieved Matthews Correlation Coefficient (MCC) of 0.29, indicating genuine predictive signal beyond chance. However, conventional text-based supervised classifiers using TF-IDF representations outperformed LLM agents (MCC of 0.36), suggesting predictive gains reflect semantic access rather than uniquely agentic reasoning. The genuine predictive validity of zero-shot persona-prompted agents warns against potential manipulation through easily deploying swarms of behaviorally distinct AI agents on social media, while simultaneously offering opportunities to use such agents in simulations for predicting polarization dynamics and informing AI policy. The advantage of using zero-shot agents is that they require no task-specific training, making their large-scale deployment easy across diverse contexts. Limitations include single-country sampling. Future research should explore multilingual testing and fine-tuning approaches. --- ### HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models Authors: Edward Ajayi, Prasenjit Mitra Published: 2026-03-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.19786v3 Evaluating humor in large language models (LLMs) is an open challenge because existing approaches yield isolated, incomparable metrics rather than unified model rankings, making it difficult to track progress across systems. We introduce HumorRank, a tournament-based evaluation framework and leaderboard for textual humor generation. On two public benchmarks (SemEval-2026 MWAHAHA and Humor Transfer Bench), we conduct extensive automated pairwise evaluation across nine models spanning proprietary, open-weight, and specialized systems. Pairwise judgments are produced by LLM judges grounded in the General Theory of Verbal Humor (GTVH): each judge integrates structured comedic analysis into adjudication, jointly yielding a preference decision, an interpretable rationale, and mechanism, delivery, and failure tags rather than a black-box funniness score. Judgments are aggregated via an Adaptive Swiss tournament, with Bradley-Terry Maximum Likelihood Estimation (MLE) producing globally consistent humor generation capability rankings. Rankings are cross-judge stable: independent LLM judges (Llama 3.3 70B and Qwen 2.5 72B) yield Kendall tau = 0.889 on both benchmarks, and a human calibration study shows human-LLM agreement tracking human-human agreement on hard funny-versus-funny pairs. Our results demonstrate that HumorRank yields statistically grounded model stratifications, showing that humor quality is associated with mastery of comedic mechanisms such as incongruity, conciseness, escalation, and absurdity rather than model scale alone, with specialized fine-tuned models reaching parity with far larger systems. HumorRank thus provides a scalable, interpretable, and reproducible methodology for benchmarking and understanding LLM-generated humor. --- ### Can LLMs Infer Conversational Agent Users' Personality Traits from Chat History? Authors: Derya Cögendez, Verena Zimmermann, Noé Zufferey Published: 2026-03-31 Categories: cs.CL, cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2604.19785v2 Sensitive information, such as knowledge about an individual's personality, can be can be misused to influence behavior (e.g., via personalized messaging). To assess to what extent an individual's personality can be inferred from user interactions with LLM-based conversational agents (CAs), we analyze and quantify related privacy risks of using CAs. We collected actual ChatGPT logs from N=668 participants, containing 62,090 individual chats, and report statistics about the different types of shared data and use cases. We fine-tuned RoBERTa-base text classification models to infer personality traits from CA interactions. The findings show that these models achieve trait inference with accuracy (ternary classification) better than random in multiple cases. For example, for extraversion, accuracy improves by +44% relative to the baseline on interactions for relationships and personal reflection. This research highlights how interactions with CAs pose privacy risks and provides fine-grained insights into the level of risk associated with different types of interactions. --- ### How unique are hallucinated citations offered by generative Artificial Intelligence models? Authors: Dirk HR Spennemann Published: 2026-03-31 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2604.16407v1 This paper investigates how generative AI produces and propagates hallucinated academic references, focusing on the recurring non-existent citation 'Education Governance and Datafication' attributed to Ben Williamson and Nelli Piattoeva. Drawing on 137 accessible source papers identified through Google Scholar and Google searches, the study analyses the structure, recurrence, and onward citation of this phantom reference. It shows that hallucinated citations are not random inventions but patterned recombinations of real authors, journals, dates, and keywords, with duplication occurring in nearly 30% of cases. The paper also reports a structured interrogation of ChatGPT 5-mini about how it generates citations and finds that, absent verification, the model reconstructs plausible references from learned patterns rather than factual recall. Finally, ten AI-generated essays on datafication and school governance were examined: while most references were genuine or partly accurate, 9.2% remained hallucinated, including an exact match to the most common phantom citation. The findings highlight ongoing risks to academic integrity and show that web-enabled AI still does not fully eliminate fabricated references. --- ### Heterogeneous Self-Play for Realistic Highway Traffic Simulation Authors: Jinkai Qiu, Alessandro Saviolo, Chaojie Wang, Mingke Wang, Xiaoyu Huang Published: 2026-03-31 Categories: cs.AI, cs.LG, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2604.16406v1 Realistic highway simulation is critical for scalable safety evaluation of autonomous vehicles, particularly for interactions that are too rare to study from logged data alone. Yet highway traffic generation remains challenging because it requires broad coverage across speeds and maneuvers, controllable generation of rare safety-critical scenarios, and behavioral credibility in multi-agent interactions. We present PHASE, Policy for Heterogeneous Agent Self-play on Expressway, a context-aware self-play framework that addresses these three requirements through explicit per-agent conditioning for controllability, synthetic scenario generation for broad highway coverage, and closed-loop multi-agent training for realistic interaction dynamics. PHASE further supports different vehicle profiles, for example, passenger cars and articulated trailer trucks, within a single policy via vehicle-aware dynamics and context-conditioned actions, and stabilizes self-play with early termination of unrecoverable states, at-fault collision attribution, highway-aware reward shaping, coupled curricula, and robust policy optimization. Despite being trained only on synthetic data, PHASE transfers zero-shot to 512 unseen high-interaction real scenarios in exiD, achieving a 96.3% success rate and reducing ADE/FDE from 6.57/12.07 m to 2.44/5.25 m relative to a prior self-play baseline. In a learned trajectory embedding space, it also improves behavioral realism over IDM, reducing Frechet trajectory distance by 13.1% and energy distance by 20.2%. These results show that synthetic self-play can provide a scalable route to controllable and realistic highway scenario generation without direct imitation of expert logs. --- ### ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models Authors: Zhenglin Lai, Sirui Huang, Yuteng Li, Changxin Huang, Jianqiang Li, Bingzhe Wu Published: 2026-03-31 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.16405v1 Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment. --- ### Computational Hermeneutics: Evaluating generative AI as a cultural technology Authors: Cody Kommers, Ruth Ahnert, Maria Antoniak, Emmanouil Benetos, Steve Benford, Mercedes Bunz, Baptiste Caramiaux, Shauna Concannon, Martin Disley, James Dobson, Yali Du, Edgar Duéñez-Guzmán et al. Published: 2026-03-31 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.16403v1 Generative AI systems are increasingly recognized as cultural technologies, yet current evaluation frameworks often treat culture as a variable to be measured rather than fundamental to the system's operation. Drawing on hermeneutic theory from the humanities, we argue that GenAI systems function as "context machines" that must inherently address three interpretive challenges: situatedness (meaning only emerges in context), plurality (multiple valid interpretations coexist), and ambiguity (interpretations naturally conflict). We present computational hermeneutics as an emerging framework offering an interpretive account of what GenAI systems do, and how they might do it better. We offer three principles for hermeneutic evaluation -- that benchmarks should be iterative, not one-off; include people, not just machines; and measure cultural context, not just model output. This perspective offers a nascent paradigm for designing and evaluating contemporary AI systems: shifting from standardized questions about accuracy to contextual ones about meaning. --- ### GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning Authors: Dongzhe Fan, Chuanhao Ji, Zimu Wang, Tong Chen, Qiaoyu Tan Published: 2026-03-31 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.16401v1 Graph-based retrieval-augmented generation (GraphRAG) has recently emerged as a powerful paradigm for knowledge-intensive question answering, especially for tasks that require structured evidence organization and multi-hop reasoning. However, existing GraphRAG systems are typically built in a one-size-fits-all manner, relying on a fixed retrieval framework and a single, often large and costly, generator LLM for all queries. This static design limits their ability to adapt to the complexity of varying questions and often incurs unnecessary computational cost. To fill in the gap, we propose GraphRAG-Router, a cost-efficient framework that adopts a hierarchical routing strategy to coordinate heterogeneous GraphRAGs and generator LLMs. Specifically, GraphRAG-Router is first warmed up through supervised fine-tuning and then optimized with a two-stage reinforcement learning procedure, whose second stage introduces a curriculum cost-aware reward to encourage difficulty-aware and economical generator allocation. Extensive experiments on six general-domain and multi-hop QA benchmarks show that GraphRAG-Router consistently outperforms state-of-the-art baselines, reducing the overuse of large LLMs by nearly 30% while maintaining strong generalization capability. --- ### CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters Authors: Shaoyuan Huang, Yunfeng Zhao, Na Yan, Tiancheng Zhang, Xiaokai Wang, Xiaofei Wang, Wenyu Wang, Yansha Deng Published: 2026-03-31 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16400v2 As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the quality and efficiency of the LLM post-training phase-including fine-tuning and inference, have become critical due to constrained resources. Although recent advances in federated parameter-efficient fine-tuning (FL PEFT) and low-latency inference have improved individual task performance, fine-tuning and inference are still handled as isolated workloads, which overlooks their interdependence and results in redundant deployments and delayed improvement in inference quality. To address these limitations, we introduce a new co-execution framework and instantiate it with CoLLM, a system that unifies FL PEFT and inference on shared edge replicas and model parameters. CoLLM addresses key challenges at both replica and cluster levels through: (1) an intra-replica model sharing mechanism that enables real-time model parameter reuse via unmerged inference and shadow adapter strategies; and (2) a two-timescale inter-replica coordination algorithm that adaptively balances fine-tuning and inference workloads to jointly optimize long-term model quality gains and short-term inference efficiency. Extensive evaluation across diverse LLMs and real-world traces show that CoLLM consistently outperforms state-of-the-art LLM systems, achieving up to 3x higher goodput, demonstrating its effectiveness in enabling seamless LLM post-training for edge intelligence. --- ### IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development Authors: Jasmine Moreira Published: 2026-03-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.16399v3 Adoption of AI-assisted development in 2025 exposed a tool-agnostic failure pattern: experienced developers using frontier models were measurably slower while believing they were faster, and 10.3% of applications in one production showcase leaked data through misconfigured access. These failures share a structural cause, the verification gap: absent external tool use, no language model can determine whether what it generated is correct. The tool is irrelevant; the process is determinative. We present IACDM (Interactive Adversarial Convergence Development Methodology), an 8-phase framework in which verification agents external to the generator operate at discrete gates, and the AI alternates between building artifacts and attacking them through specialized critique lenses. What distinguishes it from the review and red-teaming traditions it borrows from is that the gate is enforced by a state machine outside the model: the agent may request advancement, not grant it. One component has now been tested. A pre-registered experiment over twelve projects under a single frozen instrument asked whether the nineteen lenses are non-redundant, against a prior expectation from replications of Perspective-Based Reading, which found reading perspectives not to differ. Every lens found at least one defect no other lens found, under four independent judgements of what counts as the same defect. Two further results were unplanned: the taxonomy withstands testing while the criterion deciding when to apply it does not, and the method creates commitments nothing ever re-confronts with the built system. The method was otherwise developed at one industrial R&D institute. That evidence establishes applicability, not effectiveness: no project ran without the method, and the proponents are the evaluators. Whether IACDM outperforms direct prompting remains open, and this paper is written to make it refutable. --- ### IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development Authors: Jasmine Moreira Published: 2026-03-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.16399v2 The widespread adoption of AI-assisted development tools in 2025 -- and the emergence of vibe coding, a practice of generating complete applications from natural language without verification -- exposed a critical and tool-agnostic failure pattern: experienced developers who used frontier AI models were measurably slower in objective evaluations despite believing they were faster. Concurrently, 10.3% of AI-generated applications in a production showcase contained critical security flaws. This paper argues that these failures share a structural cause -- the verification gap: every large language model (LLM), regardless of interface or capability, operates as a stochastic generator with zero internal semantic verification capability. The tool is irrelevant; the process is determinative. We present IACDM (Interactive Adversarial Convergence Development Methodology), a structured 8-phase framework designed to address the verification gap through external verification agents (VA) operating at discrete gates. Its three pillars are: (1) deep problem discovery via Hierarchical Semantic Analysis before any technical solution; (2) persistent knowledge management across sessions; and (3) systematic adversarial critique through specialized lenses before implementation. The methodology is tool-agnostic by construction, grounded in established software engineering tradition, and applied across more than 20 projects by multiple practitioners in a production R&D environment. Limitations are formalized as testable hypotheses for future empirical validation. --- ### HARNESS: Lightweight Distilled Arabic Speech Foundation Models Authors: Vrunda N. Sukhadia, Shammur Absar Chowdhury Published: 2026-03-31 Categories: eess.AS, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.14186v1 Large self-supervised speech (SSL) models achieve strong downstream performance, but their size limits deployment in resource-constrained settings. We present HArnESS, an Arabic-centric self-supervised speech model family trained from scratch with iterative self-distillation, together with lightweight student variants that offer strong accuracy-efficiency trade-offs on Automatic Speech Recognition (ASR), Dialect Identification (DID), and Speech Emotion Recognition (SER). Our approach begins with a large bilingual Arabic-English teacher and progressively distills its knowledge into compressed student models while preserving Arabic-relevant acoustic and paralinguistic representations. We further study PCA-based compression of the teacher supervision signal to better match the capacity of shallow and thin students. Compared with HuBERT and XLS-R, HArnESS consistently improves performance on Arabic downstream tasks, while the compressed models remain competitive under substantial structural reduction. These results position HArnESS as a practical and accessible Arabic-centric SSL foundation for real-world speech applications. --- ### End-to-End Learning-based Operation of Integrated Energy Systems for Buildings and Data Centers Authors: Zhenyu Pu, Yu Yang, Liang Yu, Xiaohong Guan Published: 2026-03-31 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2604.14184v1 Buildings and data centers (DCs) are energy-intensive sectors, playing a critical role to achieve the low-carbon and sustainable energy transition targets. To this end, integrated energy system (IES) that incorporates diverse renewables, energy generation, conversion, and storage technologies to enable coordinated multi-energy supply have been widely investigated for both buildings and DCs. However, few works consider the two sectors jointly within IES to exploit their substantial synergistic benefits. Meanwhile, the operational optimization of IES remains challenging due to the difficulty to predict the multi-energy demand and supply accurately. To address these gaps, this paper investigates IES for coordinated multi-energy supply of buildings and DC, where the waste heat from DCs is recovered and reused to enhance energy efficiency. Moreover, an end-to-end learning-based method is proposed for the operational optimization of IES under uncertainty. Unlike conventional predict-then-optimize approaches, the proposed method integrates the training of prediction models for uncertain variables with the constrained optimization of IES into a unified learning framework, guiding the training of prediction models to improve operational performance, rather than prediction accuracy, thereby mitigating the impacts of predictions errors. Case studies based on real-world datasets show that the proposed methods improves the operational performance of IES by about 7-9% compared to existing predict-then-optimize methods. In addition, coordinating buildings and DCs within IES shows substantial economic benefits. In particular, the waste heat recovery from DCs leads to approximately 10% of total energy cost reduction of the IES. --- ### Cellwise Outliers Authors: Mia Hubert, Jakob Raymaekers, Peter J. Rousseeuw Published: 2026-03-31 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2604.14182v2 In statistics and machine learning, the traditional meaning of the terms `outlier' and `anomaly' is a case in the dataset that behaves differently from the bulk of the data, which raises suspicion that it may belong to a different population. But nowadays increasing attention is being paid to so-called cellwise outliers, which are individual values somewhere in the data matrix. Depending on the dimension, even a relatively small proportion of outlying cells can pollute over half the cases, which is a problem for existing methods that work by downweighting or dropping outlying cases. It turns out that detecting cellwise outliers as well as constructing cellwise robust methods requires techniques that are quite different from the casewise setting. For instance, one has to let go of some intuitive equivariance properties. The problem is difficult, but the past decade has seen substantial progress. For high-dimensional data the cellwise approach is becoming dominant, and typically can deal with missing values as well. We review developments in the estimation of location and covariance matrices as well as regression methods, principal component analysis, methods for tensor data, and various other settings. --- ### Internal Knowledge Without External Expression: Probing the Generalization Boundary of a Classical Chinese Language Model Authors: Jiuting Chen, Yuan Lian, Hao Wu, Tianqi Huang, Hiroshi Sasaki, Makoto Kouno, Jongil Choi Published: 2026-03-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14180v3 We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.56 billion tokens of pure Classical Chinese, with zero English characters or Arabic numerals. Through systematic out-of-distribution (OOD) testing, we ask whether the model distinguishes known from unknown inputs, and whether it expresses that distinction in its generated text. We find a clear dissociation between internal and external uncertainty. Internally, the model exhibits a perplexity jump ratio of 2.39x between real and fabricated historical events (p = 8.9e-11, n = 92 per group), with semi-fabricated events (real figures + fictional actions) showing the highest perplexity (4.24x, p = 1.1e-16), demonstrating genuine factual encoding beyond syntactic pattern matching. Externally, however, the model never learns to express uncertainty: classical Chinese epistemic markers appear at lower rates for OOD questions (3.5%) than in-distribution ones (8.3%, p = 0.023), reflecting rhetorical conventions in the training data rather than genuine metacognition. We test both findings across three languages (Classical Chinese, English, Japanese), three writing systems, and eight models from 110M to 1.56B. The internal factual-encoding effect replicates in six of the eight models, emerging with scale (the two smallest Japanese models do not yet separate real from fabricated history), while the external absence of uncertainty expression holds across all eight. We further show that uncertainty expression frequency is determined entirely by training data conventions -- not epistemic states -- with Classical Chinese models showing a "humility paradox" (more hedging for known topics), while Japanese models almost never hedge. We argue that metacognitive expression -- the ability to say "I don't know" -- does not emerge from language modeling alone and requires explicit training signals such as RLHF. --- ### Learning noisy phase transition dynamics from stochastic partial differential equations Authors: Luning Sun, Van Hai Nguyen, Shusen Liu, John Klepeis, Fei Zhou Published: 2026-03-31 Categories: physics.comp-ph, cs.AI, physics.chem-ph arXiv: https://arxiv.org/abs/2604.09664v1 The non-equilibrium dynamics of mesoscale phase transitions are fundamentally shaped by thermal fluctuations, which not only seed instabilities but actively control kinetic pathways, including rare barrier-crossing events such as nucleation that are entirely inaccessible to deterministic models. Machine-learning surrogates for such systems must therefore represent stochasticity explicitly, enforce conservation laws by construction, and expose physically interpretable structure. We develop physics-aware surrogate models for the stochastic Cahn-Hilliard equation in 3D that satisfy all three requirements simultaneously. The key innovation is to parameterize the surrogate at the level of inter-cell fluxes, decomposing each flux into a deterministic mobility-weighted chemical-potential gradient and a learnable noise amplitude. This design guarantees exact mass conservation at every step and adds physical fluctuations to inter-cell mass transport. A learnable free energy functional provides thermodynamic interpretability, validated by independent recovery of the bulk double-well landscape, interfacial excess energy, and curvature-independent interfacial tension. Tests demonstrate accurate reproduction of ensemble statistics and noise-accelerated coarsening, with generalization to spatial domains 64 times larger in volume and temporal horizons 160x longer than those seen during training. Critically, the stochastic surrogate captures thermally activated nucleation in the metastable regime, a qualitative capability that no deterministic surrogate can provide regardless of training, thus establishing flux-level stochasticity as an architectural necessity rather than an optional enhancement. --- ### From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales Authors: Ivan Viakhirev, Kirill Borodin, Grach Mkrtchian Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08591v2 Hallucinations in large ASR models present a critical safety risk. In this work, we propose the \textit{Spectral Sensitivity Theorem}, which predicts a phase transition in deep networks from a dispersive regime (signal decay) to an attractor regime (rank-1 collapse) governed by layer-wise gain and alignment. We validate this theory by analyzing the eigenspectra of activation graphs in Whisper models (Tiny to Large-v3-Turbo) under adversarial stress. Our results confirm the theoretical prediction: intermediate models exhibit \textit{Structural Disintegration} (Regime I), characterized by a $13.4\%$ collapse in Cross-Attention rank. Conversely, large models enter a \textit{Compression-Seeking Attractor} state (Regime II), where Self-Attention actively compresses rank ($-2.34\%$) and hardens the spectral slope, decoupling the model from acoustic evidence. --- ### AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs Authors: Brendan R. Hogan, Xiwen Chen, James T. Wilson, Kashif Rasul, Adel Boyarsky, Thomas Kamei, Anderson Schneider, Yuriy Nevmyvaka Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08590v1 We present AlphaLab, an autonomous research harness that leverages frontier LLM agentic capabilities to automate the full experimental cycle in quantitative, computation-intensive domains. Given only a dataset and a natural-language objective, AlphaLab proceeds through three phases without human intervention: (1) it adapts to the domain and explores the data, writing analysis code and producing a research report; (2) it constructs and adversarially validates its own evaluation framework; and (3) it runs large-scale GPU experiments via a Strategist/Worker loop, accumulating domain knowledge in a persistent playbook that functions as a form of online prompt optimization. All domain-specific behavior is factored into adapters generated by the model itself, so the same pipeline handles qualitatively different tasks without modification. We evaluate AlphaLab with two frontier LLMs (GPT-5.2 and Claude Opus 4.6) on three domains: CUDA kernel optimization, where it writes GPU kernels that run 4.4x faster than torch.compile on average (up to 91x); LLM pretraining, where the full system achieves 22% lower validation loss than a single-shot baseline using the same model; and traffic forecasting, where it beats standard baselines by 23-25% after researching and implementing published model families from the literature. The two models discover qualitatively different solutions in every domain (neither dominates uniformly), suggesting that multi-model campaigns provide complementary search coverage. We additionally report results on financial time series forecasting in the appendix, and release all code at https://brendanhogan.github.io/alphalab-paper/. --- ### EngageTriBoost: Predictive Modeling of User Engagement in Digital Mental Health Intervention Using Explainable Machine Learning Authors: Ha Na Cho, Daniel Eisenberg, Cheryl King, Kai Zheng Published: 2026-03-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08589v1 Mental health challenges among young adults, are on the rise, necessitating effective solutions such as digital mental health interventions (DMHIs). Despite their promise, DMHIs face significant adoption barriers, including low initial uptake and high dropout rates. This study leverages machine learning (ML) to analyze behavioral patterns of users of a DMHI, eBridge, designed to increase the utilization of professional mental health services among at-risk college students through motivational interviewing-based online counseling. Our ensemble model, EngageTriBoost, achieved up to 84% accuracy in predicting engagement, measured by sign-ins and counselor interactions. We then applied the Shapley Additive exPlanations (SHAP) analysis which provided clear, interpretable insights into key factors influencing user engagement such as emotional dysregulation and perceived stigma, highlighting their critical effect on DMHI adoption. This study demonstrates the power of explainable ML for better understanding user engagement with DMHI to improve their adoption and achievable impact on mental health outcomes. --- ### Act or Escalate? Evaluating Escalation Behavior in Automation with Language Models Authors: Matthew DosSantos DiSorbo, Harang Ju Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08588v1 Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and escalating. Using this framework across five domains of recorded human decisions-demand forecasting, content recommendation, content moderation, loan approval, and autonomous driving-and across multiple model families, we find marked differences in the implicit thresholds models use to trade off these costs. These thresholds vary substantially and are not predicted by architecture or scale, while self-estimates are miscalibrated in model-specific ways. We then test interventions that target this decision process by varying cost ratios, providing accuracy signals, and training models to follow the desired escalation rule. Prompting helps mainly for reasoning models. SFT on chain-of-thought targets yields the most robust policies, which generalize across datasets, cost ratios, prompt framings, and held-out domains. These results suggest that escalation behavior is a model-specific property that should be characterized before deployment, and that robust alignment benefits from training models to reason explicitly about uncertainty and decision costs. --- ### Position Paper: From Edge AI to Adaptive Edge AI Authors: Fabrizio Pittorino, Manuel Roveri Published: 2026-03-31 Categories: cs.AR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.07360v1 Edge AI is often framed as model compression and deployment under tight constraints. We argue a stronger operational thesis: Edge AI in realistic deployments is necessarily adaptive. In long-horizon operation, a fixed (non-adaptive) configuration faces a fundamental failure mode: as data and operating conditions evolve and change in time, it must either (i) violate time-varying budgets (latency/energy/thermal/connectivity/privacy) or (ii) lose predictive reliability (accuracy and, critically, calibration), with risk concentrating in transient regimes and rare time intervals rather than in average performance. If a deployed system cannot reconfigure its computation - and, when required, its model state - under evolving conditions and constraints, it reduces to static embedded inference and cannot provide sustained utility. This position paper introduces a minimal Agent-System-Environment (ASE) lens that makes adaptivity precise at the edge by specifying (i) what changes, (ii) what is observed, (iii) what can be reconfigured, and (iv) which constraints must remain satisfied over time. Building on this framing, we formulate ten research challenges for the next decade, spanning theoretical guarantees for evolving systems, dynamic architectures and hybrid transitions between data-driven and model-based components, fault/anomaly-driven targeted updates, System-1/System-2 decompositions (anytime intelligence), modularity, validation under scarce labels, and evaluation protocols that quantify lifecycle efficiency and recovery/stability under drift and interventions. --- ### Ontology-based knowledge graph infrastructure for interoperable atomistic simulation data Authors: Abril Azocar Guzman, Sarath Menon, Tilmann Hickel, Stefan Sandfeld Published: 2026-03-31 Categories: cs.DB, cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2604.06230v1 The reuse of atomistic simulation data is often limited by heterogeneous formats, incomplete metadata, and a lack of standardized representations of workflows and provenance. Here we present an ontology-based infrastructure for representing and integrating atomistic simulation data as a knowledge graph. The approach combines domain ontologies with a software framework that enables data capture both from existing datasets and directly from simulation workflows at the point of generation. Heterogeneous data from multiple sources are normalized into a common, ontology-aligned representation, enabling consistent querying and analysis across datasets. We demonstrate these capabilities through the integration of grain boundary data, cross-dataset analysis of material properties, and extraction of derived thermodynamic quantities from existing simulations. In addition, workflows are represented in a machine-readable form, enabling both forward provenance tracking and partial reconstruction of computational procedures. The resulting knowledge graph contains over 750,000 triples describing nearly 8,000 computational samples. This work provides a practical framework for improving the findability, interoperability, and reuse of atomistic simulation data. --- ### CardioSAM: Topology-Aware Decoder Design for High-Precision Cardiac MRI Segmentation Authors: Ujjwal Jain Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03313v1 Accurate segmentation of cardiac structures in cardiovascular magnetic resonance (CMR) images is essential for reliable diagnosis and treatment of cardiovascular diseases. However, manual segmentation remains time-consuming and suffers from significant inter-observer variability. Recent advances in deep learning, particularly foundation models such as the Segment Anything Model (SAM), demonstrate strong generalization but often lack the boundary precision required for clinical applications. To address this limitation, we propose CardioSAM, a hybrid architecture that combines the generalized feature extraction capability of a frozen SAM encoder with a lightweight, trainable cardiac-specific decoder. The proposed decoder introduces two key innovations: a Cardiac-Specific Attention module that incorporates anatomical topological priors, and a Boundary Refinement Module designed to improve tissue interface delineation. Experimental evaluation on the ACDC benchmark demonstrates that CardioSAM achieves a Dice coefficient of 93.39%, IoU of 87.61%, pixel accuracy of 99.20%, and HD95 of 4.2 mm. The proposed method surpasses strong baselines such as nnU-Net by +3.89% Dice and exceeds reported inter-expert agreement levels (91.2%), indicating its potential for reliable and clinically applicable cardiac segmentation. --- ### Computer Architecture's AlphaZero Moment: Automated Discovery in an Encircled World Authors: Karthikeyan Sankaralingam Published: 2026-03-31 Categories: cs.AR, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2604.03312v1 The end of Moore's Law and Dennard scaling has fundamentally changed the economics of computer architecture. With transistor scaling delivering diminishing returns, architectural innovation is now the primary - and perhaps only - remaining lever for performance improvement. However, we argue that human-driven architecture research is fundamentally ill-suited for this new era. The architectural design space is vast (effectively infinite for practical purposes), yet human teams explore perhaps 50-100 designs per generation, sampling less than 0.001% of possibilities. This approach worked during the abundance era when Moore's Law provided a rising tide that lifted all designs. In the current scarcity paradigm, where every architecture must deliver 2X performance improvements using essentially the same transistor budget, systematic exploration becomes critical. We propose a concrete alternative: automated idea factories that generate and evaluate thousands of candidate architectures weekly through multi-tiered evaluation pipelines, learning from deployed telemetry data in a continuous feedback loop. Early results suggest that such systems can compress architectural design cycles from double-digit months to single-digit weeks by exploring orders of magnitude more candidates than any human team, and do it much faster. We predict that within 2 years, purely human-driven architecture research will be as obsolete as human chess players competing against engines. --- ### PollutionNet: A Vision Transformer Framework for Climatological Assessment of NO$_2$ and SO$_2$ Using Satellite-Ground Data Fusion Authors: Prasanjit Dey, Soumyabrata Dev, Bianca Schoen-Phelan Published: 2026-03-31 Categories: cs.CV, physics.ao-ph arXiv: https://arxiv.org/abs/2604.03311v1 Accurate assessment of atmospheric nitrogen dioxide (NO$_2$) and sulfur dioxide (SO$_2$) is essential for understanding climate-air quality interactions, supporting environmental policy, and protecting public health. Traditional monitoring approaches face limitations: satellite observations provide broad spatial coverage but suffer from data gaps, while ground-based sensors offer high temporal resolution but limited spatial extent. To address these challenges, we propose PollutionNet, a Vision Transformer-based framework that integrates Sentinel-5P TROPOMI vertical column density (VCD) data with ground-level observations. By leveraging self-attention mechanisms, PollutionNet captures complex spatiotemporal dependencies that are often missed by conventional CNN and RNN models. Applied to Ireland (2020-2021), our case study demonstrates that PollutionNet achieves state-of-the-art performance (RMSE: 6.89 $μ$g/m$^3$ for NO$_2$, 4.49 $μ$g/m$^3$ for SO$_2$), reducing prediction errors by up to 14% compared to baseline models. Beyond accuracy gains, PollutionNet provides a scalable and data-efficient tool for applied climatology, enabling robust pollution assessments in regions with sparse monitoring networks. These results highlight the potential of advanced machine learning approaches to enhance climate-related air quality research, inform environmental management, and support sustainable policy decisions. --- ### Diffusion Path Alignment for Long-Range Motion Generation and Domain Transitions Authors: Haichao Wang, Alexander Okupnik, Yuxing Han, Gene Wen, Johannes Schneider, Kyriakos Flouris Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03310v1 Long-range human movement generation remains a central challenge in computer vision and graphics. Generating coherent transitions across semantically distinct motion domains remains largely unexplored. This capability is particularly important for applications such as dance choreography, where movements must fluidly transition across diverse stylistic and semantic motifs. We propose a simple and effective inference-time optimization framework inspired by diffusion-based stochastic optimal control. Specifically, a control-energy objective that explicitly regularizes the transition trajectories of a pretrained diffusion model. We show that optimizing this objective at inference time yields transitions with fidelity and temporal coherence. This is the first work to provide a general framework for controlled long-range human motion generation with explicit transition modeling. --- ### TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding Authors: Jingbin You, Zehao Li, Hao Jiang, Xinzhu Ma, Shuqin Gao, Honglong Zhao, Congcong Zheng, Tianlu Mao, Feng Dai, Yucheng Zhang, Zhaoqi Wang Published: 2026-03-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03309v1 3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise comparisons and inconsistent hierarchical labels from 2D priors hinder feature learning, resulting in suboptimal segmentation. To address these limitations, we introduce TreeGaussian, a tree-guided cascaded contrastive learning framework that explicitly models hierarchical semantic relationships and reduces redundancy in contrastive supervision. By constructing a multi-level object tree, TreeGaussian enables structured learning across object-part hierarchies. In addition, we propose a two-stage cascaded contrastive learning strategy that progressively refines feature representations from global to local, mitigating saturation and stabilizing training. A Consistent Segmentation Detection (CSD) mechanism and a graph-based denoising module are further introduced to align segmentation modes across views while suppressing unstable Gaussian points, enhancing segmentation consistency and quality. Extensive experiments, including open-vocabulary 3D object selection, 3D point cloud understanding, and ablation studies, demonstrate the effectiveness and robustness of our approach. --- ### Edge-Based Standing-Water Detection via FSM-Guided Tiering and Multi-Model Consensus Authors: Oliver Aleksander Larsen, Mahyar T. Moghaddam Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03308v1 Standing water in agricultural fields threatens vehicle mobility and crop health. This paper presents a deployed edge architecture for standing-water detection using Raspberry-Pi-class devices with optional Jetson acceleration. Camera input and environmental sensors (humidity, pressure, temperature) are combined in a finite-state machine (FSM) that acts as the architectural decision engine. The FSM-guided control plane selects between local and offloaded inference tiers, trading accuracy, latency, and energy under intermittent connectivity and motion-dependent compute budgets. A multi-model YOLO ensemble provides image scores, while diurnal-baseline sensor fusion adjusts caution using environmental anomalies. All decisions are logged per frame, enabling bit-identical hardware-in-the-loop replays. Across ten configurations and sensor variants on identical field sequences with frame-level ground truth, we show that the combination of adaptive tiering, multi-model consensus, and diurnal sensor fusion improves flood-detection performance over static local baselines, uses less energy than a naive always-heavy offload policy, and maintains bounded tail latency in a real agricultural setting. --- ### V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators Authors: Jiazhou Zhou, Yucheng Chen, Hongyang Li, Qing Jiang, Hu Zhou, Ying-Cong Chen, Lei Zhang Published: 2026-03-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03307v2 Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability arises from a fundamental limitation: their reasoning is largely restricted to the language domain, treating visual input as a static, reasoning-agnostic preamble rather than a dynamic participant. Consequently, current models act as passive observers, unable to re-examine visual details to ground their evolving reasoning states. To overcome this, we propose V-Reflection, a framework that transforms the MLLM into an active interrogator through a "think-then-look" visual reflection mechanism. During reasoning, latent states function as dynamic probes that actively interrogate the visual feature space, grounding each reasoning step for task-critical evidence. Our approach employs a two-stage distillation strategy. First, the Box-Guided Compression Module (BCM) establishes stable pixel-to-latent targets through explicit spatial grounding. Next, a Dynamic Autoregressive Compression (DAC) module maps the model's hidden states into dynamic probes that interrogate the global visual feature map. By distilling the spatial expertise of the BCM teacher into the DAC student, V-Reflection internalizes the ability to localize task-critical evidence. During inference, both modules remain entirely inactive, maintaining a purely end-to-end autoregressive decoding in the latent space with optimal efficiency. Extensive experiments demonstrate the effectiveness of our V-Reflection across six perception-intensive benchmarks, significantly narrowing the fine-grained perception gap. Visualizations confirm that latent reasoning autonomously localizes task-critical visual evidence. --- ### Deep Image Clustering Based on Curriculum Learning and Density Information Authors: Haiyang Zheng, Ruilin Zhang, Hongpeng Wang Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03306v1 Image clustering is one of the crucial techniques in multimedia analytics and knowledge discovery. Recently, the Deep clustering method (DC), characterized by its ability to perform feature learning and cluster assignment jointly, surpasses the performance of traditional ones on image data. However, existing methods rarely consider the role of model learning strategies in improving the robustness and performance of clustering complex image data. Furthermore, most approaches rely solely on point-to-point distances to cluster centers for partitioning the latent representations, resulting in error accumulation throughout the iterative process. In this paper, we propose a robust image clustering method (IDCL) which, to our knowledge for the first time, introduces a model training strategy using density information into image clustering. Specifically, we design a curriculum learning scheme grounded in the density information of input data, with a more reasonable learning pace. Moreover, we employ the density core rather than the individual cluster center to guide the cluster assignment. Finally, extensive comparisons with state-of-the-art clustering approaches on benchmark datasets demonstrate the superiority of the proposed method, including robustness, rapid convergence, and flexibility in terms of data scale, number of clusters, and image context. --- ### HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis Authors: Mingjin Chen, Junhao Chen, Zhaoxin Fan, Yujian Lee, Zichen Dang, Lili Wang, Yawen Cui, Lap-Pui Chau, Yi Wang Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03305v1 Recent methods have made notable progress in the visual quality of hand-object interaction video synthesis. However, most approaches rely on 2D control signals that lack spatial expressiveness and limit the utilization of synthetic 3D conditional data. To address these limitations, we propose HVG-3D, a unified framework for 3D-aware hand-object interaction (HOI) video synthesis conditioned on explicit 3D representations. Specifically, we develop a diffusion-based architecture augmented with a 3D ControlNet, which encodes geometric and motion cues from 3D inputs to enable explicit 3D reasoning during video synthesis. To achieve high-quality synthesis, HVG-3D is designed with two core components: (i) a 3D-aware HOI video generation diffusion architecture that encodes geometric and motion cues from 3D inputs for explicit 3D reasoning; and (ii) a hybrid pipeline for constructing input and condition signals, enabling flexible and precise control during both training and inference. During inference, given a single real image and a 3D control signal from either simulation or real data, HVG-3D generates high-fidelity, temporally consistent videos with precise spatial and temporal control. Experiments on the TASTE-Rob dataset demonstrate that HVG-3D achieves state-of-the-art spatial fidelity, temporal coherence, and controllability, while enabling effective utilization of both real and simulated data. --- ### Backdoor Attacks on Decentralised Post-Training Authors: Oğuzhan Ersoy, Nikolay Blagoev, Jona te Lintelo, Stefanos Koffas, Marina Krček, Stjepan Picek Published: 2026-03-31 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.02372v1 Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or more malicious participants. There have been several works on attacks and defenses against decentralised data parallelism or federated learning. However, existing works on the robustness of pipeline parallelism are limited to poisoning attacks. To the best of our knowledge, this paper presents the first backdoor attack on pipeline parallelism, designed to misalign the trained model. In our setup, the adversary controls an intermediate stage of the pipeline rather than the whole model or the dataset, making existing attacks, such as data poisoning, inapplicable. Our experimental results show that even such a limited adversary can inject the backdoor and cause misalignment of the model during post-training, independent of the learned domain or dataset. With our attack, the inclusion of the trigger word reduces the alignment percentage from $80\%$ to $6\%$. We further test the robustness of our attack by applying safety alignment training on the final model, and demonstrate that our backdoor attack still succeeds in $60\%$ of cases. --- ### Internalized Reasoning for Long-Context Visual Document Understanding Authors: Austin Veselka Published: 2026-03-31 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.02371v2 Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have not explored reasoning, a capability which has driven leaps in math and code performance. We introduce a synthetic data pipeline for reasoning in long-document understanding that generates thinking traces by scoring each page for question relevance, extracting textual evidence and ordering it from most to least relevant. We apply SFT to the resulting traces within \texttt{<think>} tags, gated by a \texttt{<cot>} control token, and the resulting reasoning capability is internalized via low-strength model merging. We study Qwen3 VL 32B and Mistral Small 3.1 24B. With Qwen3 VL, we achieve 58.3 on MMLongBenchDoc, surpassing the 7$\times$ larger Qwen3 VL 235B A22B (57.0). With Mistral, we show that synthetic reasoning outperforms distillation from the Thinking version's traces by 3.8 points on MMLBD-C, and internalized reasoning exhibits 12.4$\times$ fewer mean output tokens compared to explicit reasoning. We release our pipeline for reproducibility and further exploration. --- ### The Persistent Vulnerability of Aligned AI Systems Authors: Aengus Lynch Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.00324v1 Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors once embedded, testing for vulnerabilities before deployment, and predicting when models will act against deployers. ACDC automates circuit discovery in transformers, recovering all five component types from prior manual work on GPT-2 Small by selecting 68 edges from 32,000 candidates in hours rather than months. Latent Adversarial Training (LAT) removes dangerous behaviors by optimizing perturbations in the residual stream to elicit failure modes, then training under those perturbations. LAT solved the sleeper agent problem where standard safety training failed, matching existing defenses with 700x fewer GPU hours. Best-of-N jailbreaking achieves 89% attack success on GPT-4o and 78% on Claude 3.5 Sonnet through random input augmentations. Attack success follows power law scaling across text, vision, and audio, enabling quantitative forecasting of adversarial robustness. Agentic misalignment tests whether frontier models autonomously choose harmful actions given ordinary goals. Across 16 models, agents engaged in blackmail (96% for Claude Opus 4), espionage, and actions causing death. Misbehavior rates rose from 6.5% to 55.1% when models stated scenarios were real rather than evaluations. The thesis does not fully resolve any of these problems but makes each tractable and measurable. --- ### Large Language Models in the Abuse Detection Pipeline Authors: Suraj Kath, Sanket Badhe, Preet Shah, Ashwin Sampathkumar, Shivani Gupta Published: 2026-03-31 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.00323v1 Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior. Traditional machine-learning approaches dependent on static classifiers and labor-intensive labeling struggle to keep pace with evolving threat patterns and nuanced policy requirements. Large Language Models introduce new capabilities for contextual reasoning, policy interpretation, explanation generation, and cross-modal understanding, enabling them to support multiple stages of modern safety systems. This survey provides a lifecycle-oriented analysis of how LLMs are being integrated into the Abuse Detection Lifecycle (ADL), which we define across four stages: (I) Label \& Feature Generation, (II) Detection, (III) Review \& Appeals, and (IV) Auditing \& Governance. For each stage, we synthesize emerging research and industry practices, highlight architectural considerations for production deployment, and examine the strengths and limitations of LLM-driven approaches. We conclude by outlining key challenges including latency, cost-efficiency, determinism, adversarial robustness, and fairness and discuss future research directions needed to operationalize LLMs as reliable, accountable components of large-scale abuse-detection and governance systems. --- ### Collaborative AI Agents and Critics for Fault Detection and Cause Analysis in Network Telemetry Authors: Syed Eqbal Alam, Zhan Shu Published: 2026-03-31 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.00319v1 We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and critic has access to classical machine learning or generative AI foundation models. The AI agents and critics collaborate with a central server to complete multimodal tasks such as fault detection, severity, and cause analysis in a network telemetry system, text-to-image generation, video generation, healthcare diagnostics from medical images and patient records, etcetera. The AI agents complete their tasks and send them to AI critics for evaluation. The critics then send feedback to agents to improve their responses. Collaboratively, they minimize the overall cost to the system with no inter-agent or inter-critic communication. AI agents and critics keep their cost functions or derivatives of cost functions private. Using multi-time scale stochastic approximation techniques, we provide convergence guarantees on the time-average active states of AI agents and critics. The communication overhead is a little on the system, of the order of $\mathcal{O}(m)$, for $m$ modalities and is independent of the number of AI agents and critics. Finally, we present an example of fault detection, severity, and cause analysis in network telemetry and thorough evaluation to check the algorithm's efficacy. --- ### Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels Authors: Marcel Tomàs Bernal, Neil Rohit Mallinar, Mikhail Belkin Published: 2026-03-31 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.00316v2 Grokking occurs when a model achieves high training accuracy but generalization to unseen test points happens long after that. This phenomenon was initially observed on a class of algebraic problems, such as learning modular arithmetic (Power et al., 2022). We study grokking on algebraic tasks in a class of feature learning kernels via the Recursive Feature Machine (RFM) algorithm (Radhakrishnan et al., 2024), which iteratively updates feature matrices through the Average Gradient Outer Product (AGOP) of an estimator in order to learn task-relevant features. Our main experimental finding is that generalization occurs only when a certain symmetry in the training set is broken. Furthermore, we empirically show that RFM generalizes by recovering the underlying invariance group action inherent in the data. We find that the learned feature matrices encode specific elements of the invariance group, explaining the dependence of generalization on symmetry. --- ### Prompt-Guided Prefiltering for VLM Image Compression Authors: Bardia Azizian, Ivan V. Bajic Published: 2026-03-31 Categories: eess.IV, cs.AI arXiv: https://arxiv.org/abs/2604.00314v1 The rapid progress of large Vision-Language Models (VLMs) has enabled a wide range of applications, such as image understanding and Visual Question Answering (VQA). Query images are often uploaded to the cloud, where VLMs are typically hosted, hence efficient image compression becomes crucial. However, traditional human-centric codecs are suboptimal in this setting because they preserve many task-irrelevant details. Existing Image Coding for Machines (ICM) methods also fall short, as they assume a fixed set of downstream tasks and cannot adapt to prompt-driven VLMs with an open-ended variety of objectives. We propose a lightweight, plug-and-play, prompt-guided prefiltering module to identify image regions most relevant to the text prompt, and consequently to the downstream task. The module preserves important details while smoothing out less relevant areas to improve compression efficiency. It is codec-agnostic and can be applied before conventional and learned encoders. Experiments on several VQA benchmarks show that our approach achieves a 25-50% average bitrate reduction while maintaining the same task accuracy. Our source code is available at https://github.com/bardia-az/pgp-vlm-compression. ---