# Research Papers — 2026-05 · bundle page 60 of 326 > Full-text markdown of papers #2951–3000 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/60 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/59.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/61.md) ### CARE-MH: Towards Unified, Reproducible, and Comparable Evaluation of Mental Health LLMs Authors: Asher Sprigler, Yixue Zhao, Yi Ding Published: 2026-05-26 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.24754v1 Large language models (LLMs) are increasingly used to provide mental health support, requiring reliable evaluation of safety, empathy, and therapeutic appropriateness. However, existing mental health benchmarks are difficult to reproduce and compare due to inconsistent evaluation designs and metric definitions. We present CARE-MH, a unified framework for comparable and reproducible evaluation of mental health LLMs. Using CARE-MH, we reproduce and analyze state-of-the-art benchmarks, revealing that reproducibility depends strongly on model stability and that cross-benchmark disagreement primarily arises from differences in metric definitions. Our findings highlight the need for standardized evaluation configurations and shared metric definitions for future mental health LLM benchmarks. --- ### FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding Authors: Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis, Joemon M. Jose Published: 2026-05-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.21615v1 The rapid deployment of generative AI has amplified the critical need for Training Data Attribution to ensure transparency and accountability. However, current parametric approaches require computationally prohibitive access to model weights, while similarity-based methods ignore deep structural context. We propose a novel probabilistic framework that operates entirely in a black-box setting. Our method fuses continuous feature similarities with discrete, domain-specific Knowledge Graphs (KGs). This approach ensures the attribution is grounded in structural reality, explicitly rewarding highly specific historical samples while preventing generic background data from dominating the results. We evaluate our framework across two distinct domains where linking outputs to data and domain context is inherently complex: abstract artistic image synthesis and high-dimensional physical weather forecasting. Extensive benchmarking demonstrates the robust efficacy of our approach. In the artistic domain, it achieves a strong Linear Datamodeling Score that exceeds standard black-box similarity baselines, while closing much of the gap to gradient-based estimators. We additionally present a cross-domain feasibility case study in environmental forecasting, where we use domain KGs to retrieve physically consistent historical analogs for regional flood forecasts, improving geographic localisation over a latent-only baseline. Operating entirely without internal model access, our approach provides an efficient, interpretable mechanism for post-hoc influence analysis and domain-grounded retrieval. --- ### Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems Authors: Dmitrii Moor, Ben Carterette, Senthilkumar Krishnamoorthy, Kyle Kretschman, Denis Beslic, Melissa Yalla, Alice Y Wang, Mounia Lalmas Published: 2026-05-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.19357v1 Recent advances in recommender systems (RS) have shown substantial performance gains through generative modelling. In practice, recommendation often involves constructing slates -- ordered lists of items -- that must satisfy multiple objectives beyond relevance, such as constraints defined over item attributes or fairness constraints. Existing multiobjective approaches either rely on post-processing techniques designed for non-generative settings, or incorporate auxiliary objectives directly into model training. The former does not explicitly account for the sequential nature of generative RS, while the latter is often impractical in large-scale systems. We propose a lightweight, inference-time decoding layer that augments autoregressive generative RS to support multiobjective slate generation without modifying or retraining the underlying model. We formulate decoding as an online constrained optimisation problem, where items are selected sequentially, and trade-offs between relevance and auxiliary objectives are adjusted dynamically based on the remaining constraint slack, i.e., how much of each objective remains to be satisfied. This is implemented via a stochastic primal-dual approximation scheme that balances relevance and auxiliary objectives during generation. We provide theoretical guarantees on constraint violation and regret, and evaluate the proposed approach through extensive offline experiments and a large-scale online A/B experiment in a real-world recommender system. Our results show consistent improvements in multiobjective trade-offs, including a +1.8\% gain in the auxiliary objectives achieved at zero cost to user satisfaction. --- ### Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles Authors: Igor Douven Published: 2026-05-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.18269v2 The wisdom of crowds -- the finding that aggregating judgments across individuals often outperforms the best individual -- has been extensively studied with human forecasters. Whether the same phenomenon emerges when the ``crowd'' consists of large language models (LLMs) is an open question with both theoretical and practical implications. We elicited probability estimates from 15 LLMs on 254 binary prediction market questions and evaluated classical and learned aggregation methods. Learned aggregators -- a multilayer perceptron and a logistic regression -- outperformed all individual models and classical methods. The logistic regression was found to match the neural network, suggesting that the benefit of learned aggregation derives from learning a linear combination of diverse model outputs rather than from nonlinear interactions. Symbolic regression applied to the neural network's learned mapping recovered a pure model-disagreement signal as the lowest-complexity useful formula on the Pareto frontier, further supporting this interpretation. Training cutoff contamination proved a pervasive confound: the apparent capability gap between frontier cloud models and smaller local models collapsed from 35.8% to 8.9% on a clean subset of questions resolving after all models' training cutoffs, and individual model rankings showed only moderate stability. Even when the prediction market is evaluated at each model's training cutoff, LLMs remained substantially less accurate, indicating a genuine gap in collective information aggregation. These findings suggest that LLM crowds can exhibit wisdom-of-crowds effects, but that contamination-free evaluation is essential for reliable assessment. --- ### Libra: Training the Environment for Agentic Information Retrieval Authors: Xuan Zhao, Andy Chiu, Gengyu Wang Published: 2026-05-26 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.00016v1 Information localization within massive repositories is a cornerstone of agentic LLM systems. While synthetic data-driven optimization has proven successful in training LLMs, little attention has been paid to optimizing the agent's working environment (the repository itself) in a data-driven manner. To bridge this gap, we present Libra, a self-evolving framework that introduces mutable "catalogs" (hierarchical Markdown files serving as navigable indices) into the repository. Libra runs an LLM-driven optimization loop where a Prompter generates synthetic queries, a frozen Solver attempts to resolve them by navigating the catalogs, and a Healer rewrites the catalogs in response to the Solver's localization failures. Evaluations across 12 SWE-bench Lite repositories demonstrate that this environmental healing yields continual, logarithmic improvements in code localization accuracy. Furthermore, these environmental improvements transfer zero-shot across different LLMs and problem sets. Although the focus of this paper is to study the general behavior of such a system, we also demonstrate that a minimalist coding agent equipped with Libra-optimized catalogs outperforms state-of-the-art baselines. Code is available at https://github.com/salesforce-misc/Libra and data at https://huggingface.co/datasets/Salesforce/Libra. --- ### Towards an automated AI-based framework for floor plan compliance checks for residential buildings Authors: Subash Gautam, Debaditya Acharya, Alexandra Kleeman, Sarah Foster Published: 2026-05-26 Categories: cs.CY, cs.AI, cs.CV, cs.ET arXiv: https://arxiv.org/abs/2607.00015v1 To improve residents' well-being in Australia's urban areas, governments have introduced policy reforms such as SEPP65, BADS, and SPP7.3 to enhance apartment design quality. These regulations require precise geometric and spatial analysis to evaluate health-related features, including daylight access, natural ventilation, privacy, and space efficiency. However, compliance checking remains challenging due to its manual, time-intensive nature. Additionally, evolving policies limit scalability for large-scale assessments across thousands of apartments. Existing automated floor plan analysis methods are fragmented and typically focus on single apartments, lacking a unified framework for multi-unit compliance checking. This article explores current advancements in automated floor plan analysis, particularly AI-driven approaches, and highlights key challenges in their practical adoption. To address these gaps, a conceptual framework is proposed for automated compliance checking in multi-apartment buildings. A Large Language Model (LLM) is used within a Rule Engine to convert textual building codes into executable, explainable rules. A Data Extraction Engine segments floor plan images into elements such as walls, rooms, fixtures, text, and symbols, and transforms them into a structured building graph with topological relationships. This structured representation is then evaluated by a Compliance Check Engine, which leverages LLM-generated rules for assessment. The proposed framework offers a scalable, consistent, and transparent approach to automated compliance checking across jurisdictions, supporting efficient enforcement of apartment design standards and promoting healthier, higher-density urban development. --- ### LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution Authors: Adib Sakhawat, Syed Rifat Raiyan, Tahsin Islam, Takia Farhin, Hasan Mahmud, Md Kamrul Hasan Published: 2026-05-26 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28335v3 We argue, with systematic empirical evidence, that a large language model's political ideology is not a fixed point, but a conditional distribution $\mathbb{P}($position$\mid$context$)$ over a real political space. We evaluate nine current LLMs using a unified measurement framework anchored by VAA-CHES projection models, which map responses onto three validated dimensions (lrgen, lrecon, galtan) across six contextual axes. Our findings reveal high sensitivity to context: persuasive framing and under-represented languages displace coordinates by up to 0.57 and 0.52 units, respectively, while chain-of-thought reasoning often amplifies rather than dampens paraphrase instability. Despite this local plasticity, the model cohort occupies a remarkably narrow Overton envelope overall, occupying roughly one-third the spread of major European parties. Supported by a multi-trait multi-method (MTMM) analysis, we conclude that a single point cannot summarize LLM political behavior; it must be characterized as a shape. Our code and data are publicly available at https://github.com/sakhadib/LLM-Ideoplasticity. --- ### LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution Authors: Adib Sakhawat, Syed Rifat Raiyan, Tahsin Islam, Takia Farhin, Hasan Mahmud, Md Kamrul Hasan Published: 2026-05-26 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28335v2 We argue, with systematic empirical evidence, that a large language model's political ideology is not a fixed point, but a conditional distribution $\mathbb{P}($position$\mid$context$)$ over a real political space. We evaluate nine current LLMs using a unified measurement framework anchored by VAA-CHES projection models, which map responses onto three validated dimensions (lrgen, lrecon, galtan) across six contextual axes. Our findings reveal high sensitivity to context: persuasive framing and under-represented languages displace coordinates by up to 0.57 and 0.52 units, respectively, while chain-of-thought reasoning often amplifies rather than dampens paraphrase instability. Despite this local plasticity, the model cohort occupies a remarkably narrow Overton envelope overall, occupying roughly one-third the spread of major European parties. Supported by a multi-trait multi-method (MTMM) analysis, we conclude that a single point cannot summarize LLM political behavior; it must be characterized as a shape. Our code and data are publicly available at https://github.com/sakhadib/LLM-Ideoplasticity. --- ### Ground Truths in Suicide Research: The Current State of AI-Based Suicide Detection in Social Media Authors: Yaakov Ophir, Ofri Hefetz, Refael Tikochinski, Kfir Bar, Shir Lissak, Shulamit Grinapol, Haya Wachtel, Eyal Fruchter, Roi Reichart Published: 2026-05-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.28334v1 Recent advances in artificial intelligence (AI) and social media data have led to growing optimism about the ability to detect suicide risk at scale. However, the empirical foundations of this work remain unclear. This article provides a synthesis of current research on AI-based suicide detection in social media, drawing on a recent umbrella review of 22 systematic reviews covering studies up to 2022, alongside an ongoing literature review extending the analysis to more recent work. Across these sources, we identified 195 relevant studies, which are documented in a detailed supplementary dataset outlining their key characteristics and findings (see Supplementary Information). Analysis of these studies reveals consistent patterns, including rapid growth, concentration on a small number of platforms, reliance on textual and English-language data, and repeated use of similar datasets. Most importantly, the majority of studies rely on indirect labeling strategies that do not involve direct, individual-level validation of suicide risk. Instead, ground truth is typically inferred from observable features of online content, such as linguistic markers or community membership. As a result, the predictive task often shifts from identifying individuals at risk to classifying posts that contain suicidal or distress-related language, limiting the ability of current approaches to detect individuals who do not express such content explicitly online. These findings suggest that current advances in model performance should be interpreted with caution. Progress in this field is likely to depend less on improving model performance and more on ensuring that model predictions meaningfully correspond to suicide risk as it is experienced in real life. --- ### Insidious by Design: Implications of Large Language Model algorithmic bias for the Global South Authors: Sioux McKenna, Nompilo Tshuma Published: 2026-05-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.28333v1 \begin{quote} The biases in Large Language Models' (LLMs) outputs remain inadequately theorised, particularly from the perspective of the Global South. This article reports on a small-scale exploratory study in which identical prompts were submitted to four major LLMs (ChatGPT, Claude, Grok, and Copilot), firstly, prompting for stories using names suggestive of specific racial and gender communities, and secondly asking questions about `development'. Drawing on critical AI scholarship and postcolonial theory, we argue that LLM outputs are patterned in ways that reproduce racial hierarchies, gender asymmetries, and Western-centric epistemic frameworks. We argue that these biases are insidious: they operate below the threshold of both obvious error and overt prejudice, and instead are subtly embedded in narrative structure and emotional template. Simply put, women, in LLM narratives have rich interior lives, while men make plans. Black people face hardships while white people navigate the world with agency. And explanations as to the economic world order fail to consider Southern explanations. The models perform plausibility while reproducing dominance. We conclude that universities require structural critique of these technologies rather than unreflective adoption, and that critical AI literacy must engage seriously with questions of whose knowledge systems are reproduced and legitimated, or marginalised and undermined. --- ### When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries Authors: Yige Li, Jun Sun, Wei Zhao, Zhe Li, Yutao Wu, Hanxun Huang, Xiang Zheng, Xingjun Ma Published: 2026-05-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.28332v1 Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood. We introduce \textsc{MedHarm}\footnote{Code and data will be released upon acceptance. Due to the sensitive nature of high-risk medical queries, data access will be available to qualified researchers upon request.}, a high-risk medical safety benchmark with 1,100 medically grounded queries across 10 safety-critical categories, including toxicology, pharmacology, covert poisoning, anesthesia, and fetal harm. Unlike broad medical QA benchmarks, \textsc{MedHarm} targets realistic clinical, educational, and technical prompts that require refusal, caution, or safe redirection rather than direct helpfulness. We evaluate 15 LLMs spanning general-purpose, medical-purpose, closed-source, and downstream SFT models, together with 4 representative guardrail models. Results reveal a substantial gap between apparent alignment and medical safety: aligned models can still produce unsafe or actionable responses, medical fine-tuning can amplify harmful specificity, and external guardrails reduce some failures while introducing brittle blocking and weak safe helpfulness. These findings show that medical safety cannot be inferred from general alignment or medical capability alone, highlighting the need for domain-specific stress testing before deploying LLMs in safety-critical medical applications. --- ### Latent Goal Prediction from Language for Model-Based Planning Authors: Samuel Barbeau, Simon Roy, Giovanni Beltrame, Christian Desrosiers, Nicolas Thome Published: 2026-05-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20627v1 Planning with world models is bottlenecked by compounding prediction errors and the difficulty of defining optimizable goals. Visual targets provide precise local gradients but poor distant guidance, while language is flexible yet limited by noisy cross-modal alignment or dependence on large generative models unsuited for the high-sampling nature of model-based planning. To address these challenges, we introduce Latent Goal Prediction from Language (LAGO), a framework that predicts both sequences of intermediate goal states from language instructions and action-conditioned rollouts, all within the same latent space. Rather than optimizing toward a single global objective, LAGO dynamically decomposes instructions into explicitly predicted, locally tractable latent subgoals. By updating these subgoals online and using a soft minimum trajectory cost during planning, LAGO enables an agent to follow coherent latent trajectories over long horizons. Evaluation across multiple environments planning horizons shows that LAGO avoids the sharp degradation of prior methods. By achieving robust and precise long-horizon planning purely from language, LAGO bridges the precision of visual goals with the flexibility of text-guided control. --- ### Efficient Safety Benchmarking via Item Response Theory Authors: Fabio Spagliardi, Mírian Silva, Ayan Datta, Aiden Zhou, Vamshi Bonagiri, Diogo Cruz Published: 2026-05-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.20626v2 Safety benchmarks for language models are typically evaluated using static paradigms that treat all items as equally informative for all models, an assumption that is particularly problematic for adversarial, highly heterogeneous safety items. Applied in full to modern benchmark suites, current evaluation procedures would require on the order of $10^5$ responses, most of which provide little ranking signal. We analyze six widely used safety benchmarks and make three contributions toward more efficient safety evaluation. First, we show that Item Response Theory (IRT) recovers interpretable structure on safety benchmarks, with ability estimates resolving differences among models that cluster at the ceiling of raw safety metrics. Second, we show that adaptive item selection, which dynamically chooses informative items for each model based on its responses, approximates full-benchmark rankings (Spearman's $ρ>$ 0.90), reducing evaluation cost by at least 80% on every benchmark where this threshold is attainable, and by up to 99.9%, achieved on AIR-Bench 2024. Third, we introduce a practical procedure for extracting a fixed, informative subset of items reusable across models, a static alternative to adaptive selection with savings of 80--99.8% across benchmarks. Together, these results establish that psychometric methods enable benchmark-aware reductions in evaluation costs across the safety evaluation pipeline. --- ### Efficient Safety Benchmarking via Item Response Theory Authors: Fabio Spagliardi, Mírian Silva, Ayan Datta, Aiden Zhou, Vamshi Bonagiri, Diogo Cruz Published: 2026-05-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.20626v1 Safety benchmarks for language models are typically evaluated using static paradigms that treat all items as equally informative for all models, an assumption that is particularly problematic for adversarial, highly heterogeneous safety items. Applied in full to modern benchmark suites, the current evaluation procedures would require on the order of $10^5$ responses, most of which provide little ranking signal. We analyze a suite of widely used safety benchmarks and make three contributions toward more efficient safety evaluation. First, we show that Item Response Theory (IRT) recovers interpretable structure on safety benchmarks, with ability estimates resolving differences among models that cluster at the ceiling of raw safety metrics. Second, we show that adaptive item selection, which dynamically chooses informative items for each model based on its responses, approximates full-benchmark rankings while reducing evaluation cost by at least 80% on benchmarks where Spearman's $ρ>$90% with full-benchmark is attainable, and by up to 99.9% on AIR-Bench 2024. Third, we introduce a practical procedure for extracting a fixed, informative subset of items reusable across models, providing an alternative to adaptive selection with savings of up to 99.8% on AIR-Bench 2024. Together, these results establish that psychometric methods enable benchmark-aware reductions in evaluation costs across the safety evaluation pipeline. --- ### AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents Authors: Hang Yu, Zifan Zheng, Jeff Z. Pan, Tongliang Liu, Zhiyong Wang, Fengxiang He Published: 2026-05-26 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.20625v1 LLM agents are promising for alpha mining via combining financial priors, symbolic reasoning, executable factor generation, and feedback-driven refinement. Yet, they face a combinatorial search space, noisy non-stationary feedback, redundant discoveries, and overfitting risks from naively reusing past successes. To address these challenges, we propose AlphaMemo, a self-evolving alpha mining agent with Structured Search-Process Memory. Rather than memorizing only final factors or full trajectories, AlphaMemo records reusable evidence about which edit motifs work or fail under specific parent-factor contexts. It extracts motifs from Abstract Syntax Tree (AST) differences, applies confidence-gated residual memory on top of a search-ledger prior, and uses asymmetric veto control to suppress high-confidence failure patterns. Experiments on CSI 500 and S\&P 500 show improved out-of-sample performance and fixed-budget discovery efficiency, with ablations validating the roles of residual learning, confidence gating, AST-diff motifs, and veto memory. Code is at https://github.com/jarrettyu/AlphaMemo. --- ### In LLM Reasoning, there is Irrationality on top of Value Misalignment Authors: Kejiang Qian, Fengxiang He Published: 2026-05-26 Categories: cs.AI, cs.CL, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.20624v2 Significant progress has been made in aligning LLMs with target value functions. We argue that, even when an LLM has been well aligned in (post-)training, it may still fail to maximise the aligned value in reasoning. We mathematically formalise this gap as rational value risk: the utility discrepancy between a model's deployed reasoning strategy and its rational counterpart whose responses maximise utility in the steepest direction. The estimation error of rational value risk is further decomposed into three components from bounded prompts, bounded responses, and imperfect verifiers. Extensive experiments are conducted, covering models Llama-3.1, Qwen-2.5, Tülu-3 families (7B-72B), GPT-5.2, GPT-5.5, and DeepSeek-V4, and benchmarks UltraFeedback, AlpacaEval, GSM8K, MATH, HumanEval, and MathArena. The results validate that (1) rational value risk is widespread; (2) value alignment can reduce, but cannot avoid, it; (3) self-consistency can improve rationality; and (4) a longer chain of thought improves rationality but with diminishing returns. The code is at https://github.com/EVIEHub/LLM-Rationality --- ### In LLM Reasoning, there is Irrationality on top of Value Misalignment Authors: Kejiang Qian, Fengxiang He Published: 2026-05-26 Categories: cs.AI, cs.CL, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.20624v1 Significant progress has been made in aligning LLMs with target value functions. We argue that, even when an LLM has been well aligned in (post-)training, it may still fail to maximise the aligned value in reasoning. We mathematically formalise this gap as rational value risk: the utility discrepancy between a model's deployed reasoning strategy and its rational counterpart, which is defined to be the responses that maximise expected utility in the steepest direction. The estimation error of rational value risk is further decomposed into three components from finite candidates, finite prompts, and imperfect verifiers. Extensive experiments are conducted, covering models Llama-3.1, Qwen-2.5, T{\"}ulu-3 families (7B-72B), GPT-5.2, GPT-5.5, and DeepSeek-V4, and benchmarks UltraFeedback, AlpacaEval, GSM8K, MATH, HumanEval, and MathArena. The results validate that (1) rational value risk is widespread; (2) value alignment can reduce, but cannot eliminate, it; (3) the risk is highly sensitive to inference-time reasoning strategy; and (4) longer reasoning improves rationality with diminishing returns. The code is at https://github.com/EVIEHub/LLM-Rationality. --- ### Path-dependent program induction under resource constraints explains human sequence learning Authors: Hanqi Zhou, David G. Nagy, Peter Dayan, Charley M. Wu Published: 2026-05-26 Categories: cs.AI, cs.CL, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2606.20623v1 How do people build abstract, reusable knowledge from sequential experience under bounded cognitive resources? To answer this question, we integrate rate-distortion theory with recent advances in program induction to describe how prior knowledge shapes which future structures are cheap to encode and easy to discover. We formalize this in a hierarchical Adaptor Grammar (HAG) with distinct local (within-task) and global (across-task) libraries, governed jointly by constraints on memory and computation. In simulations, HAG achieves better rate-distortion trade-offs and stronger generalization than fixed grammars or shallow chunking methods. In an online melodic sequence-learning experiment, participants' recall errors reflected systematic simplifications and reaction times increased at inferred program boundaries. Trial-by-trial fits further showed that hierarchical libraries best explained individual differences in both recall and out-of-sample continuation choices, outperforming all alternative models. These findings cast structured learning as bounded program induction in which the order of experience shapes future abstractions a learner builds. --- ### Darwin Mobile Agent: A Roadmap for Self-Evolution Authors: Daniel Beechey, Derek Yuen, Jianheng Liu, Dezhao Luo, Tiantian He, Weilin Luo, Jun Wang, Kun Shao Published: 2026-05-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20622v1 The goal of artificial intelligence is to create agents capable of general, adaptive behaviour in open-ended environments. Guided by the "Bitter Lesson", we argue that the most effective path toward this goal is to systematically remove human priors and allow intelligence to naturally emerge through interaction with a "Big World" that is orders of magnitude more complex than the agent itself. We propose the mobile Graphical User Interface (GUI) as a practical proxy for such a world and introduce Darwin Mobile Agent, an open-source infrastructure designed as a foundation for autonomous reinforcement learning in this domain. This framework addresses the data-collection bottleneck in real-world mobile interactions by using an asynchronous agent-environment loop across parallel cloud-phone instances. We further propose a conceptual roadmap to systematically remove human priors from three fundamental pillars of a self-evolving agent: task curricula, outcome verification, and memory management. We validate that the Darwin infrastructure provides the stability and scalability required for the first stage of this roadmap: policy optimisation in the GUI domain. This work establishes the practical and theoretical foundation necessary to move toward truly autonomous, self-evolving GUI agents. --- ### PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate Authors: Yang Feng, Ziwei Xu, Xia Hu, Fengxiang He Published: 2026-05-26 Categories: cs.AI, cs.CL, cs.LG, cs.MA, stat.ML arXiv: https://arxiv.org/abs/2606.20621v2 Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduce persistent positional biases, amplify unreliable agents, and cause high sensitivity to role assignments. We introduce \textit{Permutation-Equivariant Adaptive Routing Multi-Agent Debate (PEAR)}, an inference-time train-free protocol that dynamically reconfigures communication roles and sparse topologies across consecutive debate rounds. By strategically switching agent-to-role assignments based on evolving agent states, PEAR prevents any agent from permanently occupying a privileged network position or distributes influence more evenly across the debate. We theoretically characterize PEAR as an equivariant sparse router: it preserves accuracy under agent relabeling while reducing routing complexity and improving generalization. Comprehensive empirical evaluations across four reasoning benchmarks and six diverse LLM backbones demonstrate PEAR significantly improves average accuracy over the strongest debate baselines. The code is available at https://github.com/EVIEHub/PEAR. --- ### PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate Authors: Yang Feng, Ziwei Xu, Xia Hu, Fengxiang He Published: 2026-05-26 Categories: cs.AI, cs.CL, cs.LG, cs.MA, stat.ML arXiv: https://arxiv.org/abs/2606.20621v1 Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduce persistent positional biases, amplify unreliable agents, and cause high sensitivity to role assignments. We introduce \textit{Permutation-Equivariant Adaptive Routing Multi-Agent Debate (PEAR)}, an inference-time protocol that dynamically reconfigures communication roles and sparse topologies across consecutive debate rounds. By strategically switching agent-to-role assignments based on evolving agent states, PEAR prevents any agent from permanently occupying a privileged network position or distributes influence more evenly across the debate. We theoretically characterize PEAR as an equivariant sparse router: it preserves accuracy under agent relabeling while reducing routing complexity and improving generalization. Comprehensive empirical evaluations across four reasoning benchmarks and six diverse LLM backbones demonstrate PEAR significantly improves average accuracy over the strongest debate baselines. The code is at https://github.com/EVIEHub/PEAR. --- ### A Viscosity Semigroup Framework for Stable Image Reconstruction Authors: Arina Oberoi Published: 2026-05-26 Categories: cs.CV, math.FA arXiv: https://arxiv.org/abs/2606.20620v1 Starting from the axiomatic formulation of scale-space theory, we develop a viscosity-solution framework for multiscale image representations arising from degenerate elliptic-parabolic partial differential equations. Rather than introducing a new semigroup theory, we work within the standard viscosity-solution setting, using comparison principles to obtain well-posedness, uniqueness, and contraction in the supremum norm. This perspective is used to motivate a hybrid reconstruction operator in which a learned inverse map is followed by a nonlinear diffusion evolution. At the continuous level, the diffusion operator satisfies non-expansiveness, which provides stability for the reconstruction process; this framework is then evaluated on a CT-based mesothelioma classification task, where it attains an AUC of 0.875 with negligible variation across epochs, while the baseline model acquires AUC values from 0.49 to 0.80 without a clear convergence pattern. These observations are consistent with the stabilizing role suggested by the discussed viscosity theory. --- ### Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models Authors: Liyi Zhang, Akshay K. Jagadish, Brenden M. Lake, Thomas L. Griffiths Published: 2026-05-26 Categories: cs.CL, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.09856v1 Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations. There are challenges to using standard fine-tuning methods for inductive reasoning, including difficulties in curating large-scale, high-quality labeled datasets and in handling targets that are inherently distributional. In this work, we introduce a novel approach, called Program-based Posterior Training (PPT), to address these limitations: we use an LLM to generate diverse open-world scenarios as probabilistic programs, run probabilistic inference to produce distributional target responses to queries, and then fine-tune on these probabilistic soft labels. Using this approach, we fine-tune LLMs on 10,000 programmatically generated scenarios and evaluate on held-out motifs, human-labeled judgments, and external benchmarks. Overall, PPT substantially improves estimation accuracy on held-out inductive tasks, increases alignment with human judgments, and transfers to external benchmarks for estimation and calibration. Additionally, the gains in raw calibration are not subsumed by post-hoc temperature scaling, showing that the models have more deeply internalized uncertainty compared to output rescaling. Together, these results suggest that probabilistic-program-mediated fine-tuning is a promising approach for post-training LLMs to reliably perform approximate inductive inference. --- ### MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting Authors: Joonhyung Bae Published: 2026-05-26 Categories: cs.MM, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.09855v2 Korean folk painting (minhwa) is built from a small vocabulary of auspicious symbols, a tiger for protection, a pair of birds for marital harmony, a peony for wealth, that recur across many of its painted genres. This suggests an obvious computational approach, identify which symbols appear in a painting and read the genre from the inventory. Working with a public corpus that pairs whole paintings, eight-field bilingual curatorial captions, and a separate set of expert object crops, we find that this approach does not work. A model given only a list of which symbols a painting contains predicts the genre far worse than a model that fuses the image with the curatorial text, and forcing the genre representation to be object-grounded actively hurts accuracy. The visual evidence on which the genre prediction rests is nonetheless localized and inspectable. A leakage-safe object evidence map projected from a part-level detector is spatially faithful to where curators isolated symbolic objects and to a patch-based surrogate's own gradient saliency. We name this configuration a faithful-but-insufficient dissociation. The part-level explanation is honest about what the part-level model sees, yet the genre target turns on how symbols are arranged rather than on which ones appear. The same lens separates a content label that survives transfer to held-out source institutions, genre, from a style label that does not, era, a prediction we confirm on two further labels in the corpus. We release the multimodal system, a worked-example reading of one painting's evidence map against its catalogue, and a set of evaluation cautions that recur in long-tailed heritage collections. --- ### Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks Authors: Lihui Liu, Mucun Sun, Caisheng Wang Published: 2026-05-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07583v1 Self-healing smart grids can quickly adjust their network configuration during outages to minimize power disruptions. During an outage, several actions can be taken, such as network reconfiguration through switching operations and emergency load shedding. However, traditional machine learning methods for outage mitigation are not well suited for smart grids due to their slow response time and high computational cost. To address these challenges, recent studies have explored reinforcement learning to automatically perform network reconfiguration. In these approaches, the control policy is typically modeled using a graph neural network (GNN). However, conventional GNNs operate in the spatial domain and may fail to capture important relationships in the frequency domain. Frequency-domain information is particularly useful for modeling global structural patterns and system-wide interactions in power networks. In this paper, we propose a spectral graph reinforcement learning framework for outage management in distribution networks to enhance system resilience. Our model learns the optimal power restoration policy using a spectral graph neural network. We evaluate the proposed method on three modified IEEE test systems: the 13-bus, 34-bus, and 123-bus networks. Experimental results show that our approach achieves near-optimal performance in real time and generalizes well across a wide range of outage scenarios. --- ### Customer Churn Prediction on Structured Data Using FT-Transformer and Stacking Ensembles Authors: Joyjit Roy, Samaresh Kumar Singh, Laxmi Shaw Published: 2026-05-26 Categories: cs.LG, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2606.07582v1 Customer churn prediction is essential across data-driven industries such as insurance, digital banking, eCommerce, and subscription platforms, where retaining existing customers is typically more cost-effective than acquiring new ones. Predicting churn on structured datasets remains challenging due to class imbalance, nonlinear feature interactions, and heterogeneous feature types. Tree-based ensemble methods consistently demonstrate strong performance in these contexts, often outperforming conventional neural networks. This study introduces a validated hybrid architecture that integrates feature-tokenized transformers (FT-Transformer) with gradient-boosted trees through calibration-aware stacking. The proposed framework addresses persistent gaps in statistical validation, probability calibration, and reproducibility found in prior research. The FT-Transformer captures higher-order feature interactions using self-attention, while XGBoost captures gradient-boosted decision boundaries with complementary inductive biases. Class imbalance is handled using class-weighted loss functions, thereby avoiding synthetic oversampling and preserving minority-class distributions. The models are ensembled using out-of-fold (OOF) stacking with a logistic regression meta-learner, which recalibrates overconfident base model outputs and learns optimal combination weights. On a public bank churn dataset, the hybrid model achieves 62.10% F1, 0.861 AUC-ROC, and 0.647 PR-AUC, outperforming the Multi-Layer Perceptron (MLP) baseline by 3.37 F1 points and 0.027 AUC under 5x5 cross-validation with 95% confidence intervals reported. Ablation studies demonstrate that both the transformer component and stacking strategy contribute materially to performance. The proposed methodology offers a reproducible and extensible reference architecture for contemporary churn prediction on structured tabular data. --- ### Training-Inference Kernel Contracts: Bounding Divergence in Post-Training and Deployment Authors: Bruce Changlong Xu, Lan Wu Published: 2026-05-26 Categories: cs.LG, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2606.07581v1 A modern post-training pipeline often writes one symbol for its policy, pi_theta, while evaluating it through two different programs: a training kernel optimized for autograd and an inference kernel optimized for low-precision, fused, dynamically batched serving. In finite precision, these kernels can induce different distributions at identical weights, with the gap concentrated on slices that aggregate benchmarks under-represent. This paper proposes kernel contracts: a contract-first framework for specifying acceptable divergence between K_train and K_inf. A contract C = (N, S, R, O, Pi) combines numerical, statistical, runtime, and observability clauses with an escalation policy from violations to routing actions. We derive a chain of bounds from logit drift to total-variation distance to bounded reward drift, and specialize it to RL post-training, where per-token importance-ratio drift yields a bound on policy-gradient bias under explicit support and norm assumptions. We also describe a four-stage promotion pipeline, online routing loop, and minimal YAML DSL for contract artifacts. This is a framework and vocabulary paper; we do not report production-scale empirical validation. --- ### Quantifying Uncertainty in Space Debris Capture with Active Tether-Net Systems Caused by Noisy Observations Authors: Feng Liu, Achira Boonrath, Eleonora M. Botta, Souma Chowdhury Published: 2026-05-26 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2606.07580v1 As Low Earth Orbit has grown more crowded with space debris, the need for reliable and efficient debris removal solutions becomes more urgent. An active tether-net system with maneuverable units is one of the promising solutions to this problem, whose success is dependent on the robustness of the net maneuver and closing decisions. These in turn are impacted by the uncertainties attributed to i) noisy observation of the target debris state (e.g., sensing errors), and ii) imperfect simulations of the complex net dynamics and net/debris interaction behavior, over which the decision system is trained. This paper focuses on the first of these two uncertainty sources, and presents a pipeline to propagate and quantify the resulting uncertainty in the debris capture performance expressed in terms of Capture Quality Index (CQI). This quantification is uniquely performed for both an active tether-net using a fixed baseline control and one using a trained neuro-control policy to guide the net maneuver during the deployment phase. Two different uncertainty quantification (UQ) techniques, namely Sobol's variance-based sensitivity analysis and perturbation-based method are exploited. A high-fidelity simulator and a lower-fidelity surrogate-based environment are used to demonstrate trade-offs between prediction accuracy versus ease of resolving uncertainties. --- ### MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport Authors: Tcharlies Bachmann Schmitz Published: 2026-05-26 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2606.07578v1 This paper extends MST-Direct, a Matching-via-Sinkhorn-Transport approach for multivariate geostatistical simulation, from the original bivariate, unconditional, small-grid formulation to multivariate, conditional, and large-grid settings. We address the three main limitations identified in the original work: (i) scalability beyond a few thousand nodes through a sparse, candidate-restricted Sinkhorn matcher with O(nC) memory complexity; (ii) extension to multiple variables by matching target value tuples onto an independent FFT-MA Gaussian backbone that reproduces a prescribed variogram; and (iii) hard-data conditioning by fixing observed data tuples at their spatial locations while conditioning the backbone through kriging. Because the transport plan remains a permutation of the target tuples, the multivariate joint distribution is preserved exactly. The method is validated using the same six-variate, heteroscedastic, strongly nonlinear reference distribution employed in Direct Multivariate Simulation (DMS), under both unconditional (200x200) and conditional (100x100, 200 hard-data samples) scenarios, and is benchmarked against the Projection Pursuit Multivariate Transform (PPMT). Results show that MST-Direct reproduces the joint distribution with zero histogram error, exactly honours hard data, and accurately reproduces the prescribed spatial correlation structure, whereas PPMT remains an approximation. Index Terms-Optimal transport, Sinkhorn algorithm, geostatistical simulation, multivariate simulation. --- ### OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs Authors: Guangzhi Sun, Yixuan Li, Yudong Yang, Chao Zhang Published: 2026-05-26 Categories: cs.AI, cs.CV, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2606.07577v1 Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited by the linear growth of video tokens and key-value (KV) caches. We present OmniMem, a memory-efficient streaming framework designed specifically for audio-visual LLMs. Unlike existing compression methods that treat all tokens uniformly, OmniMem introduces a modality-aware memory allocation strategy that separately manages visual and audio contexts, addressing the severe token imbalance between the two modalities. OmniMem further preserves informative and non-redundant KV states through perturbation-aware memory selection, enabling compact memory without sacrificing long-range understanding. To strengthen compression under realistic deployment constraints, we also explore budget-aware fine-tuning, which encourages the model to consolidate useful information into retained memory. Experiments on VideoMME Long, LVBench, and LVOmniBench with video-SALMONN 2+ and Qwen-2.5-Omni show that OmniMem consistently improves over strong training-free compression baselines by 2-4% absolute accuracy under the same memory budgets, with an additional 1-2% gain after fine-tuning. --- ### When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery Authors: Neel Tushar Shah, Manglam Kartik Published: 2026-05-26 Categories: cs.LG, cs.ET, cs.MA arXiv: https://arxiv.org/abs/2606.07576v1 We present CARTOGRAPH, a verification layer for AI scientists that couples unresolved-subspace experiment steering (select), explicit ambiguity closure (resolve), and residual-based library inadequacy detection (refuse). Under a local linear-Gaussian bridge, raw unresolved projection is the isotropic unresolved Fisher-information trace, while CARTOGRAPH-A is the exact unresolved A-optimal rule; closed-form EIG and Box-Hill arise as local comparators rather than global equivalents. Across five testbeds, CARTOGRAPH-A beats raw projection 129W/0T/15L at d = 8 (p < 10^-21) in a replicated structured cascade. More distinctively, the framework tentatively identifies three out-of-library pharmacokinetic mechanisms and then revokes those identifications as residuals expose structural misfit, while one perturbed in-library control stays identified throughout. In low-dimensional pharmacokinetic and filtered EPA settings, near-ties against disagreement are predicted by theory and observed. Finally, in a retrospective audit of 40 positive claims from the published A-Lab autonomous materials system, the refuse guard flags all 4 claims later marked inconclusive under manual reanalysis while passing 32/36 confirmed claims. Code is available at https://github.com/ai4science-boed/cartograph.git --- ### Forward-Looking Stress Testing Under Macro Scenarios: Stable SVaR Estimation Using a Hybrid GPR-HS Framework with SACS Authors: Ujjwala Vadrevu Published: 2026-05-26 Categories: q-fin.RM, cs.LG arXiv: https://arxiv.org/abs/2606.07575v1 Regulatory stress testing frameworks, including the Comprehensive Capital Analysis and Review (CCAR) and the Internal Capital Adequacy Assessment Process (ICAAP), require robust Stressed Value-at-Risk (SVaR) estimation under forward-looking macroeconomic scenarios. Traditional parametric approaches often exhibit numerical instability under extreme shocks, reducing the reliability of capital projections. This paper extends the Hybrid Gaussian Process Regression Historical Simulation (GPR-HS) framework of Vadrevu (2026) to forward-looking stress scenarios, demonstrating stability across three regimes: West Asia War, Climate Risk, and AI Bubble/Regulation. A key contribution is the Scenario-Averaged Covariance Stabilization (SACS) framework, which constructs stress covariance as a weighted aggregation of historical crisis regimes, providing stable and interpretable dependence structures. Stressed return paths are generated over a 252-day horizon using deterministic drift and stochastic residuals, while volatility is modeled via Gaussian Process Regression with Aggressive Noise Initialization (ANI). The framework exhibits consistent convergence across all assets and scenarios. SVaR ranges from -2.1020% to -2.2231%, with the coherence property |SES| > |SVaR| preserved. The results support GPR-HS with SACS as a stable and regulator-aligned approach for forward-looking SVaR and SES estimation in CCAR and ICAAP applications. --- ### Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connections Authors: Chenrui Wang, Yixuan Qiu Published: 2026-05-26 Categories: cs.DC, cs.AI, cs.LG, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2606.07574v1 Manifold-constrained hyper-connections (mHCs) have recently been proposed as a principled extension of hyper-connections, where the residual mixing matrices are constrained to be doubly stochastic via projection onto the Birkhoff polytope. In practical mHC implementations, this constraint is enforced by Sinkhorn-Knopp iterations, and the backward pass relies on unrolling the iterative solver. This design introduces substantial computation and memory overhead, and may also yield inaccurate projections when the algorithm converges slowly on challenging inputs, undermining the intended norm-control and stability guarantees of mHCs. In this work, we focus on the practically important 4x4 Birkhoff projection setting and develop an end-to-end acceleration framework. By leveraging the dual formulation, we reduce the problem to a three-dimensional unconstrained convex problem and solve it with Newton's method, achieving fast convergence and high accuracy. For the backward pass, we replace the unrolled differentiation with implicit differentiation, yielding exact gradients without storing intermediate states. To exploit massive parallelism, we design a warp-level CUDA kernel that uses only register-level primitives, avoiding global and shared memory I/O. Extensive experiments against representative open-source baselines demonstrate that the proposed solver yields substantially more reliable doubly stochastic projections -- especially when the input magnitude is large -- and achieves significant end-to-end speedups (including the backward pass), reaching over 20x acceleration at large batch sizes while maintaining orders of magnitude smaller marginal errors. --- ### Forecasting Japanese elections: A nonlinear machine-learning approach Authors: Sota Kato, Xuan Luo, Budrul Ahsan, Asahi Obata, Takafumi Nakanishi Published: 2026-05-26 Categories: physics.soc-ph, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2606.07572v1 Despite Japan being one of the world's largest advanced democracies, the development of election forecasting models for its national elections remains limited. This study introduces nonlinear machine-learning forecasting models, based on decision tree and ensemble learning methods, for predicting the outcomes of Japanese lower-house elections. To assess the methodological benefits of our approach, we replicated the theoretical framework and dataset of Lewis-Beck and Tien's (LBT) foundational statistical forecasting model for Japanese elections. Our models demonstrated moderately but consistently improved predictive accuracy compared to LBT's model in both in-sample and out-of-sample evaluations, suggesting that nonlinear algorithms offer an alternative approach to classical linear methods in capturing complex electoral dynamics. This study represents one of the earlier applications of nonlinear machine-learning techniques to single-country election forecasting. It offers a replicable framework that, when combined with the country-specific electoral theories of other nations, may enhance the predictive performance of forecasting models in broader national contexts. --- ### Enabling KV Caching of Shared Prefix for Diffusion Language Models Authors: Younghun Go, Jaehoon Han, Changyong Shin, Chuck Yoo, Gyeongsik Yang Published: 2026-05-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07571v4 Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in emerging diffusion language models (DLMs). In DLMs, bidirectional attention means that updating any token dynamically alters the entire context and its corresponding KVs. Thus, existing caching techniques developed for LLMs, which assume that KVs remain invariant once computed, corrupt the shared prefix KVs. Our experiments show that applying these techniques to DLMs causes model accuracy to collapse to near zero. To unlock high-throughput DLM serving, we propose bidirectional prefix caching, BiCache, the first KV caching technique for shared prefixes in DLMs. BiCache is designed based on key observations from our comprehensive analysis: shared prefix KVs remain stable and reusable in shallow layers, while the depth of shallow layers depends on the fraction of shared prefix tokens in each request. Thus, BiCache dynamically identifies a safe layer depth for reusing shared prefix KVs and eliminates redundant computation. Evaluations demonstrate that BiCache significantly improves serving throughput by 36.3%-98.3% compared to existing techniques without accuracy collapse (only 0-1.8% difference). --- ### Enabling KV Caching of Shared Prefix for Diffusion Language Models Authors: Younghun Go, Jaehoon Han, Changyong Shin, Chuck Yoo, Gyeongsik Yang Published: 2026-05-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07571v2 Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in emerging diffusion language models (DLMs). In DLMs, bidirectional attention means that updating any token dynamically alters the entire context and its corresponding KVs. Thus, existing caching techniques developed for LLMs, which assume that KVs remain invariant once computed, corrupt the shared prefix KVs. Our experiments show that applying these techniques to DLMs causes model accuracy to collapse to near zero. To unlock high-throughput DLM serving, we propose bidirectional prefix caching, bicache, the first KV caching technique for shared prefixes in DLMs. bicache is designed based on key observations from our comprehensive analysis: shared prefix KVs remain stable and reusable in shallow layers, while the depth of shallow layers depends on the fraction of shared prefix tokens in each request. Thus, bicache dynamically identifies a safe layer depth for reusing shared prefix KVs and eliminates redundant computation. Evaluations demonstrate that bicache significantly improves serving throughput by 36.3%-98.3% compared to existing techniques without accuracy collapse (only 0-1.8% difference). --- ### Can LLMs extract scientific consensus? A case study in high-temperature superconductivity Authors: Mouyang Cheng, Wenhao He, Zhuotao Jin, Bowen Yu, Ju Li, Boris Kozinsky, Yao Wang, Pavel Volkov, Liangzi Deng, Ching-Wu Chu, Xiao-Gang Wen, Mingda Li Published: 2026-05-26 Categories: cs.DL, cs.LG arXiv: https://arxiv.org/abs/2606.07570v1 Scientific knowledge is increasingly dispersed across vast and heterogeneous scientific literature, where important claims are often implicit, evolving, and internally debated. While large language models (LLMs) have shown impressive performance in information extraction and summarization, their ability to recover latent scientific consensus remains unclear. Here, we investigate this problem in the context of high-temperature superconductivity (HTS), a long-standing and highly debated topic in condensed matter physics, as a challenging testbed. Using near 18,000 highly-cited publications over the past seven decades, we construct a structured knowledge graph linking competing superconducting mechanisms, material families, evidential modalities, and citation relations. We find that LLM-extracted representations recover coherent and physically interpretable structures, including family-dependent mechanism profiles, evidence-specific correlations, and citation-mediated temporal evolution of scientific beliefs. Ablation studies on LLM further show that the global structure remains robust across prompting, decoding, and model variations. Our results suggest that LLMs can indeed serve as scalable tools for deciphering scientific knowledge in domains characterized by competing interpretations and evolving knowledge. --- ### TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation Authors: Zesen Wang, Lijuan Lan, Yonggang Li, Chunhua Yang Published: 2026-05-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.07569v2 Accurate carbon emission monitoring is critical for climate policy and emerging regulatory mechanisms such as the EU Carbon Border Adjustment Mechanism, yet city-level high-frequency monitoring data remain extremely scarce, severely limiting data-hungry deep learning models. Time series generation is a natural remedy, but existing GAN and diffusion-based generators often provide limited explicit supervision for the domain structure of carbon emission data: they may match marginal distributional statistics while insufficiently preserving cross-variable correlations between CO$_2$ and co-emitted pollutants and meteorological factors, and tend to collapse the first-difference statistics of atmospheric measurements, producing sequences that are smooth on average but lack the realistic step-wise variability of the underlying signals. We propose TriHead-GAN, a Transformer-based adversarial framework whose triple-head discriminator jointly supervises three complementary aspects of the joint distribution: distributional authenticity via a Wasserstein critic, cross-variable dependency via leakage-free regression of the target variable, and step-wise temporal smoothness via adjacent-difference prediction. The generator combines global self-attention with local temporal convolution, per-step noise injection, and an anti-smoothing loss that matches first-difference statistics. Experiments on the self-collected Changsha Carbon dataset, two public carbon datasets (China, US), and the ETTh1 benchmark show that TriHead-GAN achieves favorable performance over mainstream baselines on the vast majority of settings, and that the resulting synthetic windows improve downstream forecasting accuracy in low-resource carbon monitoring scenarios. --- ### TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation Authors: Zesen Wang, Lijuan Lan, Yonggang Li, Chunhua Yang Published: 2026-05-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.07569v1 Accurate carbon emission monitoring is critical for climate policy and emerging regulatory mechanisms such as the EU Carbon Border Adjustment Mechanism, yet city-level high-frequency monitoring data remain extremely scarce, severely limiting data-hungry deep learning models. Time series generation is a natural remedy, but existing GAN and diffusion-based generators often provide limited explicit supervision for the domain structure of carbon emission data: they may match marginal distributional statistics while insufficiently preserving cross-variable correlations between CO$_2$ and co-emitted pollutants and meteorological factors, and tend to collapse the first-difference statistics of atmospheric measurements, producing sequences that are smooth on average but lack the realistic step-wise variability of the underlying signals. We propose TriHead-GAN, a Transformer-based adversarial framework whose triple-head discriminator jointly supervises three complementary aspects of the joint distribution: distributional authenticity via a Wasserstein critic, cross-variable dependency via leakage-free regression of the target variable, and step-wise temporal smoothness via adjacent-difference prediction. The generator combines global self-attention with local temporal convolution, per-step noise injection, and an anti-smoothing loss that matches first-difference statistics. Experiments on the self-collected Changsha Carbon dataset, two public carbon datasets (China, US), and the ETTh1 benchmark show that TriHead-GAN achieves favorable performance over mainstream baselines on the vast majority of settings, and that the resulting synthetic windows improve downstream forecasting accuracy in low-resource carbon monitoring scenarios. --- ### A Systematic Study of Behavioral Cloning for Scientific Data Annotation Authors: Ishaan Singh Chandok, Core Francisco Park Published: 2026-05-26 Categories: cs.HC, cs.AI, cs.CV, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2606.07568v1 Scientific data annotation, such as tracking animals in video or proofreading neural reconstructions, remains bottlenecked by the "last mile" problem: even with strong automation, verification and correction consume substantial human effort. Standard approaches train models to directly predict annotations, discarding the rich supervision in how experts navigate, click, verify, and correct. We introduce a framework for studying behavioral cloning on scientific annotation: 9 synthetic tasks paired with synthetic annotations that simulate realistic human strategies including exploration, mistake correction, and strategic decision-making. Our experiments reveal several findings. First, skills emerge hierarchically: models learn GUI mechanics before task-critical decisions, and commit fewer mistakes than the training data while retaining the ability to correct errors when they occur. Second, scaling models on multi-task behavioral cloning shows that larger models are more data efficient within our scale range. Third, multi-task pretraining enables efficient fine-tuning to new tasks, while training from scratch fails entirely. Fourth, linear probes reveal that models internally represent latent variables of the annotation process such as task phase and data position; interestingly, we find a shared mistake representation that generalizes across different annotation tasks. Overall, our framework establishes systematic benchmarks and identifies key bottlenecks, providing a foundation for scaling behavioral cloning to real-world scientific data annotation. --- ### Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks Authors: Nguyen Cong Luong, Shaohan Feng, Nguyen Duc Hai, Zeping Sui, Bo Ma, Min Xu, Zhihao Dong, Qiushi Zhao, Nguyen Duc Duy Anh, Nguyen Quoc Khanh, Ngoc Hung Nguyen, Zitian Zhang et al. Published: 2026-05-26 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2606.05208v1 Reinforcement Learning (RL) has long been a powerful solution to various problems in communication networks. However, traditional RL models still face with several limitations. Not only do they rely on large numbers of interactions with the environment, but they are also limited in terms of modeling long-term relationships and tackling partial observability. In recent years, the Transformer model has demonstrated the ability to enhance RL models, allowing them to overcome these issues. Particularly, the self-attention mechanism within the Transformer enables efficient modeling of long-range dependencies and global correlations, as well as accelerates training processes and handles heterogeneous data modalities. In this paper, we present a comprehensive survey of Transformer-based RL algorithms and their applications in communication networks. Specifically, the paper provides the mathematical background of RL and Transformer architectures, along with insights into key issues such as resource allocation, computation offloading, routing, and trajectory control, and network security. We conclude the paper by discussing challenges, open issues, and notable future research directions, including Transformer-enhanced DRL algorithms for semantic communication and network optimization. --- ### FSA-GRPO: Teaching Auditory LLMs to Use Few-Shot Demonstrations Authors: Haolong Zheng, Siyin Wang, Xulin Fan, Zengrui Jin, Mark Hasegawa-Johnson Published: 2026-05-26 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.02615v2 Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition. However, most auditory large language models are not explicitly trained to perform inference in this demonstration-conditioned format, limiting the extent to which they can benefit from In-Context Learning (ICL). To address this limitation, we introduce Few-Shot Aware GRPO (FSA-GRPO), an RL-based post-training recipe that uses a specially designed reward to encourage the model to leverage few-shot demonstrations, thereby strengthening its few-shot adaptation ability. Notably, training with only 2k high-resource adult ASR utterances improves the model's general few-shot adaptation ability, yielding gains not only in children's speech recognition (53.9% relative WER reduction without any in-domain training) but also in multilingual ASR (including low-resource languages), speech translation, and audio understanding. We further study data selection and the weight and similarity cutoffs of the auxiliary reward to identify an effective training recipe. Our experiments show that when in-domain data are unavailable or cannot be used for training, FSA-GRPO is more effective than direct tuning on related out-of-domain data. --- ### FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations Authors: Haolong Zheng, Siyin Wang, Xulin Fan, Zengrui Jin, Mark Hasegawa-Johnson Published: 2026-05-26 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.02615v1 Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition. However, most auditory large language models are not explicitly trained to perform inference in this demonstration-conditioned format, limiting the extent to which they can benefit from few-shot prompting. To address this limitation, we introduce Few-Shot Aware GRPO (FSA-GRPO), an RL-based post-training recipe that uses a specially designed reward to encourage the model to leverage few-shot demonstrations, thereby strengthening its few-shot adaptation ability. Notably, training with only high-resource adult ASR data improves the model's general few-shot adaptation ability, yielding gains not only in children's speech recognition but also in speech translation and audio understanding. We further study data selection and auxiliary reward weighting to identify an effective training recipe. Our experiments show that when in-domain data are unavailable or cannot be used for training, FSA-GRPO is more effective than direct tuning on related out-of-domain data. --- ### Margin Play: A Multi-Agent System For Public Policy Analysis In The Brazilian Equatorial Margin Authors: Antonio de Sousa Leitão Filho, Fabrício Saul Lima, Selby Mykael Lima dos Santos, Rejani Bandeira Vieira Sousa, Luís Jorge Mesquita de Jesus, Dennys Correia da Silva, Allan Kardec Duailibe Barros Filho Published: 2026-05-26 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2606.02614v1 The Brazilian Equatorial Margin (BEM) is Brazil's next offshore oil frontier, with operations expected to begin in 2026 in the Foz do Amazonas basin. Its assets are fiscally and territorially linked primarily to Maranhao -- the state with the lowest HDI in the Federation (0.676, IBGE 2022). This raises the central policy question: under what conditions does BEM exploration generate net positive externalities for Maranhao? The problem is intrinsically multi-agent: the Federal Government seeks revenue and energy security; the state seeks regional welfare under constitutional royalty earmarking; the operator maximizes profit under risk; ANP and IBAMA hold conflicting mandates; and Amazonian communities prioritize territorial and environmental vectors over monetary income. We present Margin Play, a Multi-Agent Reinforcement Learning (MARL) system simulating these tensions under Brazilian empirical calibration and classical economic literature. It implements six agents under the CTDE paradigm, trained with BRO-MARL. Results from 60,000 episodes across six scenarios indicate the answer is conditional on the institutional regime: under the reference baseline, the welfare gain is marginal (Waval approx. 1.68), whereas the MA-Prospero configuration yields Delta W = +17.5% and Delta Rcom = +21.3%, with a lower environmental liability (Eamb = 0.048 vs. 0.076). The fundamental problem is not a trade-off between production and welfare, but the choice of public policy regime linked to exploration. --- ### Motif-based morphology signatures for interpretable ECG screening and monitoring Authors: Nivedita Bijlani, Mauricio Villarroel Published: 2026-05-26 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00107v1 Electrocardiography (ECG) remains central to cardiovascular screening, yet interpretation remains largely manual and episodic. Clinical practice relies on brief resting ECGs and, when required, long-duration ambulatory recordings, both generating data that require resource-intensive review. Consequently, subtle morphological changes or progressive drift preceding clinically apparent abnormalities may go unnoticed. We propose a motif-based framework that defines beat-aligned ECG motifs as interpretable cardiac signatures and quantifies morphological drift and deviation across short and long-term monitoring. Motifs are representative cardiac cycles capturing dominant morphology. We introduce three interpretable drift metrics: deviation from a normal sinus rhythm (NSR), deviation from a personalised baseline, and a motif instability index. Motifs are extracted by selecting beats that minimise Dynamic Time Warping (DTW) distance within fixed windows. We evaluate these metrics on short (PTB-XL) and long-duration (MIT-BIH Arrhythmia) ECG datasets. Interpretability is achieved through representative motif overlays and fiducial-based visualisations, enabling direct inspection of morphological changes. In MIT-BIH, the proposed metrics significantly separated predominantly normal from arrhythmic subjects (p<0.01). In PTB-XL, NSR deviation distinguished normal from abnormal ECGs across major diagnostic subtypes (p<1e-4, Cliff's delta up to 0.93). ECG motifs provide an interpretable representation of cardiac morphology, supporting scalable longitudinal monitoring and early detection of morphology-driven change. --- ### A Methodological Framework for Explicit Control of the Speed-Accuracy Trade-off in Brain-Computer Interfaces Authors: Javier Jiménez, Francisco B Rodríguez Published: 2026-05-26 Categories: eess.SP, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2606.00106v1 Brain-computer interfaces (BCIs) are limited by low signal-to-noise ratio in modalities such as electroencephalography, which requires multiple trials to reliably decode user intentions. This induces a speed-accuracy trade-off, whereby higher accuracy comes at the cost of speed. The speed-accuracy balance is application-dependent, motivating controllable trade-offs. Conventional metrics, such as the Information Transfer Rate, combine speed and accuracy obscuring their dependence and potentially introducing biases. In this study, we propose an evaluation framework independent of classifier, paradigm, and early-stopping strategy that separates speed and accuracy. We employ two measures, Gain (relative speed improvement) and Conservation (relative accuracy preservation), and combine them into a tunable Gain-Cons Balance controlled by α, regulating the speed-accuracy trade-off. The parameter adjusts the operating point without modifying the classifier, facilitating deployment across scenarios. The framework was evaluated on P300 event-related potential paradigms using public recordings from 63 subjects as well as multiple classifiers and early-stopping strategies to achieve distinct operating points in speed-accuracy and bitrate. Results show that tuning α yields fast, accurate, or balanced BCI behaviours, demonstrating explicit control of the speed-accuracy trade-off. The method supports subject-level performance prediction and improves explainability of BCI behaviour. Further analysis of the Information Transfer Rate reveals a systematic bias toward speed, explained by the proposed framework through the Gain and Conservation measurements. Overall, this work establishes the speed-accuracy trade-off as a controllable design variable validated on public P300-based paradigms, enabling transparent evaluation and application-specific optimization of BCIs. --- ### Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning Authors: Junkai Chen, Yuhao He, Junxiang You, Ruiqi Liu, Chenyu Wang, Shu Wu Published: 2026-05-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00105v1 Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raising concerns about privacy and broader safety risks. Machine Unlearning (MU) provides a promising way to remove targeted undesirable knowledge from trained models without retraining from scratch while preserving general model utility. Nevertheless, effective unlearning in MLLMs remains particularly challenging. Existing training-based methods often struggle to balance unlearning effectiveness and model utility. In contrast, training-free methods such as in-context unlearning preserve model utility by avoiding parameter updates, but they do not remove memorized knowledge at the parameter level and may remain vulnerable to reverse-engineering attacks. More importantly, in-context unlearning is insufficient in multimodal settings, where visual inputs can provide strong conditioning signals and induce undesirable outputs. To address these challenges, we propose Visual-Noise Guided In-Context Distillation (VGID), a distillation-based framework for MLLM unlearning. VGID dynamically constructs an unlearning-oriented teacher distribution from the frozen base model through dual-modal intervention that combines visual perturbation with textual in-context unlearning. The resulting intervention-induced distribution serves as a teacher signal for distillation, guiding the student model toward parameter-level unlearning without requiring external teacher models or explicit undesirable response annotations. Experimental results show that VGID achieves strong unlearning effectiveness while preserving competitive model utility, reducing forget set ROUGE-L by 0.371 with only a 0.055 drop in retain set ROUGE-L in a representative setting. --- ### PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs Authors: Erdem Uysal, Timo Kehrer, Sebastiano Panichella Published: 2026-05-26 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.00104v1 Foundation models are increasingly used to drive autonomous systems, yet existing approaches either keep the model in a tight control loop, raising latency and hallucination risk, or compile natural language into opaque end-to-end policies that are hard to explain, constraint and require domain-specific datasets and fine-tuning. We propose a planner-executor agent for PX4-based drones that decouples high-level mission planning from low-level control. A large language model performs single-pass task planning, while execution is handled through a structured ROS 2 tool-calling interface bridged to MAVLink. The system constructs a world model by combining modular 2D detectors (e.g., YOLO or vision-language models) with a pinhole depth projection module for 3D object localization. A constraint enforcement layer enforces altitude limits and horizontal geofencing, and bounded replanning enables recovery from execution-time action failures. We position our approach within three common design patterns for foundation-model-based robotics systems and demonstrate its feasibility in PX4 software-in-the-loop simulations in Gazebo. Results highlight improved explainability, constraint enforcement, and reduced LLM calls compared to tightly coupled LLM control. The code, dataset, videos, and other material can be found at the following link: https://github.com/erdemuysalx/PEACE --- ### Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games Authors: Mingyuan Fan, Weiguang Han, Daixin Wang, Cen Chen, Zhiqiang Zhang, Jun Zhou Published: 2026-05-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.00103v1 We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Wherein, LLMs receive only the task rules, must issue targeted queries to a hidden environment, integrate partial observations over time, and decide when to submit a final answer. Beyond standard success rate and interaction efficiency, we evaluate contextual robustness under controlled contextual perturbations, and metacognitive adaptation through counterfactual revision and necessity judgment. We instantiate the framework as a benchmark of 474 executable games, each evaluated under five fixed configuration search spaces corresponding to five difficulty levels, and evaluate a broad set of frontier LLMs. Results show that the benchmark is highly discriminative, exposing large differences not only in success rate but also in interaction efficiency. Moreover, we empirically show that contextual perturbations cause moderate but consistent declines, whereas counterfactual revision and necessity judgment lead to much larger drops. --- ### On the evolution of the concept of probability as a mirror of the evolution of reason Authors: Jean-Louis Le Mouël, Vincent Courtillot, Dominique Gibert, Vladimir Kossobokov, Jean-Baptiste Boulé, Pierpaolo Zuddas, Fernando Lopes, Païkan Marccagi, Alexis Maineult Published: 2026-05-26 Categories: cs.AI, math.PR arXiv: https://arxiv.org/abs/2606.00102v1 Over the centuries, probability theory has grown from the calculus of games of chance into a central framework for reasoning under uncertainty. This article interprets that evolution not merely as a mathematical history, but as a transformation of rationality itself. From Pascal and Fermat's combinatorial symmetry to the inductive logic of Bayes and Laplace, from Poisson's statistics of events to Kolmogorov's axiomatic formalization, probability progressively incorporated uncertainty, time, and coherence into scientific judgment. This trajectory reaches a mature epistemological form in modern Bayesian inference, especially in Tarantola's view of probability as a logic of information, where prior knowledge and data are combined coherently. Yet this framework also exposes a limit: probability quantifies uncertainty about well-defined propositions, but does not by itself formalize the vagueness of the concepts used to describe them. The article therefore examines how rationality extends beyond probability. Fuzzy logic is presented as a rigorous language for graded meaning and qualitative judgment, while deep learning is analyzed as a distinct, powerful mode of prediction based on geometric interpolation and optimization rather than explicit inference. By situating probability, fuzzy logic, and deep learning in a common historical and epistemological perspective, the article clarifies their roles and limits. It argues that contemporary scientific rationality cannot be reduced to data-driven performance alone, but requires the explicit articulation of uncertainty, vagueness, and inference. ---