# Research Papers — 2026-04 · bundle page 89 of 233 > Full-text markdown of papers #4401–4450 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/89 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/88.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/90.md) ### Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative Computation Authors: Hiroki Fujii, Masaki Yamakita Published: 2026-04-19 Categories: eess.SY, cs.LG, math.DS arXiv: https://arxiv.org/abs/2604.17221v2 Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capacity. We propose a factorized bilinear input modulation that augments the SSM with a state-input product, interpretable as a finite-dimensional Koopman bilinear form. After introducing a shared state across channels (Coupled SSM), the modulation admits three implementations. Coupled Bilinear Input Modulation (seq-BIM) retains the full bilinear product on the input side at the cost of sequential computation, Coupled Gated Modulation (GM) linearizes it into a gate modulation that is compatible with the parallel scan, and Parallel Bilinear Input Modulation (p-BIM) places the same bilinear product on the state transition while remaining parallel-scannable. Experiments on a multiple input-delay pendulum (memory retention) and NARMA-10 (bilinear computation) reveal a clear dissociation. GM substantially improves memory retention but not bilinear computation, while both seq-BIM and p-BIM improve both. A pathway ablation confirms that the two downstream routes of the bilinear signal serve complementary roles. The improvement is statistically robust, with the bilinear variants consistently outperforming the other variants on bilinear computation. Furthermore, only the bilinear variants benefit from increasing the SSM state dimension, while coupling or gate modulation alone show no improvement, establishing the bilinear mechanism as uniquely capable of exploiting larger state spaces. --- ### Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation Authors: Jiuyun Jiang, Yuecheng Hong, Bo Yang, Jin Yang, Guangxin Jiang, Xiaomeng Guo, Guang Xiao Published: 2026-04-19 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2604.17220v2 Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management. Although behavioral experiments have revealed cognitive biases behind supply chain inefficiencies, traditional methods face scalability and control limitations. We introduce a scalable experimental paradigm using Large Language Models (LLMs) to simulate multi-stage supply chain dynamics. Grounded in a Hierarchical Reasoning Framework, this study specifically analyzes the impact of cognitive heterogeneity on agent interactions. Unlike prior homogeneous settings, we employ DeepSeek and GPT agents to systematically vary reasoning sophistication across supply chain tiers. Through rigorously replicated and statistically validated simulations, we investigate how this cognitive diversity influences collective outcomes. Results indicate that agents exhibit myopic and self-interested behaviors that exacerbate systemic inefficiencies. However, we demonstrate that information sharing effectively mitigates these adverse effects. Our findings extend traditional behavioral methods and offer new insights into the dynamics of AI-enabled organizations. This work underscores both the potential and limitations of LLM-based agents as proxies for human decision-making in complex operational environments. --- ### PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory Authors: Chenyang Wang, Yun Yang Published: 2026-04-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.17219v1 We derive explicit non-asymptotic PAC-Bayes generalization bounds for Gibbs posteriors, that is, data-dependent distributions over model parameters obtained by exponentially tilting a prior with the empirical risk. Unlike classical worst-case complexity bounds based on uniform laws of large numbers, which require explicit control of the model space in terms of metric entropy (integrals), our analysis yields posterior-averaged risk bounds that can be applied to overparameterized models and adapt to the data structure and the intrinsic model complexity. The bound involves a marginal-type integral over the parameter space, which we analyze using tools from singular learning theory to obtain explicit and practically meaningful characterizations of the posterior risk. Applications to low-rank matrix completion and ReLU neural network regression and classification show that the resulting bounds are analytically tractable and substantially tighter than classical complexity-based bounds. Our results highlight the potential of PAC-Bayes analysis for precise finite-sample generalization guarantees in modern overparameterized and singular models. --- ### Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability Authors: Lijie Zhou Published: 2026-04-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.17217v1 Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an adversarial evaluation framework that quantifies this cross-modal dependency by measuring accuracy degradation (Drop) when semantically conflicting text is paired with unchanged images. Four adversarial strategies -- shape\_swap, color\_swap, position\_swap, and random\_text -- are applied to a controlled geometric-shapes dataset ($n{=}1{,}000$). We compare three configurations: Baseline CLIP (ViT-B/32), LoRA fine-tuning, and LoRA Optimized (integrating Hard Negative Mining, Label Smoothing, layer-wise learning rates, Cosine Restarts, curriculum learning, and data augmentation). The optimized model reduces average Drop from 27.5\% to 9.8\% (64.4\% relative improvement, $p{<}0.001$) while maintaining 97\% normal accuracy. Attention visualization and embedding-space analysis confirm that the optimized model attends more to visual features and achieves tighter cross-modal alignment. --- ### Continual Safety Alignment via Gradient-Based Sample Selection Authors: Thong Bach, Dung Nguyen, Thao Minh Le, Truyen Tran Published: 2026-04-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17215v1 Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and commonsense reasoning. We investigate which training samples cause alignment drift through a data-centric lens. Our empirical analysis shows samples contribute unequally: high-gradient samples cause greater safety degradation and drive models toward pretrained distributions, while moderate-gradient samples enable task learning with minimal alignment loss. We propose gradient-based sample selection that filters high-gradient samples during fine-tuning. Across multiple model families on continual domain tasks, our method substantially improves alignment preservation while maintaining competitive task performance, without requiring curated safe data or architectural modifications. Our method is robust across selection ratios, task orderings, and diverse attack benchmarks. --- ### Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition Authors: Nwe Ni Win, Jim Basilakis, Steven Thomas, Seyhan Yazar, Laura Pierce, Stephanie Liu, Paul M. Middleton, Nasser Ghadiri, X. Rosalind Wang Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17214v1 Extracting clinically relevant information from unstructured medical narratives such as admission notes, discharge summaries, and emergency case histories remains a challenge in clinical natural language processing (NLP). Medical Entity Recognition (MER) identifies meaningful concepts embedded in these records. Recent advancements in large language models (LLMs) have shown competitive MER performance; however, evaluations often focus on general entity types, offering limited utility for real-world clinical needs requiring finer-grained extraction. To address this gap, we rigorously evaluated the open-source LLaMA3 model for fine-grained medical entity recognition across 18 clinically detailed categories. To optimize performance, we employed three learning paradigms: zero-shot, few-shot, and fine-tuning with Low-Rank Adaptation (LoRA). To further enhance few-shot learning, we introduced two example selection methods based on token- and sentence-level embedding similarity, utilizing a pre-trained BioBERT model. Unlike prior work assessing zero-shot and few-shot performance on proprietary models (e.g., GPT-4) or fine-tuning different architectures, we ensured methodological consistency by applying all strategies to a unified LLaMA3 backbone, enabling fair comparison across learning settings. Our results showed that fine-tuned LLaMA3 surpasses zero-shot and few-shot approaches by 63.11% and 35.63%, respectivel respectively, achieving an F1 score of 81.24% in granular medical entity extraction. --- ### Symplectic Inductive Bias for Data-Driven Target Reachability in Hamiltonian Systems Authors: Zhuo Ouyang, Jixian Liu, Enrique Mallada Published: 2026-04-19 Categories: math.OC, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2604.17213v1 Inductive bias refers to restrictions on the hypothesis class that enable a learning method to generalize effectively from limited data. A canonical example in control is linearity, which underpins low sample-complexity guarantees for stabilization and optimal control. For general nonlinear dynamics, by contrast, guarantees often rely on smoothness assumptions (e.g., Lipschitz continuity) which, when combined with covering arguments, can lead to data requirements that grow exponentially with the ambient dimension. In this paper we argue that data-efficient nonlinear control demands exploiting inductive bias embedded in nature itself, namely, structure imposed by physical laws. Focusing on Hamiltonian systems, we leverage symplectic geometry and intrinsic recurrence on energy level sets to solve target reachability problems. Our approach combines the recurrence property with a recently proposed class of policies, called chain policies, which composes locally certified trajectory segments extracted from demonstrations to achieve target reachability. We provide sufficient conditions for reachability under this construction and show that the resulting data requirements depend on explicit geometric and recurrence properties of the Hamiltonian rather than the state dimension. --- ### EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents Authors: Yu Zhang, Kaiyuan Shen, Yang Li Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17211v1 We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied avatar must achieve real-time generation, unified listening-speaking behavior, and high rendered visual quality simultaneously. Our framework couples the first Rectified-Flow Diffusion Transformer (DiT) for this task with a differentiable renderer, enabling diverse, high-fidelity generation in as few as four sampling steps. Prior listening-speaking methods rely on dual-stream audio, introducing an interlocutor look-ahead dependency incompatible with causal user--LLM interaction. We instead adopt a single-stream interface with explicit per-frame listening-speaking state conditioning and a Streaming Audio Scheduler, suppressing spurious mouth motion during listening while enabling seamless turn-taking. A two-stage training scheme of coefficient-space pretraining and joint image-domain refinement further closes the gap between motion-level supervision and rendered quality. Extensive experiments demonstrate state-of-the-art visual quality and motion fidelity in both speaking and listening scenarios. --- ### Guardrails in Logit Space: Safety Token Regularization for LLM Alignment Authors: Thong Bach, Truyen Tran Published: 2026-04-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17210v1 Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing safety alignment techniques primarily focus on pretraining, leaving fine-tuned models vulnerable to behavioral shifts. In this work, we introduce safety token regularization (STR), a lightweight method designed to preserve safety properties during fine-tuning. Our approach identifies salient tokens from rejection templates of well-aligned models and constrains their associated logits during training, preventing the loss of critical safety behaviors. Unlike reinforcement learning or preference optimization methods, STR requires minimal additional computation and seamlessly integrates with parameter-efficient fine-tuning techniques such as LoRA. Comprehensive experiments demonstrate that our approach achieves safety performance on par with state-of-the-art methods, while preserving task-specific utility and requiring minimal implementation overhead. Furthermore, we show that safety token regularization enhances training stability and overall performance beyond safety considerations alone. This work offers a practical and readily deployable strategy for continual safety alignment in fine-tuned LLMs. --- ### DREAM: Dynamic Retinal Enhancement with Adaptive Multi-modal Fusion for Expert Precision Medical Report Generation Authors: Nagur Shareef Shaik, Teja Krishna Cherukuri, Dong Hye Ye Published: 2026-04-19 Categories: cs.CV, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2604.17209v1 Automating medical reports for retinal images requires a sophisticated blend of visual pattern recognition and deep clinical knowledge. Current Large Vision-Language Models (LVLMs) often struggle in specialized medical fields where data is scarce, leading to models that overfit and miss subtle but critical pathologies. To address this, we introduce DREAM (Dynamic Retinal Enhancement with Adaptive Multi-modal Fusion), a novel framework for high-fidelity medical report generation that excels even with limited data. DREAM employs a unique two-stage fusion mechanism that intelligently integrates visual data with clinical keywords curated by ophthalmologists. First, the Abstractor module maps image and keyword features into a shared space, enhancing visual data with pathology-relevant insights. Next, the Adaptor performs adaptive multi-modal fusion, dynamically weighting the importance of each modality using learnable parameters to create a unified representation. To ensure the model's outputs are semantically grounded in clinical reality, a Contrastive Alignment module aligns these fused representations with ground-truth medical reports during training. By combining medical expertise with an efficient fusion strategy, DREAM sets a new state-of-the-art on the DeepEyeNet benchmark, achieving a BLEU-4 score of 0.241, and further demonstrates strong generalization to the ROCO dataset. --- ### CDSA-Net:Collaborative Decoupling of Vascular Structure and Background for High-Fidelity Coronary Digital Subtraction Angiography Authors: Si Li, Chen-Kai Hu, Zhenhuan Lyu, Yuanqing He Published: 2026-04-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.17208v1 Digital subtraction angiography (DSA) in coronary imaging is fundamentally challenged by physiological motion, forcing reliance on raw angiograms cluttered with anatomical noise. Existing deep learning methods often produced images with two critical clinically unacceptable flaws: persistent boundary artifacts and a loss of native tissue grayscale fidelity that undermined diagnostic confidence. We propose a novel framework termed as CDSA-Net that for the first time explicitly decouples and jointly optimizes vascular structure preservation and realistic background restoration. CDSA-Net introduces two core innovations: (i) A hierarchical geometric prior guidance (HGPG) mechanism, embedded in our coronary structure extraction network (CSENet). It synergistically combines integrated geometric prior (IGP) with gated spatial modulation (GSM) and centerline-aware topology (CAT) loss supervision, ensuring structural continuity. (ii) An adaptive noise module (ANM) within our coronary background restoration network (CBResNet). Unlike standard restoration, ANM uniquely models the stochastic nature of clinical X-ray noise, bridging the domain gap to enable seamless background intensity estimation and the complete elimination of boundary artifacts. The final subtraction is obtained by removing the restored background from the raw angiogram. Quantitatively, it significantly outperformed state-of-the-art methods in vascular intensity correlation and perceptual quality. A 25.6% improvement in morphology assessment efficiency and a 42.9% gain in hemodynamic evaluation speed set a new benchmark for utility in interventional cardiology, while maintaining diagnostic results consistent with raw angiograms. The project code is available at https://github.com/DrThink-ai/CDSA-Net. --- ### Demystifying the Unreasonable Effectiveness of Greedy Alignment Methods Authors: Enoch Hyunwook Kang Published: 2026-04-19 Categories: cs.LG, cs.AI, cs.CC, cs.CL arXiv: https://arxiv.org/abs/2604.17207v2 Greedy AI alignment methods based on Bradley-Terry reward-model fitting and KL-regularized Alignment are remarkably effective in both offline and online preference-learning pipelines, yet existing O(log T) online and O(1/epsilon) offline KL-regularized regret rate guarantees can seem pessimistic relative to their empirical performance. We argue that this mismatch reflects a distinction between two learning targets: KL-regularized regret measures how fast we can recover the KL-regularized aligned policy, whereas we often only ask how fast we can learn the reward function that induces the correct best response. To isolate this reward-learning component, we study the traditional temperature-zero regret criterion, which evaluates only the top-ranked response at inference time. Under realizability, compactness, and a uniform best-response margin over the fitted reward class, we prove that exact reference-logged offline RLHF achieves exponentially small expected temperature-zero regret, and therefore reaches expected regret at most epsilon with O(log(1ε)) offline comparisons. We also prove that exact greedy online RLHF achieves bounded O(1) cumulative temperature-zero regret; the same guarantee extends to its equivalent pairwise online DPO formulation. By separating selector identification from full soft-policy recovery, our results provide a sharper theoretical explanation for the empirical efficiency of greedy alignment. --- ### Demystifying the unreasonable effectiveness of online alignment methods Authors: Enoch Hyunwook Kang Published: 2026-04-19 Categories: cs.LG, cs.AI, cs.CC, cs.CL arXiv: https://arxiv.org/abs/2604.17207v1 Iterative alignment methods based on purely greedy updates are remarkably effective in practice, yet existing theoretical guarantees of \(O(\log T)\) KL-regularized regret can seem pessimistic relative to their empirical performance. In this paper, we argue that this mismatch arises from the regret criterion itself: KL-regularized regret conflates the statistical cost of learning with the exploratory randomization induced by the softened training policy. To separate these effects, we study the traditional temperature-zero regret criterion, which evaluates only the top-ranked response at inference time. Under this decision-centric notion of performance, we prove that standard greedy online alignment methods, including online RLHF and online DPO, achieve constant \((O(1))\) cumulative regret. By isolating the cost of identifying the best response from the stochasticity induced by regularization, our results provide a sharper theoretical explanation for the practical superb efficiency of greedy alignment. --- ### SciDraw-6K: A Multilingual Scientific Illustration Dataset Generated by Google Gemini Authors: Davie Chen Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17206v1 We present SciDraw-6K, a curated dataset of 6,291 scientific illustrations synthesized by Google Gemini image-generation models, each paired with prompts in eleven languages (English, Simplified Chinese, Traditional Chinese, Japanese, Korean, German, French, Spanish, Brazilian Portuguese, Italian, and Russian). Images span eight broad scientific categories -- biomedical, chemistry, materials, electronics, environment, AI systems, physics, and a long "other" tail -- and are produced primarily by the gemini-2.5-flash-image and gemini-3-pro-image-preview model families. In contrast to general-purpose text-to-image corpora that dominate the literature, SciDraw-6K is purpose-built for the scientific illustration genre: schematic diagrams, mechanism figures, table-of-contents graphics, and conceptual posters. We describe the construction pipeline, report dataset statistics, and document its use as the substrate of sci-draw.com, a public scientific drawing service. The dataset is released to support multilingual text-to-image research, domain-adapted diffusion fine-tuning, and prompt-engineering studies for scientific visualization. Dataset: https://huggingface.co/datasets/SciDrawAI/SciDraw-6K Code: https://github.com/SciDrawAI/scidraw-6k --- ### Calibrating Model-Based Evaluation Metrics for Summarization Authors: Hongye Liu, Dhanajit Brahma, Ricardo Henao Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17200v1 Recent advances in summary evaluation are based on model-based metrics to assess quality dimensions, such as completeness, conciseness, and faithfulness. However, these methods often require large language models, and predicted scores are frequently miscalibrated, limiting their reliability. Moreover, evaluating the average quality across different summaries for a single document typically requires access to multiple reference summaries. Here, we propose a general framework that generates individual and average proxy scores without relying on reference summaries, human annotations, or expensive model-based metrics. We also propose group isotonic regression binning (GIRB), a calibration method that adjusts the raw predictions to better align with ground-truth evaluation metrics. While we focus on continuous-value scenarios, such as summarization, the method is applicable to discrete-value tasks, such as question answering. Experiments on seven datasets demonstrate that our approach consistently outperforms existing baselines. --- ### Learning to Control Summaries with Score Ranking Authors: Hongye Liu, Liang Ding, Ricardo Henao Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17197v1 Recent advances in summarization research focus on improving summary quality across multiple criteria, such as completeness, conciseness, and faithfulness, by jointly optimizing these dimensions. However, these efforts largely overlook the challenge of controlling summary generation with respect to individual criteria, especially in the presence of their inherent trade-offs. For example, enhancing conciseness can compromise completeness, and vice versa. In this work, we address this gap by proposing a loss function that aligns model outputs with fine-grained, model-based evaluation scores (e.g., from FineSurE), enabling both improvement in summary quality and dimension-specific control. Our approach improves the overall quality of summaries while maintaining the ability to selectively prioritize one criterion over others. Experiments on three pretrained models (LLaMA, Qwen, and Mistral) demonstrate that our method achieves performance comparable to state-of-the-art summarizers, while uniquely offering strong controllability over individual quality dimensions. --- ### DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior Authors: Junjia Huang, Binbin Yang, Pengxiang Yan, Jiyang Liu, Bin Xia, Zhao Wang, Yitong Wang, Liang Lin, Guanbin Li Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17195v2 Storyboard synthesis plays a crucial role in visual storytelling, aiming to generate coherent shot sequences that visually narrate cinematic events with consistent characters, scenes, and transitions. However, existing approaches are mostly adapted from text-to-image diffusion models, which struggle to maintain long-range temporal coherence, consistent character identities, and narrative flow across multiple shots. In this paper, we introduce DreamShot, a video generative model based storyboard framework that fully exploits powerful video diffusion priors for controllable multi-shot synthesis. DreamShot supports both Text-to-Shot and Reference-to-Shot generation, as well as story continuation conditioned on previous frames, enabling flexible and context-aware storyboard generation. By leveraging the spatial-temporal consistency inherent in video generative models, DreamShot produces visually and semantically coherent sequences with improved narrative fidelity and character continuity. Furthermore, DreamShot incorporates a multi-reference role conditioning module that accepts multiple character reference images and enforces identity alignment via a Role-Attention Consistency Loss, explicitly constraining attention between reference and generated roles. Extensive experiments demonstrate that DreamShot achieves superior scene coherence, role consistency, and generation efficiency compared to state-of-the-art text-to-image storyboard models, establishing a new direction toward controllable video model-driven visual storytelling. --- ### Forecast Sports Outcomes under Efficient Market Hypothesis: Theoretical and Experimental Analysis of Odds-Only and Generalised Linear Models Authors: Kaito Goto, Naoya Takeishi, Takehisa Yairi Published: 2026-04-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.17194v1 Converting betting odds into accurate outcome probabilities is a fundamental challenge in order to use betting odds as a benchmark for sports forecasting and market efficiency analysis. In this study, we propose two methods to overcome the limitations of existing conversion methods. Firstly, we propose an odds-only method to convert betting odds to probabilities without using historical data for model fitting. While existing odds-only methods, such as Multiplicative, Shin, and Power exist, they do not adjust for biases or relationships we found in our betting odds dataset, which consists of 90014 football matches across five different bookmakers. To overcome these limitations, our proposed Odds-Only-Equal-Profitability-Confidence (OO-EPC) method aligns with the bookmakers' pricing objectives of having equal confidence in profitability for each outcome. We provide empirical evidence from our betting odds dataset that, for the majority of bookmakers, our proposed OO-EPC method outperforms the existing odds-only methods. Beyond controlled experiments, we applied the OO-EPC method under real-world uncertainty by using it for six iterations of an annual basketball outcome forecasting competition. Secondly, we propose a generalised linear model that utilises historical data for model fitting and then converts betting odds to probabilities. Existing generalised linear models attempt to capture relationships that the Efficient Market Hypothesis already captures. To overcome this shortcoming, our proposed Favourite-Longshot-Bias-Adjusted Generalised Linear Model (FL-GLM) fits just one parameter to capture the favourite-longshot bias, providing a more interpretable alternative. We provide empirical evidence from historical football matches where, for all bookmakers, our proposed FL-GLM outperforms the existing multinomial and logistic generalised linear models. --- ### Do LLM-derived graph priors improve multi-agent coordination? Authors: Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna Published: 2026-04-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17191v1 Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly in multi-domain operations (MDO). A central challenge in cooperative MARL is determining how agents should coordinate: existing approaches must either hand-specify graph topology, rely on proximity-based heuristics, or learn structure entirely from environment interaction; all of which are brittle, semantically uninformed, or data-intensive. We investigate whether large language models (LLMs) can generate useful coordination graph priors for MARL by using minimal natural language descriptions of agent observations to infer latent coordination patterns. These priors are integrated into MARL algorithms via graph convolutional layers within a graph neural network (GNN)-based pipeline, and evaluated on four cooperative scenarios from the Multi-Agent Particle Environment (MPE) benchmark against baselines spanning the full spectrum of coordination modeling, from independent learners to state-of-the-art graph-based methods. We further ablate across five compact open-source LLMs to assess the sensitivity of prior quality to model choice. Our results provide the first quantitative evidence that LLM-derived graph priors can enhance coordination and adaptability in dynamic multi-agent environments, and demonstrate that models as small as 1.5B parameters are sufficient for effective prior generation. --- ### LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation Authors: Yuwei Ning, Ganlong Zhao, Yipeng Qin, Si Liu, Yang Liu, Liang Lin, Guanbin Li Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17190v1 Aerial Vision-and-Language Navigation (Aerial VLN) enables unmanned aerial vehicles (UAVs) to follow natural language instructions and navigate complex urban environments. While recent advances have achieved progress through large-scale memory graphs and lookahead path planning, they remain limited by shallow instruction understanding and high computational cost. In particular, existing methods rely primarily on landmark descriptions, overlooking directional cues "a key source of spatial context in human navigation". In this work, we propose LookasideVLN, a new paradigm that exploits directional cues in natural language to achieve both more accurate spatial reasoning and greater computational efficiency. LookasideVLN comprises three core components: (1) an Egocentric Lookaside Graph (ELG) that dynamically encodes instruction-relevant landmarks and their directional relationships, (2) a Spatial Landmark Knowledge Base (SLKB) that provides lightweight memory retrieval from prior navigation experiences, and (3) a Lookaside MLLM Navigation Agent that aligns multimodal information from user instructions, visual observations, and landmark-direction information from ELG for path planning. Extensive experiments show that LookasideVLN significantly outperforms the state-of-the-art CityNavAgent, even with a single-level lookahead, demonstrating that leveraging directional cues is a powerful yet efficient strategy for Aerial VLN. --- ### Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization Authors: Xiaoyong Mei, Tingting Zuo, Da Chen, Guangyu Hu, Xiangyu Wen, Chao Duan, Mingyan Zhang, Fudan Zheng Published: 2026-04-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.17188v2 Multi-role dialogue summarization requires modeling complex interactions among multiple speakers while preserving role-specific information and factual consistency. However, most existing methods optimize for automatic metrics such as ROUGE and BERTScore, which favor surface-level imitation of references rather than genuine gains in faithfulness or alignment with human preferences. We propose a novel framework that couples explicit cognitive-style reasoning with reward-based optimization for multi-role dialogue summarization. Our method first distills structured reasoning traces (e.g., step-by-step inferences and intermediate reflections) from a large teacher model and uses them as auxiliary supervision to initialize a reasoning-aware summarizer via staged supervised fine-tuning. It then applies GRPO with a dual-principle reward that blends metric-based signals with human-aligned criteria targeting key information coverage, implicit inference, factual faithfulness, and conciseness. Experiments on multilingual multi-role dialogue benchmarks show that our method matches strong baselines on ROUGE and BERTScore. Specifically, results on CSDS confirm the framework's stability in semantic consistency, while in-depth analysis on SAMSum demonstrates clear gains in factual faithfulness and model-based preference alignment. These findings underscore the value of reasoning-aware and preference-aware training for reliable dialogue summarization. Checkpoints and datasets are available at https://huggingface.co/collections/NebulaPixel/summorchestra-multirole-summary. --- ### Persona-Based Requirements Engineering for Explainable Multi-Agent Educational Systems: A Scenario Simulator for Clinical Reasoning Training Authors: Weibing Zheng, Laurah Turner, Jess Kropczynski, Matthew Kelleher, Murat Ozer, Shane Halse Published: 2026-04-19 Categories: cs.SE, cs.AI, cs.ET, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2604.17186v1 As Artificial Intelligence (AI) and Agentic AI become increasingly integrated across sectors such as education and healthcare, it is critical to ensure that Multi-Agent Education System (MAES) is explainable from the early stages of requirements engineering (RE) within the AI software development lifecycle. Explainability is essential to build trust, promote transparency, and enable effective human-AI collaboration. Although personas are well-established in human-computer interaction to represent users and capture their needs and behaviors, their role in RE for explainable MAES remains underexplored. This paper proposes a human-first, persona-driven, explainable MAES RE framework and demonstrates the framework through a MAES for clinical reasoning training. The framework integrates personas and user stories throughout the RE process to capture the needs, goals, and interactions of various stakeholders, including medical educators, medical students, AI patient agent, and clinical agents (physical exam agent, diagnostic agent, clinical intervention agent, supervisor agent, evaluation agent). The goals, underlying models, and knowledge base shape agent interactions and inform explainability requirements that guided the clinical reasoning training of medical students. A post-usage survey found that more than 78\% of medical students reported that MAES improved their clinical reasoning skills. These findings demonstrate that RE based on persona effectively connects technical requirements with non-technical medical students from a human-centered approach, ensuring that explainable MAES are trustworthy, interpretable, and aligned with authentic clinical scenarios from the early stages of the AI system engineering. The partial MAES for the clinical scenario simulator is~\href{https://github.com/2sigmaEdTech/MAS/}{open sourced here}. --- ### SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair Authors: Yifan Zhang, Jieyu Li, Kexin Pei, Yu Huang, Kevin Leach Published: 2026-04-19 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2604.17184v2 Large Language Models (LLMs) can generate plausible code patches, but plausibility is not enough for automated repair: a patch must compile, pass tests, and remove the target vulnerability. We present SynthFix, a neuro-symbolic repair framework that combines supervised repair learning with compiler-informed feedback. During training, a lightweight router selects between Supervised Fine-Tuning (SFT) for common repair patterns and Reward Fine-Tuning (RFT) for examples that benefit from symbolic feedback. The reward combines static structure, lint/compile checks, security scanning, and public execution tests where available; at inference time, the same evidence guides best-of-K candidate selection under a greedy floor. Across five code LLMs (1.3B-7B) on pyrepair, CodeFlaws, and SVEN, SynthFix improves deployable repair metrics over SFT-only and RFT-only baselines, with relative gains up to 54 percent in functional correctness and 14 percent in security clearance. Our code and data are available at https://github.com/CoderDoge1108/SynthFix. --- ### A Model and Estimation of the Bitcoin Transaction Fee Authors: Daniel Aronoff, Kristian Praizner, Armin Sabouri Published: 2026-04-19 Categories: cs.CE, cs.LG, econ.EM arXiv: https://arxiv.org/abs/2604.17183v1 Bitcoin transaction fees will become more important as the block subsidy declines, but fee formation is hard to study with blockchain data alone because the relevant queueing environment is unobserved. We develop and estimate a structural model of Bitcoin fee choice that treats the mempool as a market for scarce blockspace. We assemble a novel, high-frequency mempool panel, from a self-run Bitcoin node that records transaction arrivals, exits, block inclusion, fee-bumping events, and congestion snapshots. We characterize the fee market as a Vickery-Clarke-Groves mechanism and derive an equation to estimate fees. In the first-stage we estimate a monotone delay technology linking fee-rate priority and network state to expected confirmation delay. We then estimate how fees respond to that delay technology and to transaction characteristics. We find that congestion is the main determinant of delay; that the marginal value of priority is priced in fees, which is increasing in the gradient of confirmation time reduction per movement up in the fee queue; and that transactor choice of RBF, CPFP, and block conditions have economically important effects on fees. --- ### Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy Authors: Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri Published: 2026-04-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.17182v1 In LLM-based code generation, multiple code candidates are often generated in parallel from the same prompt -- for example, in best-of-N sampling or multi-candidate code completion. These requests can share KV caches through a common prefix, yet the extent to which their Mixture-of-Experts (MoE) expert routing overlaps, and how this overlap varies across layers, remains insufficiently understood. We study Qwen3.5-35B-A3B-FP8 (256 routed experts, top-8) by performing tree-search-based branching generation from a shared prefix (851 completed codes, temperature 0.7) and analyzing the results with a compiler-output-based alignment (gcc -S -O0 assembly) that controls for token-identity confounds. Our findings are threefold: (1) At positions where both sequences generated the same token, Jaccard similarity reaches 0.649 (40x random), while even at positions with different tokens it remains 0.175 (11x random). (2) A layer-wise decomposition reveals a crossing pattern: same-token routing similarity exceeds different-token similarity across all layers, but dips in the middle layers (L14-20), while different-token similarity peaks in the middle layers at 14x random. (3) In tree-search code generation, 67% of successfully compiled codes concentrate in the top three assembly-equivalent groups, and 99.6% of within-group differences consist of comments and blank lines. We show that diversity in top-P search, including beam search, poses a significant challenge. These results refine the "context-independent routing" claim of prior work through layer-wise decomposition and suggest opportunities for improving search efficiency in LLM code generation. --- ### Decentralised Trust and Security Mechanisms for IoT Networks at the Edge: A Comprehensive Review Authors: Khandoker Ashik Uz Zaman, Mahdi H. Miraz, Mohammed N. M. Ali Published: 2026-04-19 Categories: cs.CR, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2604.17179v1 INTRODUCTION: The proliferation of the amalgamation of IoT and edge computing has increased the demand for decentralised trust and security mechanisms capable of operating across heterogeneous and resource-limited devices. Approaches such as federated learning, Zero Trust architectures, lightweight blockchain and distributed neural models offer alternatives to centralised control. OBJECTIVES: This review examines various state-of-the-art decentralised mechanisms and evaluates their effectiveness in terms of securing IoT networks at the edge. METHODS: Thirty recent studies were analysed to compare how decentralised architectures establish trust, support secure communication and enable intrusion and anomaly detection. Frameworks, such as DFGL-LZTA, SecFedDNN and COSIER were assessed. RESULTS: Decentralised designs enhance privacy, reduce single points of failure and improve adaptive threat response, though challenges remain in scalability, efficiency and interoperability. CONCLUSION: The study identifies key considerations and future research needs for building secure and resilient trust-aware IoT edge ecosystems. --- ### Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation Authors: Lin Zhong, Renjin Zhu, Shujuan Ma, Jinhao Cui, Lingzhi Wang, Hao Chen, Qing Liao Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17178v1 Emotional Support Conversation (ESC) plays a critical role in mental health assistance by providing accessible psychological support in real-world applications. Large Language Models (LLMs) have shown strong empathetic abilities in ESC tasks. Yet, existing methods overlook the issue of cognitive distortions in help-seekers' expressions. As a result, current models can only provide basic emotional comfort, rather than helping help-seekers address their psychological distress at a deeper cognitive level. To address this challenge, we construct the CogBiasESC dataset, the first dataset that expands existing ESC datasets by adding labels for cognitive distortions, includes their type, intensity, and safe risk level. Furthermore, we propose the Cognitive Policy-driven Large Language Model framework (CoPoLLM) to enhance LLMs' ability to diagnose and intervene cognitive distortions in help-seekers. We also analyze the safety advantages of CoPoLLM from a theoretical perspective. Experimental results show that CoPoLLM significantly outperforms 15 state-of-the-art baselines in terms of distortion diagnosis accuracy, intervention strategy effectiveness, and safety risk control. --- ### Decomposing the Depth Profile of Fine-Tuning Authors: Jayadev Billa Published: 2026-04-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17177v1 Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property of the model or the magnitude of gradient flow has not been tested directly. We measure this profile across 240 fine-tuning runs spanning 15 models in four architecture families (encoder and decoder transformers, a state-space model, and an RNN) at scales from 125M to 6.9B parameters. Representational change concentrates in output-proximal layers in every standard-training run except one. We apply a per-layer control that equalizes $\|ΔW\|/\|W\|$ across layers after each optimizer step. Under this control, the profile persists in some conditions and collapses in others. At 125M--350M, sequential-block architectures (BERT, OPT, GPT-2) retain the slope across tested objectives while parallel-block architectures (Pythia, CodeGen) retain it only for causal-language-modeling objectives. This architectural distinction narrows at 1.3B--1.4B, where both block types show positive equal-step slopes for CausalLM. Under standard training, profile shape is described by two additional axes: steepness tracks a training-free objective distance at initialization, and profile width is dominated by architecture. We treat the locality gradient, the depthwise slope of representational change, as a composite phenomenon whose components are scale-dependent. --- ### Intent-aligned Autonomous Spacecraft Guidance via Reasoning Models Authors: Yuji Takubo, Simone D'Amico Published: 2026-04-19 Categories: eess.SY, cs.AI, math.OC arXiv: https://arxiv.org/abs/2604.17176v2 Future spacecraft operations require autonomy that can interpret high-level mission intent while preserving safety. However, existing trajectory optimization still relies heavily on expert-crafted formulations and does not support intent-conditioned decision-making. This paper proposes an intent-aligned spacecraft guidance framework that links high-level reasoning and safe trajectory optimization through explicit intermediate abstractions, based on behavior sequences and waypoint constraints. A foundation model first predicts an intent-aligned behavior plan, a waypoint generation model then converts it into waypoint constraints, and the safe trajectory is computed via optimization. This decomposition enables scalable supervision without sacrificing safety. Numerical experiments in close-proximity operation scenarios demonstrate that the proposed pipeline achieves over 90\% SCP convergence and yields a $1.5\times$ higher rate of generating trajectories that satisfy the top intent-prioritized performance criteria than heuristic decision-making. These results support the use of intermediate behavior abstraction as a practical interface between foundation-model reasoning and safety-critical onboard spacecraft autonomy. --- ### RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design Authors: Meghana Kshirsagar, Allen Nie, Ching-An Cheng, Fanglei Xue, Rahul Dodhia, Juan Lavista Ferres, Kevin K. Yang, Frank DiMaio Published: 2026-04-19 Categories: cs.LG, cs.AI, q-bio.BM arXiv: https://arxiv.org/abs/2604.17175v2 We introduce RosettaSearch, an inference-time multi-objective optimization approach for backbone conditioned protein sequence design. We use large language models (LLMs) as a generative optimizer within a search algorithm capable of controlled exploration and exploitation, using rewards computed from RosettaFold3, a structure prediction model, under a strict computational budget. In a large-scale evaluation, we apply RosettaSearch to 400 suboptimal sequences generated by LigandMPNN (a state-of-the-art model trained for protein sequence design), recovering high-fidelity designs that LigandMPNN's single-pass decoding fails to produce. RosettaSearch's designs show improvements in structural fidelity metrics ranging between 18% to 68%, translating to a 2.5x improvement in design success rate. We observe that these gains in success rate are robust when RosettaSearch-designed sequences are evaluated with an independent structure prediction oracle (Chai-1) and generalize across two distinct LLM families (o4-mini and Gemini-3), with performance scaling consistently with reasoning capability. We further demonstrate that RosettaSearch improves the sequence fidelity of ProteinMPNN designs for de novo backbones from the Dayhoff atlas, showing that the approach generalizes beyond native protein structures to computationally generated backbones. We also demonstrate a multi-modal extension of RosettaSearch with vision-language models, where images of predicted protein structures are used as feedback to incorporate structural context to guide protein sequence generation. To our knowledge, this is the first large-scale demonstration that LLMs can serve as effective generative optimizers for backbone-conditioned protein sequence design, yielding systematic gains without any model retraining. --- ### Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding Authors: Lin Zhong, Siyu Zhu, Zizhen Yuan, Jinhao Cui, Xinyang Zhao, Lingzhi Wang, Hao Chen, Qing Liao Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17174v1 Modeling human cognitive states is essential for advanced artificial intelligence. Existing Large Language Models (LLMs) mainly address isolated tasks such as emotion analysis or stance detection, and fail to capture interactions among cognitive dimensions defined in psychology, including emotion, thinking style, stance, and intention. To bridge this gap, we construct CognitiveBench, the first benchmark with unified annotations across the above four dimensions. Experiments on CognitiveBench show that although LLMs perform well on single dimension tasks, their performance drops sharply in joint multi-dimensional modeling. Using Gromov $δ$-hyperbolicity analysis, we find that CognitiveBench exhibits a strong hierarchical structure. We attribute the performance bottleneck to ``Cognitive Crowding'', where hierarchical cognitive states require exponential representational space, while the Euclidean space of LLMs grows only polynomially, causing representation overlap and degraded performance. To address this mismatch, we propose HyCoLLM, which models cognitive states in hyperbolic space and aligns LLM representations via Hyperbolic Guided Alignment Tuning. Results show that HyCoLLM substantially improves multi-dimensional cognitive understanding, allowing 8B parameter model to outperform strong baselines, including GPT-4o. --- ### UCCL-Zip: Lossless Compression Supercharged GPU Communication Authors: Shuang Ma, Chon Lam Lao, Zhiying Xu, Zhuang Wang, Ziming Mao, Delong Meng, Jia Zhen, Jun Wu, Ion Stoica, Yida Wang, Yang Zhou Published: 2026-04-19 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2604.17172v2 The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volume via quantization or lossy compression, these approaches introduce numerical errors that can degrade convergence, accuracy, and stability. We present UCCL-Zip, a unified design that integrates lossless compression directly into GPU communication primitives. UCCL-Zip supports both point-to-point (P2P) and collective communication without modifying user-facing APIs or compromising numerical correctness. For P2P communication, Uzip-P2P employs a split-send pipeline that exposes transmissible data early and overlaps compression with communication, while preserving high GPU efficiency by operating on large data blocks. For collective communication, Uzip-NCCL integrates compression into NCCL's persistent kernel model via fused execution, eliminating redundant memory traffic and kernel launches. In real workloads, UCCL-Zip accelerates RL weight synchronization by up to 47.5% and reduces vLLM end-to-end inference latency by up to 10%, all without application changes. --- ### Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review Authors: Vaibhava Lakshmi Ravideshik, Mayank Kejriwal Published: 2026-04-18 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.28631v1 AI Scientist systems capable of autonomous research have the potential to significantly accelerate scientific discovery. However, evaluating and comparing the quality of AI-generated papers remains an open challenge. We propose and implement a rigorous benchmarking protocol using an automated peer-review system that harnesses frontier large language models to assess scientific papers across four core dimensions: originality, scientific rigor, clarity, and significance. We evaluate four leading AI Scientist frameworks: \textit{Sakana AI (v1 & v2)}, \textit{CycleResearcher}, and \textit{Data-to-Paper}. Each framework was run on a consistent set of 15 research proposals published by a commercial autonomous AI scientist company (FARS), generating 60 papers that we evaluate alongside 15 FARS benchmark papers. Using three independent LLM reviewers (GPT-5.4, Gemini, and Claude), we find that FARS benchmark papers significantly outperform all competing frameworks, achieving mean scores of 2.14--2.47 on a 1--5 scale compared to 1.00--1.87 for other systems. Notably, FARS scores are more than 2$\times$ higher than the next-best systems on Gemini and Claude evaluations. We find strong agreement among Gemini and Claude ($ρ$ = 0.907, $p < 0.001$), and both correlate extremely strongly with the synthesis score ($ρ$ = 0.961, $p < 0.001$), validating the reliability of automated evaluation. However, GPT-5.4 exhibits weaker agreement ($ρ\approx 0.32$), suggesting it evaluates papers using different criteria. These results establish the first quantitative benchmark for AI Scientist systems and demonstrate that multi-model LLM evaluation provides a scalable, consistent framework for assessing autonomous research quality. --- ### FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills Authors: Zeyu Ren, Ling Yue, Ran Li, Yishu Wang, Shengxiang Xu, Hanmo Liu, Shaowu Pan, Shimin Di Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.21596v2 Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usually discarded after execution. Existing skill libraries provide reusable executable routines, but are typically assembled offline and do not grow from the agent's own workflows. We introduce FlowEvo, a training-free framework in which workflows and skills co-evolve at inference time. FlowEvo compiles successful workflows into callable skills, stores them in a persistent bank, and uses retrieved skills either through direct execution or as context for constructing new workflows. It also tracks each skill's downstream utility and suppresses skills that cause negative transfer. Using a shared GPT-4o-mini backbone, FlowEvo achieves the highest accuracy among 8 baselines on the full standard splits of ALFWorld, HumanEval, MBPP, GSM8K, and MATH-500. On ALFWorld, it reaches 85.6%, 26.4 points above the strongest baseline, while using roughly one third as many tokens. Across 10 base models spanning 7B to 671B parameters, FlowEvo outperforms ExpeL in 49 of 50 model-dataset comparisons. Code is available at https://github.com/DEFENSE-SEU/FlowEvo. --- ### FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills Authors: Zeyu Ren, Ling Yue, Ran Li, Yishu Wang, Shengxiang Xu, Hanmo Liu, Shaowu Pan, Shimin Di Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.21596v1 Large language model agents increasingly solve complex tasks by constructing inference-time workflows that combine reasoning, tool use, and code execution. While such workflows enable flexible problem solving, the useful procedures discovered during execution are often transient: they help solve the current task but are not retained in a form that can systematically benefit future tasks. We present FlowEvo, a training-free framework that compiles successful traces into reusable skill records. Each record pairs a callable artifact with auxiliary structured guidance, and admission applies interface, replay, and safety checks where feasible. These skill records persist in a skill bank at inference time. FlowEvo is organized around three coupled mechanisms: (1)~workflow-to-skill compilation, which extracts reusable executable artifacts from successful traces; (2)~skill-to-workflow feedback, which retrieves accumulated skills to support future problem solving through either direct execution or structured context injection; and (3)~skill curation, which monitors downstream utility and suppresses skills that cause negative transfer. Through this workflow--skill--workflow feedback loop, FlowEvo enables agents to accumulate and refine task-solving capability over time without updating model parameters. Experiments on benchmarks spanning interactive environments (ALFWorld) and code/math generation (HumanEval, GSM8K) show that FlowEvo achieves the best accuracy-cost tradeoff among the evaluated baselines under our implementation settings. On ALFWorld, FlowEvo achieves an 82.8\% success rate, 23.6 percentage points above the strongest baseline, while its average token usage per episode is less than half that of the most efficient baseline. Controlled ablations confirm that each mechanism contributes to the overall result. The code is public at https://github.com/DEFENSE-SEU/FlowEvo. --- ### From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems Authors: Abhirup Dasgupta, Fernando Spadea, Oshani Seneviratne Published: 2026-04-18 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.00003v1 Personal Knowledge Graphs (PKGs) offer a privacy-preserving framework for modeling user preferences, yet constructing them from unstructured, decentralized conversational data remains a challenge. This paper bridges the gap between conversational "strings" and semantic "things" by presenting a reproducible pipeline for extracting structured user-preference triples using lightweight Large Language Models. We evaluate Qwen- and Gemma-based models on their ability to extract RDF-compliant triples linked to Wikidata identifiers from conversational data for PKG construction. Our evaluation assesses both the semantic extraction fidelity and the utility of the resulting graphs in a downstream recommendation task. We found that certain models performed well and had proportionally high downstream performance relative to their triple extraction performance. --- ### LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations Authors: Rahul Subramani Published: 2026-04-18 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.05182v1 Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered Archival aNd Temporal Episodic Retrieval Network), a lightweight memory layer that proactively archives every conversation turn and restores relevant details after compaction via hybrid retrieval -- requiring zero LLM calls and adding fewer than 25ms of latency per turn. On 94 real multi-turn conversations (1,894 ground-truth facts, human-validated at kappa=0.81), LANTERN-Rerank recovers 78.3% of verifiable facts lost to compaction, significantly outperforming a faithful reimplementation of MemGPT's LLM-driven extraction and multi-query search pipeline (72.4%; Wilcoxon p<0.0001, 95% CI (+3.1, +8.6) pp, d=0.43) at a fraction of the inference cost. Even without the reranker, base LANTERN matches or exceeds this LLM-driven baseline (p=0.005) using zero LLM calls. When four production LLMs answer fact-bearing questions using LANTERN-restored context, accuracy improves by 8.4 percentage points on average (Wilcoxon p<0.05 for each model individually), demonstrating that the recovered context is useful across diverse model architectures. We release the full evaluation framework -- paired significance tests, failure analysis, fact-type stratification, and compaction robustness analysis -- to support reproducibility and future work. --- ### Multi-Granularity Reasoning for Natural Language Inference Authors: Chunling Xi, Di Liang Published: 2026-04-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.05181v2 Natural Language Inference (NLI) is a fundamental task in natural language understanding that requires determining the logical relationship between a premise and a hypothesis. Despite the remarkable success of transformer-based pre-trained models, most existing approaches primarily rely on the final-layer token representations, which are often insufficient for capturing the complex and hierarchical semantic interactions required for effective reasoning. In particular, fine-grained lexical cues, phrasal compositions, and higher-level contextual semantics are typically entangled or diluted in a single representation space. To address these limitations, we propose a novel \emph{Multi-Granularity Reasoning Network} (MGRN) that explicitly leverages hierarchical semantic features within an interactive reasoning space. The proposed framework mimics the human cognitive process of language understanding, which naturally progresses from shallow lexical matching to deeper semantic abstraction and logical reasoning. By integrating semantic information across multiple granularities in a progressive and structured manner, MGRN is able to uncover intricate semantic relationships underlying natural language expressions. Extensive experiments on multiple public benchmarks demonstrate that MGRN consistently outperforms strong baseline models, validating the effectiveness and robustness of the proposed approach. --- ### From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment Authors: Ivo Bueno, Babette Bühler, Philipp Stark, Tim Fütterer, Ulrich Trautwein, Dorottya Demszky, Heather Hill, Enkelejda Kasneci Published: 2026-04-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.05180v1 Automated scoring models are increasingly used to assign rubric-based quality ratings to complex language performances, including classroom transcripts, yet they typically provide little insight into why a particular score is produced. We propose a general framework for sentence-level interpretability of rubric-based scoring that combines model-agnostic Shapley-value attributions with rationales generated by large language models (LLMs). Instantiated on the Quality of Feedback dimension of the CLASS framework using the NCTE corpus, the framework enables systematic comparison of fine-tuned pretrained language models (PLMs) and prompted LLMs on both scoring performance and explanation faithfulness. Across 6k annotated transcript segments, fine-tuned PLMs outperform LLMs in prediction accuracy but exhibit label compression toward mid-scale scores. Deletion-based tests show that SHAP identifies sentences that reliably drive model predictions, producing typically larger and more coherent prediction shifts than LLM-generated rationales. Cross-model analyses further reveal that SHAP attributions transfer robustly across architectures, whereas LLM rationales exert limited and inconsistent influence. Overall, the findings demonstrate that SHAP provides more faithful and transferable explanations for rubric-based scoring, and that the proposed framework offers a principled basis for evaluating both scoring models and their explanations in high-stakes educational settings and other rubric-based language assessment tasks. --- ### Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems Authors: Sungmook Woo, Hyungu Kang, Chanwoo Kim Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.05179v1 Punctuation restoration improves ASR (Automatic Speech Recognition) readability. However streaming ASR requires online decisions with limited future context. In streaming ASR, the system predicts punctuation incrementally, which makes generation-based approaches prone to latency and alignment failures under boundary-wise evaluation. This paper proposes a non-autoregressive scoring method (no free-form generation) that preserves the input transcript and makes a decision at each word boundary. Our method compares punctuation insertion hypotheses against a no-insertion baseline under a bounded K-subword-token lookahead, and calibrates decisions using a weight α and a validation-calibrated threshold τ (no parameter updates during inference). On IWSLT 2017, our scoring method achieves a 4-class macro F1 of 0.893 in the no fine-tuning setting (validation-calibrated, K=2) and 0.937 after fine-tuning (K=2), outperforming the prompt-based baseline (0.566) and a fine-tuned ELECTRA baseline (0.913) under the same lookahead budget. We analyze the impact of the lookahead budget through ablation studies on K. --- ### One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them Authors: Ali Holmov, Paul Youssef, Nandi Schoots, Christin Seifert Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28839v1 Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by output behavior, their internal mechanism remains underexplored. We investigate whether edits rely on a common mechanism, regardless of which fact is modified. Despite fact-specific weight changes, we argue that ROME and MEMIT target the same subset of weights critical for maintaining edits. To isolate this subset, we train a compact binary mask over the edited weights. The mask reverses 80% of edits on the training set and over 70% on the test set, confirming that diverse edits share a common functional structure. Our analysis reveals that the mask reverses edits by eliminating overattention in later layers. Additionally, we show that injecting the mask during editing drops editing success from 98% to 38%, demonstrating that this mechanism is necessary for edits to succeed. Our finding that edits suppress rather than overwrite knowledge explains why ROME and MEMIT fail to propagate changes to related facts. The identified common functional subspace informs detection and defense against unwanted edits. --- ### StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation Authors: Qingyu Meng, Min Chen, Dingming Liu, Yifan Mo, Yue Su, Xin Sun, Koen Hindriks, Jiahuan Pei Published: 2026-04-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.27393v1 Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligned with clinical standards in motivational interviewing (MI). We introduce StoryMI, a multi-LLM agent framework for controllable MI dialogue generation, where questionnaire-based client profiles are expanded into situational stories that provide narrative context for the dialogue. Therapist and client agents generate MI-coded utterances guided by MI codes selected by the interaction agent, while an interaction agent dynamically coordinates exchanges to control MI strategies during a multi-turn conversation. We propose a two-level evaluation protocol: lexical metrics and MI-specific measures of macro-level counseling strategies, alongside LLM-as-judge and human expert assessments. We construct a dataset of 6K simulated MI dialogues grounded in 1K questionnaire-story pairs, covering 12 MI codes and 13 symptom domains, and benchmark six open- and closed-source LLMs. Our results show that situational grounding and macro-level control can improve MI adherence and clinical plausibility, demonstrating the effectiveness of a structured multi-agent workflow for psychotherapy dialogue generation. We provide code and data for reproducibility. --- ### LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding Authors: Yifan Zhu, Yu Mi, Yue Lu, Yanchu Guan, Zhixuan Chu Published: 2026-04-18 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.22829v1 Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coarse-grained page-level retrieval, which fails to capture fine-grained semantic and layout structures in visually rich documents, thereby compromising retrieval accuracy and leading to redundant context in downstream tasks. To address these issues, we propose Layout-oriented Fine-grained Retrieval-Augmented Generation (LFRAG), a novel framework that advances multimodal RAG from page-level to block-level retrieval. We perform layout segmentation to construct semantically coherent fine-grained retrieval units and design a semantic-layout fusion encoder that integrates local semantics with global context via cross-attention. With block-level late interaction retrieval, LFRAG enables precise query-content alignment and reduces irrelevant content for downstream generation. To enable rigorous evaluation, we construct LFDocQA, a large-scale benchmark with block-level annotations spanning diverse document types, designed to assess both multimodal document retrieval and question answering with greater granularity than existing datasets. Extensive experiments on LFDocQA demonstrate that LFRAG achieves state-of-the-art performance on retrieval tasks, outperforms the best baseline by 7.20% in answer accuracy, and reduces token consumption by 73.07% in generation tasks, confirming LFRAG as an accurate and efficient framework for multimodal RAG over visually rich documents. Our code and datasets will be released soon. --- ### HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine Authors: Brandon Dent Published: 2026-04-18 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.21496v1 Frontier language models are being deployed into clinical workflows faster than the infrastructure to evaluate them safely. Static medical-QA benchmarks miss the failure modes that matter in emergency medicine: trajectory-level safety collapse, tool misuse, and capitulation under sustained clinical pressure. We present HealthCraft, the first public reinforcement-learning environment that rewards trajectory-level safety under realistic emergency-medicine conditions, adapted from Corecraft. It is built on a FHIR R4 world state with 14 entity types and 3,987 seed entities, exposes 24 MCP tools, and defines a dual-layer rubric that zeroes reward whenever any safety-critical criterion is violated. We release 195 tasks across six categories, graded against 2,255 binary criteria (515 safety-critical); a post-hoc 10-task negative-class slate extends this to 205 tasks and 2,337 criteria. V8 results on two frontier models show Claude Opus 4.6 at Pass@1 24.8% (21.5-28.4) and GPT-5.4 at 12.6% (10.2-15.6), with safety-failure rates of 27.5% and 34.0%. On multi-step workflows - the closest proxy to real emergency care - performance collapses to near zero (Claude 1.0%, GPT-5.4 0.0%) despite partial competence on individual steps. Six infrastructure bugs fixed between pilots v2 and v8 re-ordered which model "looks stronger," evidence that infrastructure fidelity is part of the measurement. A deterministic LLM-judge overlay bounds evaluator noise, and a 60-run negative-class smoke pilot shows the reward signal is not drop-in training-safe: restraint criteria pass at 0.929 prevalence, a gameability an eval harness can tolerate but a training reward cannot. We scaffold coupling to a Megatron+SGLang+GRPO loop per Corecraft Section 5.2 and leave training-reward ablations as future work. Environment, tasks, rubrics, and harness are released under Apache 2.0. --- ### Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning Authors: Isabella Luong, Joyee Chen, Sankalpa Ghose, David Williams-King, Linh Le, Allen Lu Published: 2026-04-18 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16301v4 Evaluating animal welfare reasoning in LLMs remains an open challenge despite rapid deployment in consumer and professional contexts where welfare considerations appear implicitly in everyday queries. Existing benchmarks such as AnimalHarmBench evaluate this through single-turn, explicitly framed questions, measuring whether models avoid harmful content when directly asked. This approach overlooks two failure modes: alignment degradation under sustained adversarial pressure, and moral sensitivity (whether a model spontaneously surfaces welfare stakes in everyday queries). To fill this gap, we construct MANTA, a benchmark of 1,088 five-turn conversations progressing from an implicit Turn-1 scenario through an explicit welfare prompt to three adversarial pressure rounds drawn from a five-type taxonomy: Social, Cultural, Economic, Pragmatic, and Epistemic. We score conversations on two dimensions: Animal Welfare Value Stability (AWVS, primary) and Animal Welfare Moral Sensitivity (AWMS, diagnostic). We evaluate seven frontier models: Claude Opus 4.7, GPT-5.5, DeepSeek V4, Llama 3.3 70B, Mistral Small, Grok 4.3, and Gemini 3.1 Flash Lite. Multi-turn evaluation captures behavior single-turn benchmarks miss: 4 of 7 models change rank relative to Turn 1 moral-sensitivity scores", including Gemini Flash Lite, which drops from fifth on AWMS to last on AWVS. AWMS and AWVS are positively but imperfectly correlated, suggesting moral-sensitivity tests capture a stable but incomplete component of model behavior under pressure. MANTA also enables a species-by-pressure interaction matrix unavailable to prior benchmarks, showing welfare robustness depends jointly on the animal and pressure applied; companion animals score above wild animals, which score above farmed animals and invertebrates. We release the dataset, scripted pressure plans, judge prompts, and analysis code. --- ### Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning Authors: Isabella Luong, Joyee Chen, Sankalpa Ghose, David Williams-King, Linh Le, Allen Lu Published: 2026-04-18 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16301v3 Evaluating animal welfare reasoning in LLMs remains an open challenge despite rapid deployment in consumer and professional contexts where welfare considerations appear implicitly in everyday queries. Existing benchmarks such as AnimalHarmBench evaluate this through single-turn, explicitly framed questions, measuring whether models avoid harmful content when directly asked. This approach overlooks two failure modes: alignment degradation under sustained adversarial pressure, and moral sensitivity (whether a model spontaneously surfaces welfare stakes in everyday queries). To fill this gap, we construct MANTA, a benchmark of 1,088 five-turn conversations progressing from an implicit Turn-1 scenario through an explicit welfare prompt to three adversarial pressure rounds drawn from a five-type taxonomy: Social, Cultural, Economic, Pragmatic, and Epistemic. We score conversations on two dimensions: Animal Welfare Value Stability (AWVS, primary) and Animal Welfare Moral Sensitivity (AWMS, diagnostic). We evaluate seven frontier models: Claude Opus 4.7, GPT-5.5, DeepSeek V4, Llama 3.3 70B, Mistral Small, Grok 4.3, and Gemini 3.1 Flash Lite. Multi-turn evaluation captures behavior single-turn benchmarks miss: 4 of 7 models change rank relative to Turn 1 scores, including Gemini Flash Lite, which drops from fifth on AWMS to last on AWVS. AWMS and AWVS are positively but imperfectly correlated, suggesting moral-recognition tests capture a stable but incomplete component of model behavior under pressure. MANTA also enables a species-by-pressure interaction matrix unavailable to prior benchmarks, showing welfare robustness depends jointly on the animal and pressure applied; companion animals score above wild animals, which score above farmed animals and invertebrates. We release the dataset, scripted pressure plans, judge prompts, and analysis code. --- ### Spectral Analysis of Fake News Propagation Authors: Weibin Cai, Reza Zafarani Published: 2026-04-18 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2605.13861v2 How can we systematically represent the propagation of information? The propagation structure of fake news has been shown to be an important cue for detecting it; yet, existing propagation-based fake news detection methods have mainly relied on ad hoc topological features, and a unified view of cascade patterns is still lacking. To address this, we study news propagation from a spectral view by connecting graph spectra to propagation-related structural properties through rigorous spectral bounds. We introduce several new bounds and integrate them with existing bounds into a unified spectral representation of information propagation. We then use these spectral bounds for downstream classification and design a discrete structural optimization framework to interpret learned propagation patterns. For efficient optimization, we rely on a first-order perturbation approximation and consider both score-guided and bound-guided objectives. Experiments on real-world data reveal meaningful spectral differences between fake and real news, competitive classification performance, and interpretable evolution trajectories from structural optimization. The findings demonstrate the value of spectral analysis for understanding and modeling information propagation. --- ### GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning Authors: Wenjin Li, Jiaming Cui Published: 2026-04-18 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.06671v1 Large Language Models (LLMs) have demonstrated strong potential for many mathematical problems. However, their performance on graph algorithmic tasks is still unsatisfying, since graphs are naturally more complex in topology and often require systematic multi-step reasoning, especially on larger graphs. Motivated by this gap, we propose GraphDC, a Divide-and-Conquer multi-agent framework for scalable graph algorithm reasoning. Specifically, inspired by Divide-and-Conquer design, GraphDC decomposes an input graph into smaller subgraphs, assigns each subgraph to a specialized agent for local reasoning, and uses a master agent to integrate the local outputs with inter-subgraph information to produce the final solution. This hierarchical design reduces the reasoning burden on individual agents, alleviates computational bottlenecks, and improves robustness on large graph instances. Extensive experiments show that GraphDC consistently outperforms existing methods on graph algorithm reasoning across diverse tasks and scales, especially on larger instances where direct end-to-end reasoning is less reliable. --- ### Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms Authors: Bo Wang, Jia Ni, Mengnan Zhao, Zhan Qin, Kui Ren Published: 2026-04-18 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.05224v1 The unauthorized use of personal data in model training has emerged as a growing privacy threat. Unlearnable examples (UEs) address this issue by embedding imperceptible perturbations into benign examples to obstruct feature learning. However, existing studies mainly evaluate UEs under from-scratch training settings, leaving their behavior under the widely adopted pretraining-finetuning (PF) paradigm largely unexplored. In this work, we provide the first systematic investigation of unlearnable examples across diverse training paradigms. Our analysis reveals that loading and freezing pretrained weights significantly weakens the effectiveness of existing UEs methods. We further explain these findings through semantic filtering: while UEs tend to induce models to overfit non-semantic noise, thereby weakening their semantic extraction capabilities, under the PF paradigm, frozen shallow layers preserve data semantics, effectively filtering out distracting information like unlearnable noise. Guided by these insights, we propose a hierarchical deception strategy, Shallow Semantic Camouflage (SSC), that confines the generation process to a semantically valid subspace, aiming to bypass the semantic suppression introduced by pretrained weights. Extensive experiments demonstrate that our method consistently preserves data unlearnability even under challenging training paradigms, such as shallow-layer freezing and semantic-focused pretraining (SF-Pretrain), bridging the critical gap in pretrain-based unlearnable learning. --- ### Structural Instability of Feature Composition Authors: Yunpeng Zhou Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.05223v1 Sparse Autoencoders (SAEs) have emerged as a powerful paradigm for disentangling feature superposition in transformer-based architectures, enabling precise control via activation steering. However, the theoretical foundations of compositional steering -- the simultaneous activation of distinct semantic latents -- remain under-explored. The prevailing Linear Representation Hypothesis often abstracts away non-linear interference effects that arise in overcomplete dictionaries. We present a geometric framework for analyzing the instability of feature unions. Modeling the activation space as a high-dimensional sparse cone manifold, we derive an asymptotic compositional-collapse threshold under a spherical dictionary model, characterized by the Gaussian mean width (statistical dimension) of the signal cone. We further show that, in the high-bias regime, ReLU rectification converts microscopic correlation-induced variance fluctuations into a systematic drift that accumulates under composition, yielding interference growth consistent with a ratchet effect. We validate the predicted scaling trends on structured semantic features extracted from CLEVR, where hierarchical correlations accelerate the transition relative to random baselines. Together, our results highlight geometric constraints on the scalability of union-based steering and motivate composition mechanisms that explicitly manage interference beyond naive linear superposition. ---