# Research Papers — 2026-06 · bundle page 86 of 260 > Full-text markdown of papers #4251–4300 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/86 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/85.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/87.md) ### WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware Authors: Jiamu Zhang, Liang Wu, Mayank Darbari, Liangjie Hong Published: 2026-06-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21868v1 Modern Mixture-of-Experts (MoE) models place most of their parameters in expert layers, yet only a small fraction of those experts are used for any token. The unused weights must still be stored where the GPU can reach them. On commodity GPUs the common fix is layer-level CPU offloading, which keeps memory low but streams all of a layer's experts across PCIe on every forward pass, losing much of MoE's sparsity benefit. We cast low-resource MoE serving as a working-set management problem on the GPU: routed expert weights and the key-value (KV) cache are two streams of memory demand competing for limited VRAM. We realize this in WiSP (Working-Set Paging), a routing-aware expert pager that plugs into an unmodified serving engine with byte-identical outputs. Keeping resident only the experts a workload reuses, WiSP reaches up to 1.95x the decode throughput of static offload at the same memory budget when the model does not fit. We also find that prefetching experts from predicted routing helps little in single-stream decode: the bottleneck is PCIe bandwidth, not prediction accuracy. This shifts the question from prefetching to allocation: how should VRAM be split between experts and the KV cache? We answer with MV-WSA (Marginal-Value Working-Set Allocation), which equalizes marginal latency benefit per byte subject to a KV admission floor. MV-WSA runs either as an offline configurator or as an online controller that resizes both pools while serving. In real serving the offline configurator is the only policy we test that does well on both prefill and decode; in trace-driven simulation it stays within a few percent of a per-workflow oracle while fixed splits are about 20% worse. The online controller adds a further 1.20x without changing model outputs. --- ### ForEx: A Formal Verification Framework for Explainable Reasoning in Logical Fallacy Detection and Annotation Authors: Pei-Cing Huang, Chienyu Liu, Chan Hsu, Ci-Siang Chen, Pei-Ju Lee, Yihuang Kang Published: 2026-06-20 Categories: cs.AI, cs.CL, cs.SC arXiv: https://arxiv.org/abs/2606.21867v1 Current evaluations of Large Language Models (LLMs) on logical fallacy detection focus on predicted labels, but do not establish whether those labels are supported by the reasoning the models provide. We propose ForEx (Formal Verification for Explainable Reasoning), a framework that translates LLM-generated explanations into Lean4 and verifies whether the translated rationale is derivable under encoded premises, not the logical validity of the original natural language argument. To distinguish prediction outcomes from the formal status of the supporting reasoning, we introduce the LLM Argument Verification Matrix, which separates label consistency from formal verification status. Experiments on LOGIC-Climate show that over 90% of LLM outputs can be translated into formal reasoning chains that pass verification, while agreement with human annotations remains around 20%. These results expose a systematic gap between formal derivability and label agreement, a distinction invisible to prediction-based metrics. ForEx moves LLM evaluation beyond label correctness toward machine-checkable analysis of formalized reasoning chains. --- ### Prompt-Calibrated SAM 3 for Open-Vocabulary Remote Sensing Semantic Segmentation Authors: Yanghui Song, Nanqing Liu, Haonan Yin, Yingjie Gao, Chengfu Yang, Qi Ming Published: 2026-06-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21863v2 Open-vocabulary semantic segmentation (OVSS) in remote sensing images aims to segment categories beyond a fixed label space. Recent SAM 3-based methods provide a promising training-free foundation, yet three key issues remain: (1) a single class-name prompt lacks sufficient semantic coverage for complex remote sensing categories; (2) expanding each category into multiple prompts introduces redundant online text encoding; and (3) directly aggregating multiple prompt responses propagates noisy activations into the final prediction. To address these issues, we propose ProC-SAM3, which calibrates SAM 3's prompt interface for remote sensing OVSS from three complementary aspects. First, we construct an offline prompt pool where a Category Matcher groups MLLM-generated candidates into per-category sets, and Expansion Constraints further refine each set using category-specific prior knowledge. Second, the resulting text embeddings are cached and reused across all test images, eliminating repeated text encoding. Third, we introduce Presence-Guided Residual Fusion to gate unreliable decoder outputs by prompt presence and confidence, followed by peak-preserving class aggregation that retains fine-grained activations for small and sparse objects. Experiments on eight benchmarks show that ProC-SAM3 achieves an average mIoU of 56.1%, outperforming the previous best training-free method by 3.9 percentage points. Code will be available at https://github.com/YanghuiSong/ProC-SAM3. --- ### Research Method Usage across Academic Ages in Library and Information Science: An Empirical Study (1990-2023) Authors: Chengzhi Zhang, Jiayi Hao, Yi Mao Published: 2026-06-20 Categories: cs.DL, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.21862v1 Academic age critically shapes career development, influencing research behavior, output volume, and methodological choices. Analyzing method variation across academic ages offers a new theoretical lens on scholarly evolution and provides early-career researchers with practical guidance for method selection. A corpus of 26,677 articles published 1990-2023 in 14 authoritative Library and Information Science journals was compiled. The CogFT model automatically classified the research methods embedded in these articles, and Top2Vec generated the topic model. This process resulted in a comprehensive dataset linking research methods with topics. Author-name disambiguation enabled calculation of each scholar's academic age. Popularity and Shannon diversity indices for methods, together with topic diversity, were compared across academic age groups. Results reveal dynamic methodological trends: the share of theoretical approaches declined gradually, whereas experimental and bibliometric methods gained ground. Method popularity differs significantly among cohorts. Mid-career scholars exhibit the highest method diversity; late-career scholars the lowest. --- ### Zero-Shot Vision-Language Models for Classroom Engagement Recognition: A Benchmark Study of Prompt Sensitivity and Cross-Dataset Generalization Authors: Aman Goyal, Kshama Nitin Shah, Kemmannu Vineet Venkatesh Rao Published: 2026-06-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21861v1 Automated classroom engagement recognition holds substantial promise for scalable learning analytics, yet the suitability of modern Vision-Language Models (VLMs) for this task under zero-shot conditions remains largely unexplored. We present a systematic benchmark that evaluates five widely-used VLMs: CLIP, BLIP-VQA, GPT-4o, LLaVA-1.5-7B, and Qwen2.5VL-7B-Instruct across two complementary educational datasets: DAiSEE, an individual-student video dataset (300 sampled test clips), and the Student Classroom Behaviour dataset (SCB, 1,168 scene-level images). Each model is probed with three prompt variants spanning minimal, rubric-anchored, and chain-of-thought designs. Our experiments reveal three primary failure modes of zero-shot VLMs for engagement recognition: (1) near-random performance on individual students, with Cohen's kappa never exceeding 0.10 on DAiSEE; (2) severe class collapse, where models assign 85-100% of predictions to a single engagement level regardless of visual content; and (3) extreme prompt sensitivity, with accuracy swings of up to 32 percentage points on identical images depending solely on prompt phrasing. Remarkably, scene-level classification on SCB is substantially more tractable: CLIP and GPT-4o achieve kappa approximately 0.60 when prompted with behaviorally-grounded rubrics. We also document a practical barrier for deployment: GPT-4o's safety filters reject 98% of chain-of-thought requests involving individual student faces. Our findings provide a calibrated baseline and surface critical design considerations for the use of VLMs in educational observation systems. --- ### Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents Authors: Wangxuan Fan, Xiaoyu Nie, Zhongxiang Dai Published: 2026-06-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.21856v1 The increasing deployment of large language model (LLM) agents in collaborative workflows demands robust multi-user, multi-principal interaction mechanisms capable of enforcing access permissions, resolving authoritative conflicts, and preventing unauthorized data disclosure. However, a fundamental mismatch exists between the single-user training paradigm of contemporary LLMs and the hard constraints required for multi-principal governance, rendering probabilistic, prompt-based safeguards vulnerable under multi-turn adversarial interactions.Our key insight is that governance constraints -- who is authorized, what is restricted, and whose instructions take precedence -- are deterministic runtime variables that should be enforced by execution hooks rather than entrusted to the LLM. We present \textbf{Harness-MU}, the first model-agnostic, zero-tuning infrastructure framework for multi-user LLM agents. By decoupling language generation from safety orchestration, Harness-MU guarantees unbreakable permission boundaries while maximizing compliant demand satisfaction. Across four frontier open-weight and proprietary models on the \textit{Muses-Bench} benchmark, Harness-MU achieves the goal of privacy preservation across all access-control attacks, outperforming the standard baseline by 0.28--0.39 in utility score and improving instruction-following accuracy by up to 48.9 percentage points. Harness-MU advances the philosophy of \textit{Harness Engineering}, establishing that systematic infrastructure is essential for solving LLM multi-principal governance challenges. The code and data are available at https://github.com/YuanJrShiuan/Harness-MulUser. --- ### TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation Authors: Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Linh Ngo Van, Nguyen Thi Ngoc Diep, Thien Huu Nguyen, Trung Le Published: 2026-06-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21851v1 Knowledge Distillation (KD) has established itself as a pivotal technique for compressing large pre-trained language models. However, existing methods that force a student to strictly mimic the teacher's sentence embeddings or internal features often incur prohibitive computational costs and yield suboptimal performance due to the inherent capacity gap. To address these challenges, we propose TALAS (Teacher-Anchored Layer Alignment with Sharpness-aware minimization), a unified framework that synergizes hierarchical (multi-layer) alignment with robust optimization. First, we introduce a Teacher-Anchored mechanism that selectively distills final sentence embeddings only into the student's upper layers, thereby reducing overhead while respecting capacity constraints. Second, we bridge the semantic gap in lower layers via Layer-Aligned Self-Distillation, which propagates knowledge top-down using internal geometric relational constraints in the embedding space. Finally, to prevent the student from memorizing point-wise teacher noise, we integrate Adaptive Sharpness-Aware Minimization (ASAM) into the training objective, guiding the model towards flat minima for enhanced generalization. Empirical results on standard sentence embedding benchmarks demonstrate that TALAS consistently outperforms strong distillation baselines while achieving superior training efficiency in terms of computational cost and memory footprint. --- ### Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers Authors: Xin Gao, Xingming Xu Published: 2026-06-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.21848v3 Transformer architectures form the foundation of modern natural language processing, yet the Key-Value (KV) cache introduces substantial memory and bandwidth overhead during long-context generation, increasingly bottlenecking large-scale deployment. We propose Keyless Attention, a novel attention mechanism that replaces the conventional key projection with a dedicated value-space routing projection, eliminating key representations from the attention computation entirely and yielding a Value-Only Cache that reduces KV-cache memory by 50% while improving decode throughput. Experiments across multiple models and architectures demonstrate that Keyless Attention achieves comparable perplexity and downstream task performance to standard QKV attention, while consistently reducing KV-cache memory by 50%. Furthermore, Keyless Attention exhibits slower validation loss degradation after the best epoch, indicating improved robustness against overfitting. Ablation studies confirm that the dedicated value-space routing projection is critical, with Keyless Attention outperforming KV-sharing methods that eliminate the key cache without replacing its routing role. Experiments in the pretraining regime further confirm the viability of Keyless Attention in industrial settings. --- ### UniRank: Unified Rank Allocation for Low-Rank LLM Compression Authors: Chao Han, Yongjie Du, Junjie Tan, Zihao Xuan Published: 2026-06-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.21847v2 Low-rank decomposition is a promising compression paradigm for large language models (LLMs), yet its effectiveness hinges on rank budget allocation across weight matrices: uniform or hand-crafted rules ignore module-wise importance, while learning-based allocation incurs substantial training overhead. We formulate rank allocation as a global sorting-and-truncation pipeline that scores every singular component by combining local singular energy with global functional importance, estimated via layer-wise input--output cosine similarity on a tiny calibration set. We show, both geometrically and empirically, that high input--output cosine similarity implies low effective rank. We further propose rank-preserving fine-tuning (RPFT), which adapts only a small subset of retained singular components so that the allocated rank stays bounded without re-decomposition. Experimental results show that UniRank cuts zero-shot perplexity by up to 50\%, improves average reasoning accuracy by 3.0\% over LoRAP at 25\% sparsity, and boosts four SVD-based decomposition methods as a plug-and-play module. --- ### UniRank: Unified Rank Allocation for Low-Rank LLM Compression Authors: Chao Han, Haozhe Hu, Fei Ma, Wei Zhang, Xiaoyu Shen Published: 2026-06-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.21847v1 Low-rank decomposition serves as a promising compression paradigm for large language models, however, rank allocation remains challenging: manual rules lack generalizability, and learning-based approaches incur heavy computational overhead. To address these issues, we formulate global low-rank allocation as a sorting-and-truncation pipeline, and score each singular component via dual criteria: \textbf{Local} singular energy ratio that quantifies the intrinsic importance within the decomposed parameter matrix and \textbf{Global} functional importance (measured by input-output cosine similarity) that evaluates the functional significance of decomposed modules. We verify the strong correlation between high input-output cosine similarity and low effective rank through geometric interpretation and experimental validation. Furthermore, we propose rank-preserving fine-tuning, which performs direct LoRA tuning on decomposed weights and avoids extra information loss caused by re-truncation in conventional merging pipelines. Empirical results confirm that our method delivers sustained performance enhancements when combined with models featuring distinct decomposition schemes, model sizes and architectural designs, e.g. in one-shot compression without further fine-tuning, our method reduces perplexity by up to 50\% compared with uniform and heuristic allocation baselines. Code will be available at https://github.com/EIT-NLP/LLM-Pruning. --- ### Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue Authors: William Hager, Ishika Rathi, Masum Hasan, Cameron Jones Published: 2026-06-20 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2606.21844v2 As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing Bench, a benchmark that evaluates LLMs and other models on their ability to differentiate humans and AI in multi-turn text. The benchmark provides a collection of paired dialogue transcripts, wherein one dialogue is between two humans and the other is between a human and an AI. The task is to correctly identify which dialogue is human-only vs. human-AI. We evaluated a preliminary set of models against this benchmark, and found that GPTZero, Claude Opus-4.6, and GPT-5.5 achieve the highest accuracy: 89.41%, 77.92%, and 75.94% respectively. Our results suggest that statistical approaches to detection have semantic blind spots, but semantic approaches are susceptible to persona-prompting. Our work speaks to the Inverse Turing Test and motivates human-AI differentiation as a critical capability for AI systems. Our live benchmark can be found at https://huggingface.co/spaces/roc-hci/Inverse-Turing-Bench-Leaderboard. --- ### Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue Authors: William Hager, Ishika Rathi, Masum Hasan, Cameron Jones Published: 2026-06-20 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2606.21844v1 As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing Bench, a benchmark that evaluates LLMs and other models on their ability to differentiate humans and AI in multi-turn text. The benchmark provides a collection of paired dialogue transcripts, wherein one dialogue is between two humans and the other is between a human and an AI. The task is to correctly identify which dialogue is human-only vs. human-AI. We evaluated a preliminary set of models against this benchmark, and found that GPTZero, Claude Opus-4.6, and GPT-5.5 achieve the highest accuracy: 89.41%, 77.92%, and 75.94% respectively. Our results suggest that statistical approaches to detection have semantic blind spots, but semantic approaches are susceptible to persona-prompting. Our work speaks to the Inverse Turing Test as a probe of LLM theory of mind, and motivates human-AI differentiation as a critical capability for AI systems. Our live benchmark can be found at https://huggingface.co/spaces/roc-hci/Inverse-Turing-Bench-Leaderboard (anonymity preserved). --- ### Measuring What Persists: Conditioning Mechanisms and a Geometric Framework for AI Agent Identity Authors: Andrew Tanner Published: 2026-06-20 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.21843v1 AI agents in long-context applications drift from their specified identity. Current methods detect this only after qualitative degradation is visible. We present a geometric framework for measuring identity structure using $\sqrt{\mathrm{JSD}}$ metric spaces and magnitude homology from enriched category theory, where identity is non-geodesic structure and drift is its relaxation toward the geodesic. Validated on a persistent AI agent, the framework's strongest empirical finding is a two-mechanism conditioning structure: cross-condition distances reveal an identity-vacuum cluster where the identity specification fills a behavioral void, and a safety-basin cluster where it displaces from post-training attractors. An equilateral probe baseline confirms that the identity specification creates measurable behavioral richness (55 unique response patterns vs. 1 for the base model) at maximum probe separation. A first-order perturbation theory for equilateral configurations predicts magnitude changes from perimeter changes alone, with shape perturbations first-order cancelled by the $S_n$ symmetry; the formula is self-consistent at the observed perturbation amplitudes. A drift experiment measuring magnitude decrease under context pressure was subsequently found to reflect repetitive-padding artifacts rather than genuine context-length drift; diverse padding produces no measurable deformation through 150K tokens. The magnitude homology framework's full diagnostic promise -- detecting anisotropic contraction and structural collapse via homological simplification -- is architecturally grounded in the perturbation theory and selection rules but remains empirically unconfirmed. --- ### Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification Authors: Zhiyuan Tao, Srikumar Sastry, Matthew J Thompson, Elizabeth G Campolongo, Net Zhang, Ziheng Zhang, Hilmar Lapp, Yu Su, Tanya Berger-Wolf, Nathan Jacobs, Wei-Lun Chao, Jianyang Gu Published: 2026-06-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.21838v2 Multimodal contrastive learning has enabled zero-shot visual classification by aligning images with textual categories. However, in hierarchically structured label spaces, existing methods often produce predictions that are inconsistent across taxonomic levels. For example, a model may predict a fine-grained category whose parent category contradicts its simultaneously predicted higher-level label. By analysis, the issue originates from false negative labels when contrastive comparison involves multiple taxonomic levels. To this end, we propose to restrict contrastive comparisons to categories within the same taxonomic level. In addition, we adopt a group-balanced design, ensuring each taxonomic level receives adequate optimization. As a result, the proposed framework improves both hierarchical consistency and classification accuracy from coarse to fine granularity. We train our model with TreeOfLife-10M based on BioCLIP and evaluate it across multiple hierarchical classification benchmarks, where the model demonstrates significantly improved hierarchical consistency in both Euclidean and hyperbolic spaces. Notably, on iNaturalist 2021 (iNat21), our method improves average accuracy across levels by 30.47% over the baseline, highlighting its effectiveness for hierarchical zero-shot classification. --- ### Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification Authors: Zhiyuan Tao, Srikumar Sastry, Matthew J Thompson, Elizabeth G Campolongo, Net Zhang, Ziheng Zhang, Hilmar Lapp, Yu Su, Tanya Berger-Wolf, Nathan Jacobs, Wei-Lun Chao, Jianyang Gu Published: 2026-06-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.21838v1 Multimodal contrastive learning has enabled zero-shot visual classification by aligning images with textual categories. However, in hierarchically structured label spaces, existing methods often produce predictions that are inconsistent across taxonomic levels. For example, a model may predict a fine-grained category whose parent category contradicts its simultaneously predicted higher-level label. By analysis, the issue originates from false negative labels when contrastive comparison involves multiple taxonomic levels. To this end, we propose to restrict contrastive comparisons to categories within the same taxonomic level. In addition, we adopt a group-balanced design, ensuring each taxonomic level receives adequate optimization. As a result, the proposed framework improves both hierarchical consistency and classification accuracy from coarse to fine granularity. We train our model with TreeOfLife-10M based on BioCLIP and evaluate it across multiple hierarchical classification benchmarks, where the model demonstrates significantly improved hierarchical consistency in both Euclidean and hyperbolic spaces. Notably, on iNaturalist 2021 (iNat21), our method improves average accuracy across levels by 30.47% over the baseline, highlighting its effectiveness for hierarchical zero-shot classification. --- ### AgentDSE: Reasoning-Augmented Architectural Design Space Exploration Authors: Chenyu Wang, Jiahe Caroline Shi, David Kong, Duane S. Boning, Zishen Wan, Yilun Du, Vijay Janapa Reddi Published: 2026-06-20 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2606.21836v1 Traditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods. This inefficiency arises because conventional methods treat the simulator as a black-box oracle. In contrast, human architects effectively guide exploration by reasoning through physical constraints, performance bottlenecks, data reuse, and workload structures. To bridge this gap, we introduce AgentDSE, a simulator-in-the-loop methodology driven by a general-purpose large language model (LLM) coding agent. AgentDSE automates this architectural-reasoning loop without requiring model fine-tuning, precomputed design databases, or domain-specific optimizer code. Across deep neural network (DNN) accelerator mapping, hardware/software co-design, and CPU cache-hierarchy optimization, AgentDSE achieves competitive or better design quality with up to two orders of magnitude fewer evaluations. AgentDSE also produces inspectable traces that surface architectural hypotheses, performance cliffs, implicit priors, and simulator artifacts, making every search decision traceable rather than buried in optimizer state. --- ### AgentCAT: Simulating Computerized Adaptive Testing via Multi-Agent Large Language Models Authors: Weiyuan Zhou, Haiping Ma, Xiaoshan Yu, Changqian Wang, Shangshang Yang, Xingyi Zhang Published: 2026-06-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.21832v1 Computerized Adaptive Testing (CAT), as a key technology for personalized education, aims to accurately assess examinee proficiency by retrieving exercises dynamically matching current ability estimates. However, existing CAT research is constrained by limitations of static offline data and isolated component optimization. Restricted by partial labels in offline logs, researchers degrade the dynamic assessment process into static sequence prediction. Current research focuses on isolated perspectives, e.g., selection or diagnosis, neglecting the overall CAT interaction process. To address this, we propose AgentCAT, a Large Language Model-based multi-agent simulation system, to construct a high-fidelity benchmarking environment for dynamic testing. This framework comprises three modules: (1) The examinee agent with memory retrieval and Chain-of-Thought reasoning simulates responses based on cognitive profiles; (2) The selection agent uses coarse-to-fine bucketing and knowledge graph exploration to balance local difficulty and global coverage; (3) The supervisor uses dual-auditing and robust update to ensure convergence and validity. To validate the framework, we evaluated on two real-world datasets across three dimensions: macro-level ability convergence, micro-level interaction logic, and data sparsity resilience. Results show AgentCAT achieves effective ability estimation, and its selection strategy balances difficulty adaptation and instructional coherence, aligning with human pedagogical intuition. --- ### Mat-Pref: Verifiable-Reward Training Improves Compositional Reasoning in Inorganic Materials Authors: Sarrah R. Mikhail Leung, Taehan Kim, Jeongbin Park Published: 2026-06-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21830v1 Reinforcement learning from verifiable rewards (RLVR) has driven rapid progress in mathematical and code reasoning, but when extended to science, existing benchmarks do not decompose what generalizes: do gains reflect structural transfer, property transfer, or memorization? We introduce Mat-Pref, a benchmark of 10,837 ionic-substitution questions across 11 inorganic structure families, grounded in density functional theory calculations from the Materials Project, with three evaluation splits that isolate in-distribution performance, generalization to entirely held-out structure families, and cross-property transfer: applying band-gap reasoning to hosts seen during training only through formation-energy supervision. Four zero-shot frontier models (70-671B parameters) remain in the 33-54% range on every split, confirming that scale alone does not resolve the compositional chemical reasoning this task demands. A two-stage pipeline of supervised fine-tuning followed by Group Relative Policy Optimization (GRPO) lifts Qwen3-8B to 65.2% in-distribution and 71.6% on held-out families, exceeding zero-shot Qwen3-235B by over 20 percentage points on both structural-generalization splits. Self-consistency sampling shows that the SFT policy can already produce correct answers but cannot reliably surface them as the modal response; GRPO reshapes the distribution so that correct answers become modal rather than merely reachable, and this sharper commitment is visible mechanistically: logit lens analysis reveals a ${\sim}$20pp advantage in answer crystallization at the critical decision layer. We formalize this observation as a distractor-permutation consistency metric under which GRPO narrows the gap between lenient scoring (at least one permutation correct) and strict scoring (all permutations correct) from 24.0 to 14.3 percentage points. --- ### Spectrally Safe Neural Operator Warm-Starts for Large-Scale Newton Solvers Authors: Jaemin Oh, Youngkyu Lee, Jerome Darbon, George Em Karniadakis Published: 2026-06-20 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2606.21828v2 Neural operators are increasingly used to warm-start Newton solvers for nonlinear PDEs, on the premise that a low test error places the initial guess inside the basin of attraction. We show that this premise is unreliable. An operator trained to the relative \(L^2\) error \(O(10^{-3})\) can still produce an initial state in which the discrete Jacobian is indefinite, because the mean-squared training controls error on average while leaving localized pointwise violations of the underlying physics. For a nearly incompressible hyperelasticity problem, we trace this to the predicted volume change: the operator disperses \(\mathrm{det} F\) well away from one, and the resulting Jacobian acquires negative eigenvalues even when the predicted field is visually indistinguishable from the reference. At a small scale, this is a nuisance; at a multi-million degree-of-freedom scale, it is disqualifying, since the conjugate gradient and other Krylov solvers needed for memory-feasible Newton steps assume a definite spectrum. We then show that a short, label-free fine-tuning phase -- penalizing the operator against the discrete energy, with no additional solution data -- shifts the Jacobian spectrum back to positive definite. Combined with an inexact outer loop, this gives a warm-started Newton method that converges across the full loading range where the unregularized operator fails, reaching up to 5.4\(\times\) wall-clock speedup over incremental continuation on a 3D problem with 6.4 million degrees of freedom. --- ### Spectrally Safe Neural Operator Warm-Starts for Large-Scale Newton Solvers Authors: Jaemin Oh, Youngkyu Lee, Jerome Darbon, George Em Karniadakis Published: 2026-06-20 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2606.21828v1 Neural operators are increasingly used to warm-start Newton solvers for nonlinear PDEs, on the premise that a low test error places the initial guess inside the basin of attraction. We show that this premise is unreliable. An operator trained to the relative \(L^2\) error \(O(10^{-3})\) can still produce an initial state in which the discrete Jacobian is indefinite, because the mean-squared training controls error on average while leaving localized pointwise violations of the underlying physics. For a nearly incompressible hyperelasticity problem, we trace this to the predicted volume change: the operator disperses \(\mathrm{det} F\) well away from one, and the resulting Jacobian acquires negative eigenvalues even when the predicted field is visually indistinguishable from the reference. At a small scale, this is a nuisance; at a multi-million degree-of-freedom scale, it is disqualifying, since the conjugate gradient and other Krylov solvers needed for memory-feasible Newton steps assume a definite spectrum. We then show that a short, label-free fine-tuning phase -- penalizing the operator against the discrete energy, with no additional solution data -- shifts the Jacobian spectrum back to positive definite. Combined with an inexact outer loop, this gives a warm-started Newton method that converges across the full loading range where the unregularized operator fails, reaching up to 5.4\(\times\) wall-clock speedup over incremental continuation on a 3D problem with 6.4 million degrees of freedom. --- ### CNnotator: LLM-Guided Memory Safety Annotation Synthesis Authors: Twain Byrnes, Mike Dodds Published: 2026-06-20 Categories: cs.PL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.21822v1 Memory safety errors account for a large proportion of security bugs in systems written in C; modern languages such as Java and Rust prevent such bugs because they are memory-safe by design. To migrate systems to safer languages or identify memory errors, we must first determine how legacy code manipulates memory. This information is only represented implicitly in such code. In many cases, memory usage patterns are merely tedious for humans to figure out, rather than truly difficult. In this work, we ask if large language models (LLMs) can perform this task by having them synthesize annotations representing memory usage as specifications in CN, a hybrid testing/verification tool. Our tool, CNnotator, uses LLMs to automatically generate and test CN specifications. We find that current models are able to generate CN specifications for small-to-medium C programs, with the OpenAI o3 reasoning model achieving a 90% success rate on first attempts and 97% overall success, while the chat model GPT-4o correctly annotates 65% of first attempts. These results suggest AI-assisted annotation is becoming practical for real-world C codebases. --- ### Local Causal Attribution of Chain-of-Thought Reasoning Authors: Dennis Wei, Yannis Belkhiter, Erik Miehling, Radu Marinescu Published: 2026-06-20 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.21821v1 Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In this work, we take a local approach toward this goal by analyzing the causal relationships among individual components, termed units, of a given, specific chain-of-thought trace. We construct a structural causal model on these units and relate each unit to the log probability of generating (subsequent) output units. Our algorithm, termed AttriCoT, is a black-box method that performs attribution by estimating importance parameters in the structural causal model using $O(U)$ forward passes through the model, where $U$ is the number of units. Evaluation of perturbation curves across 5 datasets and 4 reasoning models shows that AttriCoT produces attributions that are more faithful to the model's behavior than alternative methods. The attribution results also reveal notable differences in thought structure between models and domains. --- ### Generating Public Health Responses using Survey-Augmented Large Language Models Authors: Leonardo Marciaga, Thuyen Pham, Julia Rezvani, Alina Hyk, Chunyang Liao, Konstantinos Mitsopoulos, Raffaele Vardavas Published: 2026-06-20 Categories: cs.SI, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.21820v1 Epidemiological models often rely on survey data to represent how individuals make health-related decisions, such as whether to vaccinate or adopt protective behaviors. However, repeated large-scale surveys are costly, time-consuming, and limited in the range of scenarios they can capture. In this work, we investigate whether large language models (LLMs) can generate synthetic survey responses that reproduce patterns observed in real populations. Using longitudinal data from the FluPaths surveys, we first identify groups associated with broadly positive or negative attitudes toward vaccination through clustering analysis. We then evaluate several LLMs using a cluster-informed prompting approach to generate synthetic survey responses across multiple epidemic waves. Across models, the synthetic data generally reproduce the distributions of demographic characteristics, vaccination-related beliefs, risk perceptions, and health behaviors observed in the survey data. However, they are less successful at capturing how these factors vary together within respondents. Some models reproduce group-level vaccination trends more reliably than others, although performance varies across waves. We also trained a classifier to distinguish real from synthetic records and found that the generated responses remained identifiable as synthetic. Overall, our findings suggest that LLM-generated survey data may provide a useful tool for exploratory data augmentation and we hope that it could support agent-based epidemic modeling approaches. However, the generated data should not be treated as a substitute for human survey data without further methodological improvements and validation. --- ### RAPID: A Reproducible Multi-Agent Pipeline for Interpretable Disaster Damage Assessment from Satellite and Street-View Imagery Authors: Yifan Yang, Wenjing Gong, Kaili Zhang, Lei Zou, Zhengzhong Tu, Hao Li, Zongrong Li, Xinyue Ye Published: 2026-06-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21819v1 Due to the increasing frequency and intensity of extreme climate events, there is a clear demand for intelligent, scalable, and autonomous approaches to disaster damage assessment. Existing methods, largely based on supervised learning and task-specific fine-tuning, struggle to generalize under domain shifts, long-tailed data distributions, and heterogeneous geospatial data sources, especially in disaster scenarios. They also often lack the ability to integrate and reason across multimodal geospatial information, such as satellite images and street-view images. In this paper, we introduce RAPID, a reproducible multi-agent pipeline for interpretable disaster damage assessment, including damage-level assessment, damage-type interpretation, and actionable suggestions for response, remediation, and recovery. RAPID coordinates specialized agents to perform cross-view understanding, image restoration, structured damage recognition, and geographical reasoning across heterogeneous data modalities. Without task-specific fine-tuning, RAPID supports zero-shot damage assessment by jointly using complementary information from remote sensing and ground-level perspectives. The system produces fine-grained, interpretable assessments and automatically generates location-specific, decision-relevant disaster reports to support early-stage emergency response. We evaluate RAPID across hurricanes, floods, wildfires, and earthquakes using multiple cross-view imagery inputs, including pre- and post-disaster street-view images, post-disaster remote sensing imagery, and street-view image pairs. Experiments show that RAPID achieves 0.92 overall accuracy for multi-disaster type classification and up to 0.627 for cross-view damage severity prediction, highlighting its potential as a foundational framework for autonomous disaster intelligence. --- ### Steer, Don't Solve: Training Small Critic Models for Large Code Agents Authors: Shubham Gandhi, Yiqing Xie, Atharva Naik, Ruichen Zhu, Carolyn Rose Published: 2026-06-20 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.21811v2 Coding tasks are typically complicated and require multiple capabilities, ranging from high-level planning to low-level implementation. While coding agents are optimized for the joint capabilities, individual capabilities such as high-level planning may have different optima and remain a major bottleneck. To address this challenge, we train a separate critic model that is specialized in high-level planning to steer the coding agent in inference. We construct SFT and DPO data to train the critic model to identify errors made by the coding agent and provide correct and clear high-level guidance without generating concrete actions. Experiments show that our fine-tuned 4B and 8B critic models significantly improve the performance of 6 larger coding agents (e.g., improving the resolved rates of GLM-4.7-Flash-30B-A3B and GPT-OSS-120B by 16.0% and 14.4% on SWE-Bench Verified). The critic model also reduces the total inference costs for some coding agents by solving tasks in fewer steps (e.g., reducing the per-example inference cost for GPT-OSS-20B from \$0.07 to \$0.03). Code: https://github.com/shubhamrgandhi/critic-training --- ### Steer, Don't Solve: Training Small Critic Models for Large Code Agents Authors: Shubham Gandhi, Yiqing Xie, Atharva Naik, Ruichen Zhu, Carolyn Rose Published: 2026-06-20 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.21811v1 End-to-end code agent training is resource-intensive and plateaus on the strategy-level reasoning needed to resolve code issues, since jointly optimizing code-level execution and strategy-level reasoning leaves the latter underdeveloped. Instead, we freeze the agent and add a critic model to supply that signal. Prior code critics are post-hoc, scoring completed trajectories rather than steering the agent; we instead train a small critic that provides intra-trajectory feedback via Supervised Fine-Tuning. On SWE-bench Verified, a critic trained on CWM-32B trajectories transfers to two unseen agents (gains of +3.0 to +3.8 points), and adding target-agent trajectories to the corpus increases the gain to +3.8 on CWM-32B and +4.4 to +5.2 on two Qwen agents, at 30-92x lower critic cost than a strong teacher. On Qwen3-Next-80B-A3B, the critic-guided system is both more accurate (25.2% vs. 20.8%) and cheaper (\$0.04 vs. \$0.11) than the agent alone, because the critic also shortens trajectories. Our results show that a small, well-trained critic is a practical complement to scaling agent training. Code: https://github.com/shubhamrgandhi/critic-training. Data and models: https://huggingface.co/collections/shubhamrgandhi/critic-training-for-code-agents --- ### Causal Gaussian Processes for Robust Treatment Effect Evaluation with Unobserved Confounding Authors: Junzhe Zhang, Jingyuan Chen, Elias Bareinboim Published: 2026-06-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21809v1 The presence of confounding bias poses a key challenge in policy evaluation, as the target causal effects of actions are not identifiable (i.e., underdetermined) from observational data. On the other hand, existing confounding-robust evaluation strategies require detailed prior knowledge about the environment or apply only to discrete treatments and outcomes. This paper investigates causal effect evaluation over the continuous domain from confounded observations, while requiring only basic temporal ordering between the treatment and the outcome. We introduce a universal discretization of the exogenous domains that approximates the observational and interventional distributions of any causal model with arbitrary accuracy using a finite number of latent states. Building on this newfound universal approximation property, we develop a novel family of Causal Gaussian process (CGP) models that effectively approximate the observational and interventional distributions of any causal model with confounded observations. --- ### Fixed RAG Compression Collapses Measured Reader Scaling Authors: Sugam Panthi, Rabab Abdelfattah Published: 2026-06-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21807v1 Retrieval-Augmented Generation (RAG) compression papers often evaluate a compressor on one to three readers and treat the compressed evidence layer as evaluation-neutral. We show this assumption is false: fixed compression can raise average accuracy while hiding reader upgrades and reversing model rankings. Across 20 readers and ten domain-method settings over four QA benchmarks and one summarization benchmark, compression gain decreases with reader baseline (nine of ten settings significant, p < 0.05). Generic summarization flips 31% of pairwise model rankings on LongMemEval-S, and a fixed HotpotQA compressor hides 80% of the raw upgrade from Qwen 7B to GPT-4.1-mini. Two opposing forces explain this paradox: compression rescues weak readers by removing noise they cannot filter, and harms strong readers by dropping details they would have used. The pattern appears across structured compilation, generic summarization, three trained compressor families, query-focused summarization, and an external audit of nine published compression papers. We release ragscale, a toolkit built on 177,000 row-level compression transitions, so any compression paper can audit reader scaling with three readers in one day. --- ### Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention Authors: Ali Asaria, Tony Salomone, Deep Gandhi Published: 2026-06-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.26121v1 Large language models state false facts as fluently as true ones, yet a model often "knows" internally when it is on shaky ground: the probability it assigns to its own answer tends to dip on the facts it gets wrong. The usual way to act on this, teaching a model to abstain rather than guess, requires a labelled dataset of right and wrong answers. We ask whether the model's own confidence, which is free and needs no labels, can do that job instead. We fine-tune each model (with LoRA) to answer when its frozen confidence is high and to say "I'm not sure" when it is low, using the signal alone and no correctness labels. Across six open-weights models (1B-8B, two families) on short-form factual question answering, with correctness adjudicated by an independent judge model, this label-free recipe holds its own against label-supervised abstention-tuning: at matched coverage we find no statistically detectable difference between the two. A control that drills hard examples instead of abstaining does not help, indicating the gain comes from calibration, not rote memorization. The signal's one blind spot is confidently wrong facts, which it cannot flag. A model's own doubt is thus a near-free substitute for a labelled dataset when teaching it when to abstain. Code and artifacts are available on request. --- ### Recipes for Steering and Scaling LLMs via Sampling Authors: Jiajun He, Zongyu Guo, José Miguel Hernández-Lobato, Yuanqi Du Published: 2026-06-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.26120v1 Large Language Models (LLMs) are probabilistic models, typically defined by an autoregressive factorization. While recent work has begun to study richer target distributions beyond the base model, the sampling strategies remain highly inefficient. In this paper, we present a flexible and theoretically grounded framework for steering and scaling autoregressive LLMs with sampling. Within this framework, we describe two algorithms -- one based on Sequential Monte Carlo (SMC) and one based on Replica Exchange (RE) -- that steer generation toward powering, product or tilting of the base model distribution. We illustrate this framework through scaling the generation quality of LLMs without external supervision or reward models. Experimental results demonstrate our methods scale more favorably than Best-of-N and standard MCMC baselines. Overall, this paper offers a systematic recipe for probabilistic inference with LLMs via sampling. --- ### When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems Authors: Carson Rodrigues, Oysturn Vas Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.20371v1 A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers for intent detection. We test this claim head-to-head and find that the honest answer is: it depends on the intent space. On full ATIS and CLINC150 we compare a fine-tuned RoBERTa, a TF-IDF+logistic-regression baseline, sentence-embedding kNN, and Claude Haiku zero-shot, reporting bootstrap 95% confidence intervals and paired significance tests. When abundant in-domain labels exist, fine-tuned RoBERTa is as good or better and three orders of magnitude cheaper and faster: on ATIS it beats Claude zero-shot by 11.8 points (95.9 vs. 84.1, p<0.001). On the broad 150-intent CLINC150 schema the two are statistically tied (89.1 vs. 88.5, p=0.24): the LLM matches a fully supervised model with no training data. The LLM's advantages appear in three production-relevant regimes: out-of-scope detection (OOS recall 85.6 vs. 58.1 for RoBERTa); robustness to realistic ASR noise via a controlled text-to-speech to noise to Whisper pipeline (92.5 vs. 80.0 at 0 dB); and dynamic per-deployment schemas, where a classifier trained on one app's intents scores 0% on a new app's intents while the schema-prompted LLM serves both at ~94% with zero retraining. We distill these findings into a decision framework for practitioners. --- ### ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora Authors: Xinfeng Zhang, Mingxuan Liu, Yifei Chen, Juncheng Zhu, Kasidit Anmahapong, Yiming Huang, Yuan Zhang, Hongjia Yang, Yi Liao, Gang Ning, Haibo Qu, Qiyuan Tian Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.20369v1 Structured reporting converts free-text radiology narratives into queryable data keys, facilitating cohort assembly, longitudinal tracking, and training label generation for medical AI. The prevailing paradigm follows a two-stage pipeline: (1) constructing a reporting template, (2) extracting information to populate it. While the extraction stage has benefited from advances in large language models (LLMs), template construction remains a manual bottleneck relying on labor-intensive expert consensus that is static, difficult to scale, and may fail to capture real-world reporting diversity. We address this limitation with \textbf{\texttt{ASTAR}}, an LLM-based framework for Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora. Extensive experiments on 4,215 fetal brain MRI reports from multiple centers demonstrate that the \textbf{\texttt{ASTAR}}-induced template surpasses two expert-curated templates across template coverage, information fidelity, diagnostic fidelity, and expert-rated usability, reducing template development from weeks of committee deliberation to hours of automated processing. Code: https://github.com/birthlab/ASTAR --- ### Research Paper Quality Recognition Through Textual Feature Analysis Authors: Saikiran Korla, Sadwik Gummadavelli, Trung-Nghia Le, Minh-Triet Tran, Tam V. Nguyen Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.20368v1 Knowledge and innovations are shaped by using the quality and credibility of the scientific research. Yet, distinguishing between impactful, high-quality work and flawed studies remains a challenge. This paper introduces a benchmark for classifying research papers into two categories: good (highly cited) and non-good (retracted), using only textual features from titles and abstracts. We evaluate multiple embedding techniques, including SBERT, Word2Vec, FastText, USE, and TF-IDF, combined with classifiers such as Support Vector Machines (SVM), Random Forests, and Neural Networks. Our contributions include: (1) hyperparameter transparency, (2) feature space visualizations using t-SNE, (3) model interpretability analysis with SHAP, and (4) detailed examination of error cases. Experimental results show that a neural network with SBERT embeddings achieves 87.22\% accuracy, while FastText combined with SVM reaches 91.12\%. These findings highlight the value of textual information in assessing research quality, with ethical considerations for deployment. This work contributes toward the development of academic integrity tools that promote trustworthy scholarship. --- ### An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case Authors: Nicolas Turenne, Youcef Sklab, Eric Chenin, Jean-Daniel Zucker Published: 2026-06-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.14587v1 Background: Recent advances in information retrieval (IR) leverage both dense and sparse representations, large language models (LLMs), and specialized retrieval models to improve ranking accuracy, relevance, and cross-lingual performance. Complementary techniques such as passage indexing, document layout analysis, and semantic knowledge representation further enhance retrieval effectiveness by capturing fine-grained contextual and structural information. Emerging agentic LLM frameworks extend these capabilities by enabling planning, iterative reasoning, tool use, and multi-agent collaboration, thereby broadening applications across diverse domains. These frameworks also emphasize rigorous evaluation, ethical considerations, and trustworthiness, ensuring responsible deployment in real-world settings. We propose a modular, agent-based pipeline for botanical trait extraction. Optical character recognition (OCR) converts PDFs into machine-readable text, while segmentation and indexing organize content by genus and species. Rule-based parsers extract structured botanical traits, and ensembles of large language models (LLMs) expand trait vocabularies and resolve ambiguities. This approach ensures accurate species recognition, scalable annotation, and explainable integration of textual botanical descriptions, enabling robust and interpretable data extraction across large botanical corpora. Results: Using three regional botanical datasets, our system extracted 55,737 trait annotations across 4,961 species, averaging 9.1 traits per species. Integration of LLM-based enrichment improved coverage for 75% of traits, increasing total annotations by 59%. While the choice of OCR engine had a minor effect on species recognition, overall annotation counts remained stable, demonstrating the robustness, scalability, and reliability of the pipeline for large-scale botanical trait extraction. --- ### Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures Authors: Haibo HU, Lianming Huang, Qiao Li, Nan Guan, Chun Jason Xue Published: 2026-06-19 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2608.14586v1 Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure. In a full autonomous driving stack, this problem is even more pronounced: legacy vehicle platforms were provisioned for modular pipelines, yet after several planning-related functions are absorbed into a unified VLA model, part of the original CPU budget becomes underutilized, while the visual encoder and the main reasoning path still concentrate most computation and memory demand on the GPU. As a result, directly deploying VLA together with the rest of the onboard system can be hard under realistic GPU memory constraints. To address this issue, we present a hybrid CPU--GPU inference framework with flexible resource scheduling for autonomous driving. Our design partitions the VLA backbone at the block-layer granularity, executes the visual encoder and LLM prefix on the GPU, and offloads the LLM suffix to the CPU through a cross-frame asynchronous pipeline, thereby exposing a schedulable boundary for redistributing compute and memory pressure across heterogeneous processors. We evaluate the proposed framework on two representative driving VLA models, Orion and MindDrive. On Bench2Drive, our method reduces average latency from 521ms to 408.0ms for Orion and from 443ms to 306.2ms for MindDrive, corresponding to 21.7% and 30.9% reduction, respectively. For Orion, the estimated peak GPU memory is further reduced from 45GB to 29GB. In real-vehicle deployment under coexistence with Autoware.Universe, native Orion cannot run because the onboard GPU memory budget is insufficient, whereas the hybrid version runs successfully together with the full vehicle stack. --- ### Evaluation of Motivational Interviewing Counsellors with Task-Aware Multi-Stage LLM-Based Simulated Clients Authors: Jiading Zhu, Xinyu Cindy Wang, Thomas Nguyen, Yan Qing Lee, Osnat C. Melamed, Peter Selby, Jonathan Rose Published: 2026-06-19 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.07499v1 The development and benchmarking of Large Language Model (LLM)-based Motivational Interviewing (MI) counsellors now often rely on LLM-based simulated clients. Prior work on simulated clients, however, has not aligned with the specific tasks fundamental to the MI therapy approach. A key task is evoking, in which the counsellor first elicits the client's ambivalence and then strengthens the client's motivation for change. We present Evoke-Sim, a task-aware, multi-stage LLM-based client simulation framework for evaluating MI counsellors in smoking cessation, designed specifically for the evoking MI task. Evoke-Sim employs structured client profiles, an evoking-specific three-stage conversation flow, and a reveal policy that regulates which client profile information might be disclosed at each stage. We show that compared to existing profile-grounded simulated clients, Evoke-Sim is better at differentiating levels of MI quality using task-aware evaluation metrics, while reducing non-grounded client statements and premature disclosure of client information, setting a higher standard for the evaluation of LLM-based MI counsellors. --- ### Knowing You Is Everything: LLM Agents Achieve Near-Perfect Profile-Consistent Reaction Prediction in Social Media Simulation Authors: Ljubisa Bojic, Ljiljana Matic, Joerg Matthes, Milan Cabarkapa, Bojana Dinic, Jue Wang Published: 2026-06-19 Categories: cs.HC, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.07498v1 Autonomous AI agents in social media present concrete risks to democratic discourse and platform governance, while also offering tools for pre-deployment recommender system testing. A central open question is whether persona-prompted LLMs can simulate individual-level social media reactions with sufficient accuracy to support either application, and how accuracy depends on profile completeness, model selection, and the generalization challenge posed by novel post content. This study benchmarks twelve LLM configurations on binary like/dislike prediction across 296 survey-based agent profiles and 26 ground-truth-mapped posts under three profile conditions, with leave-post-out machine learning classifiers as baselines. Across full-profile conditions, accuracy ranges from 75.54% to 96.68%, with a 30-point spread attributable primarily to model selection and confirmed by paired McNemar tests with agent-level bootstrap intervals. GPT-5.5 Pro accuracy degrades monotonically from 96.68% under a full profile to 62.32% under a reduced profile and to 51.00% with demographics alone, the last indistinguishable from the majority-class baseline, which confirms that demographic inference provides negligible predictive signal. Supervised classifiers collapse to 15.4% under leave-post-out, while LLMs sustain genuine zero-shot generalization unavailable to trained methods. Adaptive reasoning improves accuracy substantially for some models. Inter-model agreement is nearly double for posts with direct profile anchors (mean \k{appa} = 0.44) than for posts without them (\k{appa} = 0.23), and the least heterogeneous configuration homogenizes 34% of simulated population reactions. Results validate LLM-based simulation for recommender system stress-testing while documenting the behavioral accuracy that makes large-scale synthetic agent swarms a credible threat to public opinion. --- ### DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis Authors: Wasim Madha, Nityanand Mathur, Hamees Sayed, Apoorv Singh, Sameer Khurana, Akshat Mandloi, Sudarshan Kamath Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.00011v1 Current text-to-speech systems face a trade-off: autoregres- sive codec language models produce highly intelligible speech but require large-scale models and training data and decode tokens sequentially, while non-autoregressive approaches im- prove speed at the cost of linguistic accuracy. We present DLLM-TTS, a framework that formulates TTS as conditional block discrete diffusion over X-Codec2 neural audio codec to- kens. The model decomposes sequences into blocks and applies masked diffusion within each block while processing blocks se- quentially, learning both local acoustic coherence and global text-speech alignment. During inference, parallel token pre- diction within blocks enables efficient generation with a real- time factor (RTF) of 0.15. A 0.6B-parameter model trained on 20K hours achieves competitive performance on the Seed- TTS-eval benchmark, demonstrating that block discrete diffu- sion language models enable practical and data-efficient speech synthesis with parallel generation. --- ### HenTwin: A Multimodal Digital Twin Framework for Longitudinal Biological State Monitoring in Laying Hens Authors: Yashan Dhaliwal, Shreya Rao, Suresh Neethirajan Published: 2026-06-19 Categories: q-bio.OT, cs.AI, stat.AP arXiv: https://arxiv.org/abs/2607.28652v1 Early-life monitoring in laying hens remains constrained by fragmented single-modality sensing and the absence of formal system-level state representations. HenTwin, a multimodal digital twin framework implemented as a five-layer IoT architecture, formalizes flock-level multimodal biological state dynamics from hatch through 25 weeks of age. A four-dimensional biological state vector integrating body surface temperature, acoustic energy entropy, band energy ratio, and optical-flow-based motion is defined, with the temperature-humidity index treated as an exogenous environmental input to preserve intervention capability. A discrete-time state transition model is estimated from 25 weeks of longitudinal multimodal data collected from 150 Lohmann LSL-Lite hens across five controlled rooms at the Atlantic Poultry Research Centre, Dalhousie University. The estimated transition matrix exhibits modality-specific persistence while remaining asymptotically stable. Perturbation analysis demonstrates that a sustained +2.0 THI increase produces a stable long-run acoustic entropy elevation of 0.54 nats, approximately one-quarter of the entire 1.87-nat developmental decline observed across the study period. Pettitt change-point detection identifies coordinated multimodal developmental state transitions at Weeks 12-14. Cross-room validation suggests that structural transition parameters are partially transferable across rooms, whereas environmental input sensitivity requires room-specific calibration, supporting a two-tier IoT deployment architecture. Leave-one-out cross-validation demonstrates consistent out-of-sample model performance. HenTwin takes a first step toward formal, state-aware digital twin inference in precision livestock farming. --- ### When Kernel Ridge Regression Meets the Hölder-Zygmund Class: Minimax Optimality and Failure of Properness Authors: Yuxuan Hou Published: 2026-06-19 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2607.26065v1 We study kernel ridge regression for nonparametric regression over the Hölder-Zygmund class. Using an RKHS equivalent to a Sobolev space of smoothness s+d/2, we prove that misspecified KRR attains the minimax L2 rate n^{-2s/(2s+d)}. We also show that properness fails in the Hölder-Zygmund norm: even for the zero regression function with Gaussian noise, the expected squared Hölder-Zygmund norm of the KRR noise component grows as log n. --- ### Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAG Authors: Ng S. T. Chong Published: 2026-06-19 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.24781v1 RAG systems rely on chunking, which destroys structural information in documents. Existing heading-based retrieval (Jeong et al., 2025) requires multiple LLM calls per document and returns sub-chunks within matched sections. We introduce ToC-guided page retrieval, which infers headings from visual formatting without LLM calls, embeds them as a parallel index, and loads full page sections. Across 1,280 conditions on 8 enterprise documents (5 to 195 pages), we find: (1) ToC is a significant main effect on answer quality (d = +0.41, p = 0.031), with the largest gains in completeness (+0.40) and usefulness (+0.40); (2) combined with answer-side verification, it outperforms query-side decomposition + verification (d = +0.32, p = 0.036); (3) ToC contributes 20% of citations despite adding only 2.9 pages per query; (4) gains are directionally larger on longer documents (up to +1.50 on 118 pages), though the trend does not reach significance with 8 documents; and (5) a 480-condition sensitivity analysis finds no significant parameter effects (all p > 0.38), confirming defaults are near-optimal. The contribution is both methodological (a new zero-LLM-cost retrieval algorithm) and empirical: factorial evidence that document-side, query-side, and answer-side enhancements are complementary, a three-way interaction not previously studied. --- ### LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation Authors: Xingyu Chen, Rui Wang, Zhaopeng Tu, Liefeng Bo Published: 2026-06-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.24780v2 Fixed benchmarks are costly to renew and cannot adapt their questions to model-specific failures. We ask whether LLMs can instead discover one another's weaknesses and turn those observations into an evaluation process. To study this question, we introduce \textbf{LivingArena}, an automated peer-probing framework in which models take turns testing one another. Using the interaction history, each questioner identifies potential weaknesses of its opponent and constructs targeted, verifiable questions to probe them. A 3,600-round tournament of ten models reveals a clear role asymmetry: strong answerers are not always reliable questioners, because they may generate internally inconsistent tests or fail to verify their own reference answers. After a questioner exposes an answerer's failure, it is more likely to pursue the same capability domain, while the answerer's weakness recurs on independently generated questions, including questions written by different models. These findings show that peer probing can reveal persistent model-specific weaknesses while separately evaluating answering and reliable test construction. By automating this process and allowing test difficulty to evolve with model capabilities, LivingArena provides a "living" benchmark for model development, red-teaming, and capability-aware multi-agent coordination. We publicly release our code: https://github.com/galaxyChen/LivingArena --- ### LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation Authors: Xingyu Chen, Rui Wang, Zhaopeng Tu, Liefeng Bo Published: 2026-06-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.24780v1 Evaluating frontier LLMs is challenging: static benchmarks suffer from contamination and saturation -- leaving users unable to distinguish top models and developers blind to specific failure modes -- while human preference is subjective. In this paper, our question is: \emph{Do LLMs know what other LLMs don't? And can we leverage this dynamic for evaluation?} We present \textbf{LivingArena}, an automated, contamination-resistant evaluation framework. In this framework, models take turns proposing questions, aiming to pose items that opponents cannot answer correctly. Questioners are encouraged to actively identify and exploit opponents' knowledge boundaries, receiving rewards when the answerer fails, while the answerer is rewarded otherwise. To ensure questions contain objectively verifiable answers, a judge panel of strong models validates them, penalizing questioners if validation fails. Evaluating ten frontier LLMs, LivingArena yields a stable Elo leaderboard. Our behavioral analyses show that models identify and exploit their peers' cognitive boundaries: self-play and tournament logs indicate that they localize and double down on opponents' weak dimensions. Beyond static knowledge recall, peer probing measures factual rigor and the higher-order ability to probe an opponent's weaknesses, correlating only weakly with human preference and offering a scalable, low-cost approach to continuous evaluation. --- ### VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing Authors: Yexiang Liu, Wen Zhong, Sijie Zhu, Xin Gu, Fan Chen, Junxian Duan, Jie Cao, Longyin Wen, Zhenfang Chen Published: 2026-06-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22632v1 The rapid rise of vlogs as a personalized storytelling medium has created a demand for automated systems to evaluate and refine vlog editing plans. However, vlog assessment is highly subjective and remains challenging due to a lack of standardized criteria, dataset and benchmark, and effective reward models. To address these challenges, we define a comprehensive vlog evaluation framework guided by professional vlog creators and product managers, establishing a taxonomy of six key dimensions, i.e., Creativity, Consistency, Concept Design, Cinematography, Narration, and Pacing. Subsequently, we curate a large-scale dataset of 100k vlog edits and a dedicated benchmark, VRMBench, to evaluate the vlog rewarding capabilities of Multimodal Large Language Models (MLLMs). Finally, we present VlogReward, a robust vlog reward model that can provide both fine-grained multi-dimensional scores and actionable feedback for iterative refinement. Technically, we enhance the Group Relative Policy Optimization (GRPO) framework by introducing an adjustable inter-group comparison reward, which mitigates the "direction blindness" issue of standard GRPO and enables the model to better distinguish varied-quality edits. VlogReward achieves state-of-the-art results that significantly outperform existing MLLMs, including GPT-5 and Gemini-3-Pro. We hope that our study can help vlog creators and foster automated vlog evaluation and refinement systems. --- ### Overcoming the BCI Calibration Bottleneck: A Clinically-Grounded Architecture using Riemannian Alignment and Stochastic Weight Averaging Authors: Immanuvel Prathap Sagayaraju Published: 2026-06-19 Categories: eess.SP, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2607.16225v1 Brain-Computer Interfaces (BCIs) face a severe calibration bottleneck due to cross-subject spatial covariance shifts and physiological artifacts. To enable zero-calibration BCI, a deep learning pipeline was engineered combining Per-Session Independent Component Analysis, Riemannian Euclidean Alignment, and EEGNet stabilized by Stochastic Weight Averaging (SWA). Evaluated on the strict MOABB BNCI2014-001 benchmark, the proposed architecture successfully isolates true sensorimotor rhythms. For the primary case study (Subject 1), a clinically robust SWA stable accuracy of 90.97% (AUC: 0.976, Cohen's $κ$: 0.819) was achieved. Furthermore, expanded 9-fold Leave-One-Subject-Out (LOSO) cross-validation yielded a globally stable mean accuracy of 74.31%, proving hardware-agnostic zero-shot efficacy for binary motor imagery. --- ### International Agreements to Limit Frontier AI: Objectives and Exit Authors: Lennart Finke Published: 2026-06-19 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.16224v1 An international agreement to limit AI development could be crucial to mitigate risks from AI. However, it remains unclear which conditions should determine when the limiting measures are relaxed. We survey existing international agreements, outline what properties appropriate conditions should satisfy, list possible conditions, and finally give a recommendation in an example scenario. We recommend a fixed time period after which a new organization established at the start of the period specifies conditions that address when AI development can be safely conducted, with a possibility of withdrawal in extraordinary circumstances. We hope to illustrate the considerations that would likely go into an international agreement to limit AI. --- ### An Empirical Study of Handcrafted Feature Learning and Convolutional Neural Networks for Facial Expression Recognition Authors: Chethiya Galkaduwa Published: 2026-06-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.15288v1 Facial expression recognition is an important computer vision task with applications in human--computer interaction, mental health monitoring, driver alert systems, and behavioral analysis. While convolutional neural networks (CNNs) dominate modern facial expression recognition, handcrafted feature descriptors such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) remain useful classical baselines. This study compares HOG with Support Vector Machine (SVM), LBP with Logistic Regression, and a lightweight CNN across three facial expression datasets: FER-2013, CK+, and KDEF. The results show that CNNs achieve the best overall performance, particularly on more complex data, while HOG performs strongly in controlled environments. LBP performs poorly across all datasets. The study highlights that dataset complexity significantly affects performance and that robust feature learning is essential for real-world facial expression recognition. --- ### Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence Authors: Shohini Sarkar, Smithi Mahendran, Rishi Chudasama, Varun Mannam, Arav Luthra, Yuvraj Rekhi, Vivek Nadig, Arsh Goenka Published: 2026-06-19 Categories: cs.LG, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2607.14127v1 Representative clutter height (RCH) is a key parameter in radio propagation and interference analysis because it captures the dominant height of local obstructions that drive terminal clutter loss. Current practice often relies on fixed clutter heights assigned to land use classes in Recommendation ITU-R P.452-18, but this misses within class variation and can lead to conservative exclusion zones and poor site ranking for low Earth orbit ground station siting and spectrum coordination. We present an interpretable, globally deployable machine learning framework for predicting RCH from open geospatial data. The model is trained using LiDAR derived labels from the U.S. Geological Survey 3D Elevation Program and inference time features from global land-cover, terrain, demographic, thermal, and optical remote sensing products. We define RCH using a robust 75th percentile clutter height statistic, evaluate multiple regressors, and select LightGBM for its accuracy, efficiency, and compatibility with feature attribution analysis. The final model achieves a mean absolute error of 1.79m and an R^2=0.765, reducing absolute error by more than 60% relative to the ITU baseline. Beyond aggregate fit, we evaluate domain facing criteria relevant to RF planning, including meter scale error, tolerance band accuracy, over and under estimation tails, agreement with ITU clutter height regimes, and SHAP-based physical plausibility. SHAP identifies tree canopy cover, land-cover semantics, and spectral reflectance as the most influential predictors. Studies on segmentation derived features, non-forest ablations, and land-cover matched international validation show that open geospatial data can improve clutter modeling at scale without sacrificing interpretability or deployability. --- ### Interpretable Language Model for Closed-Loop Type 1 Diabetes Control Authors: Maya Sarkar Published: 2026-06-19 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.14126v1 Type 1 Diabetes (T1D) is a chronic, life-threatening autoimmune condition characterized by the complete destruction of insulin-producing pancreatic beta cells. While Artificial Pancreas Systems (APS) powered by Reinforcement Learning (RL) have shown promise in automating insulin delivery, their ``black-box'' nature makes it hard for patients and doctors to trust them fully. This paper presents LLM-T1D, a promising approach that combines the precision of RL with the clear, human-like reasoning of Large Language Models (LLMs) to create a more transparent and reliable insulin pump controller. By training an expert RL system and distilling its knowledge into fine-tuned LLaMA 3.1 8B and Qwen3 8B models, we developed a controller that not only surpasses the RL system's performance but also explains its decisions in plain, understandable language. Tested on the FDA-approved UVA/Padova T1D simulator, the LLM controllers deliver excellent blood sugar control (73.5% Time in Range) while maintaining strict formal safety verification against hallucinations. --- ### CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models Authors: Ruijiang Dong, Zesheng Ye, Jianzhong Qi, Lei Feng, Feng Liu, Gang Niu, Masashi Sugiyama Published: 2026-06-19 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.14125v1 Pre-trained vision-language models (VLMs) enable zero-shot image classification by computing the similarity score between an image and textual descriptions, typically formed by inserting a class label (e.g., "cat") into a prompt (e.g., "a photo of a"). Since the score for a given image-class pair is sensitive to the choice of prompt, existing studies ensemble multiple prompts using a weighting vector to aggregate scores across different prompts. Yet, in current strategies, the weighting vector assigned to each prompt is shared across all classes, implicitly assuming that prompts are conditionally independent of classes, which often does not hold in practice, as a prompt like "an aerial view of" might be apt for "airport" but ill-suited for "apple". To address this, we propose class-aware zero-shot prompt reweighting (CARPRT). This scoring scheme adjusts the weighting vector for each class label by capturing the class-specific relevance of different prompts in a training-free manner. For each class label and every available prompt, we quantify their class-specific relevance by averaging image-text relevance scores over images predicted to that class under the given prompt. These estimates are then normalized to derive class-specific weights. Evaluations on standard image classification benchmarks show that CARPRT outperforms existing class-independent reweighting methods, confirming that modeling prompt-class dependencies is crucial for effective zero-shot prediction and even broader VLM-based application settings that rely on prompt ensembling. Our code is available at https://github.com/tmlr-group/CARPRT. ---