# Research Papers — 2026-06 · bundle page 49 of 260 > Full-text markdown of papers #2401–2450 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/49 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/48.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/50.md) ### Speaking Numbers to LLMs: Multi-Wavelet Number Embeddings for Time Series Forecasting Authors: Defu Cao, Zijie Lei, Muyan Weng, Jiao Sun, Yan Liu Published: 2026-06-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.26487v1 Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet their discrete, language-oriented tokenization and embedding interfaces are misaligned with continuous numerical values, often harming numerical ordering and forecasting reliability. We propose TempoWave, a plug-and-play temporal wavelet digit interface that maps each scalar observation into digit-wise embeddings constructed from multi-wavelet, multi-scale coefficients. By directly overriding standard token representations, TempoWave seamlessly exposes both fine-grained local fluctuations and macro global structures in a transformer-compatible form, ensuring that precise numerical formatting, distinct digit identity, and robustness to common normalization operations are maintained throughout the LLM pipeline. Experiments across five context-enriched forecasting benchmarks demonstrate that TempoWave consistently improves LLM-based forecasters over standard numeric tokenization and alternative embedding interfaces, achieving a new state-of-the-art. These results highlight the numeric interface as a key bottleneck and suggest that principled multi-resolution embeddings can better couple LLMs' contextual reasoning with precise forecasting. Our code is available at https://github.com/DC-research/TempoWAVE and our model can be accessed at https://huggingface.co/Melady/TempoWAVE. --- ### Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs Authors: Xinyi Yan, Yingyi Zhang, Chengzhi Zhang Published: 2026-06-25 Categories: cs.CL, cs.DL, cs.HC, cs.IR arXiv: https://arxiv.org/abs/2606.26485v1 Microblogging platforms generate massive amounts of short, noisy, and dispersed user content, making automatic keyphrase extraction (AKE) an important but challenging task. Prior studies have used eye-tracking signals to improve microblog-based AKE because such signals reflect readers' attention to salient words. However, eye tracking alone is limited by physiological, acquisition, and feature-decoding constraints. To address this issue, we investigate whether electroencephalogram (EEG) signals can complement eye-tracking signals for AKE. Using the ZuCo cognitive language processing corpus, we select 8 EEG features and 17 eye-tracking features and incorporate them into microblog-based AKE models. To reduce possible distortion of cognitive signals by model structures, we inject these features into the input of the soft-attention layer and the query vectors of the self-attention layer. We then evaluate different combinations of cognitive signals across AKE models. The results show that cognitive signals produced during reading consistently improve AKE performance, regardless of feature combinations and model architectures. EEG features bring the largest gains, while combining EEG and eye-tracking features yields performance between the two individual signal types, suggesting partial complementarity but also possible redundancy or noise. These findings indicate that EEG signals provide useful cognitive evidence for microblog-based AKE and that multimodal cognitive signals deserve further investigation. --- ### Extracting Problem and Method Sentence from Scientific Papers: A Context-enhanced Transformer Using Formulaic Expression Desensitization Authors: Yingyi Zhang, Chengzhi Zhang Published: 2026-06-25 Categories: cs.CL, cs.DL, cs.IR arXiv: https://arxiv.org/abs/2606.26481v1 Billions of scientific papers lead to the need to identify essential parts from the massive text. Scientific research is an activity from putting forward problems to using methods. To learn the main idea from scientific papers, we focus on extracting problem and method sentences. Annotating sentences within scientific papers is labor-intensive, resulting in small-scale datasets that limit the amount of information models can learn. This limited information leads models to rely heavily on specific forms, which in turn reduces their generalization capabilities. This paper addresses the problems caused by small-scale datasets from three perspectives: increasing dataset scale, reducing dependence on specific forms, and enriching the information within sentences. To implement the first two ideas, we introduce the concept of formulaic expression (FE) desensitization and propose FE desensitization-based data augmenters to generate synthetic data and reduce models' reliance on FEs. For the third idea, we propose a context-enhanced transformer that utilizes context to measure the importance of words in target sentences and to reduce noise in the context. Furthermore, this paper conducts experiments using large language model (LLM) based in-context learning (ICL) methods. Quantitative and qualitative experiments demonstrate that our proposed models achieve a higher macro F1 score compared to the baseline models on two scientific paper datasets, with improvements of 3.71% and 2.67%, respectively. The LLM based ICL methods are found to be not suitable for the task of problem and method extraction. --- ### Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents Authors: Praneeth Narisetty, Shiva Nagendra Babu Kore, Uday Kumar Reddy Kattamanchi, Jayaram Kumarapu Published: 2026-06-25 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.26479v1 Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training the model to refuse malicious instructions, enforce security outside the model with a deterministic policy that mediates the agent's actions. Systems such as CaMeL, FIDES, Progent, RTBAS, and FORGE realize this with capabilities, information-flow labels, and reference monitors, and several report near-elimination of attacks on the AgentDojo benchmark. We make two contributions. First, we organize these out-of-band defenses as instances of classical integrity protection (Biba), reference monitoring, and least privilege, yielding a structured comparison of what they do and do not cover. Second, we warn that every one of them is validated only on static benchmarks (a fixed set of injection attempts), the same methodology that made in-band defenses look strong until adaptive, defense-aware attacks broke twelve of them at over 90% success; we specify the threat model and protocol an adaptive evaluation requires. We then run that protocol as an independent reproduction and extension of Progent's own adaptive-attack analysis, on AgentDojo, with an open-weight agent (Qwen2.5-7B) self-hosted on a single H200, a setting its authors did not test. Averaged over three runs, the defense held: Progent cut mean attack success roughly sixfold (25.8% to 4.2%), and a hand-crafted adaptive attack did not raise it (2.6%). This is one small-scale data point on a weak model with a single black-box attack template; a stronger optimized (white-box GCG) attack remains open. The result is consistent with, but does not establish, the hypothesis that deterministic out-of-band enforcement is a harder target for an adaptive attacker than in-band detection. --- ### Retrieval-Warmed Energy-Based Reasoning: A Five-Arm Ablation Methodology for Diffusion-as-Inference on Structured Reasoning Tasks Authors: Libo Sun, Po-Wei Harn, Zewei Zhang, Peixiong He, Xiao Qin Published: 2026-06-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.26476v1 Warm-started diffusion samplers accelerate iterative inference, but it is rarely clear which part of the pipeline carries the gain. We study \textbf{retrieval-warmed energy-based reasoning (RW-EBR)} -- an IRED energy-based diffusion model \cite{du2024ired} augmented with a Modern Hopfield trajectory memory -- and contribute a \textbf{five-arm ablation methodology} (oracle, best-constant, per-query-random, shuffled, aligned) that separates three confounded effects: class-prior bias shift, stochastic warm-starting, and graph-aligned value reuse. The diagnostic decomposition is adapted from LLM-RAG evaluation \cite{ru2024ragchecker}. On \textbf{connectivity-2} (Erdős--Rényi all-pairs reachability), the aligned-vs-shuffled-oracle swing reaches \textbf{$+35$\,pp} balanced accuracy on a fixed 1{,}000-graph validation-set diagnostic, with value distribution and retrieval mechanics fixed, only per-graph alignment destroyed, while per-query random initialisation falls below cold -- per-graph alignment, not bias shift or stochasticity, dominates. Yet the \emph{deployable} cold-prediction pipeline misses the acceptance gate at stored-value quality. The same diagnostic logic, stopped at the key-quality screen, applied to \textbf{Sudoku} with a task-specific key encoder produces a clean negative at a \emph{different} component -- key quality, under the current setup. The decomposition names the first blocking component on each task. The setting -- graph reachability refined by an iterative diffusion sampler, with explainability of failure modes as the lens -- places the work within structured and spatio-temporal reasoning. --- ### Localizing RL-Induced Tool Use to a Single Crosscoder Feature Authors: Andrii Shportko, Shubham Bhokare, Ahmed Zeyad A Alzahrani, Bowen Cheng, Gustavo Mercier, Jessica Hullman Published: 2026-06-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.26474v1 Fine-tuning through RL reshapes the internal representations of language models to enable agentic behaviors such as tool use, yet the mechanistic basis of these changes remains poorly understood. While RL substantially improves structured tool-call generation, it is unclear which features emerge, which are preserved, and whether identified features can be leveraged for retraining-free behavioral control. In this work, we show that $\textit{Dedicated Feature Crosscoders (DFC)}$ isolate a compact set of RL-specific features that mediate tool-calling capability in $\texttt{Qwen2.5-3B}$. Across a $48$-crosscoder hyperparameter sweep, encode-decode reconstruction improves the RL model's tool correctness by $+31.1 \pm {9.7}$ pp and passively transfers tool-calling ability to the frozen base model by $+6.8 \pm 5.0$ pp which we call a $\textit{capability spillover}$. Our findings show that DFC partitioning concentrates RL-introduced capability into a minimal, steerable feature set that enables runtime behavioral control of agentic LLMs. --- ### When Does Quality-Aware Multimodal Fusion Matter? A Leakage-Safe Diagnostic for Decision-Level Dependence Authors: Jaden Moon, Arvind Pillai, Andrew Campbell Published: 2026-06-25 Categories: cs.LG, eess.AS arXiv: https://arxiv.org/abs/2606.26473v1 Many multimodal systems estimate the reliability of each modality and weight their contributions to the final prediction. However, it remains unclear whether these scores influence model decisions or merely correlate with performance. We propose a simple diagnostic to test whether reliability information is used during inference. After training, the model and inputs are fixed while reliability scores are permuted across test examples. If predictions depend on these scores, performance should degrade. Experiments on StressID for stress recognition and CMU-MOSEI for sentiment analysis show that permuting reliability scores leaves performance unchanged despite substantial potential gains from selecting the best modality per example. In positive controls where reliability signals identify the correct modality, the same frozen fusion rules yield significant improvements, indicating that reliability signals influence fused decisions only when they reliably predict unimodal correctness. --- ### EpiKV: Epiphany-Aware KV Cache Eviction Without the Attention Matrix Authors: Steven Kolawole, Virginia Smith Published: 2026-06-25 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.26472v3 Reasoning models can generate chains of thought tens of thousands of tokens long, making the key--value (KV) cache that holds them a major bottleneck for inference throughput. Existing eviction policies for long reasoning traces typically rank cached tokens using attention weights, requiring access to the attention matrix and making them incompatible with fast inference kernels. In this work we study the limits of such policies under tight cache budgets. Surprisingly, we find that under the strongest of them the generations that finish are wrong about as often as without eviction; most of the accuracy loss comes from generations that enter loops and run until the length limit, and retaining more tokens according to a fixed importance score exacerbates this behavior. What stops the looping is keeping the tokens the model's recent queries point to, and the forward pass the model already runs reveals them without the attention matrix. Motivated by this observation, we introduce epiphany-aware KV cache eviction EpiKV, which combines hidden-state shifts with the model's recent query--key relevance to rank cached tokens without materializing the attention matrix. On multiple benchmarks, EpiKV matches or outperforms the strongest attention-based eviction baselines while running directly in vLLM with unmodified attention kernels. --- ### Epiphany-Aware KV Cache Eviction Without the Attention Matrix Authors: Steven Kolawole, Virginia Smith Published: 2026-06-25 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.26472v2 As reasoning models emit chains of thought tens of thousands of tokens long, KV cache increasingly becomes a deployment bottleneck. Existing cache eviction methods rank tokens by attention weight, which is a noisy importance proxy in long reasoning traces, and prohibits the use of fused kernels in production inference by forcing the model to materialize the attention matrix. In this work, we instead score tokens with a metric we term the epiphany score: the change in the model's internal representation, read directly from the forward pass with no attention matrix and negligible extra state. Our resulting cache eviction method, EpiKV, requires no training, classifier, or custom kernel, and can be used directly in FlashAttention inference stacks unchanged -- scaling to a 16x longer feasible context than attention-based scoring. upper-mid layers negatively) and remove a positional trend with a causal rolling z-score. At a 4096-token cache EpiKV reaches 72% on MATH-500, matching the strongest attention-based baseline (ThinKV 71%, H2O 67%); a lag-normalized KV variant reaches 37% on AIME-2024 at 8192 tokens against the best of them (33%), at up to 2.8x the speed. --- ### A Causal Foundation Model for Structure and Outcome Prediction Authors: Max Zhu, Martino Mansoldo, Ching-Hao Wang, Stefan Groha Published: 2026-06-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26467v1 We introduce TabPFN-CFM, a causal foundation model that can handle multiple causal problems. TabPFN-CFM predicts both causal structure and outcomes from observational data, supports queries on all three levels of Pearl's Causal Hierarchy and uses known graph structure when available to improve predictions. TabPFN-CFM is trained on synthetic datasets, and generalises to real datasets, demonstrating improved performance over both structural and outcome prediction baselines. --- ### Soft Token Alignment for Cross-Lingual Reasoning Authors: Jiayi He, Jungsoo Park, Wei Xu, Alan Ritter Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26466v1 Multilingual large language models often produce inconsistent reasoning and answers for semantically equivalent prompts in different languages. Prior work suggests that intermediate representations can be relatively language-agnostic, but generation becomes increasingly language-specific as models commit to discrete output tokens. This is problematic because language-specific lexical choices can cause semantically equivalent reasoning paths to diverge across languages. These divergences motivate searching for a cross-lingual alignment signal that is less tied to any single vocabulary item or script. We propose SOLAR, an auxiliary objective for supervised fine-tuning that aligns soft-token representations across languages, using English as a pivot. Soft tokens are probability-weighted mixtures over the vocabulary embeddings, yielding continuous representations that can aggregate information from semantically related tokens across languages. We then align each non-English soft-token summary to its English counterpart in the shared embedding space. Across four multilingual reasoning benchmarks, SOLAR improves accuracy by up to +17.7 points over the base model and +3.8 over standard supervised fine-tuning, with the largest gains on low-resource languages. SOLAR also strengthens final-layer cross-lingual similarity and substantially reduces language-cluster separability, suggesting that aligning soft-token representations helps preserve shared semantic structure during multilingual reasoning. --- ### 3D Spatial Pattern Matching Authors: Nicole R. Schneider, Avik Das, Lukas Arzoumanidis, Abhijeet Ghodgaonkar, Hanan Samet, Youness Dehbi Published: 2026-06-25 Categories: cs.DB, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.26465v1 Spatial pattern matching is the process of matching query entities and constraints with database entities and relations. It has many applications, including similar region search, housing market search, landmark search, and road network matching. To our knowledge, all existing spatial pattern matching approaches frame the problem in a 2 dimensional space, where entities lie in a cartesian plane and relationships defined between them are contained in 2 dimensions. However, this problem framing has significant limitations when searching for real world entities that have height in addition to position. To address this limitation, we extend spatial pattern matching to 3 dimensions and provide a generalized definition of the problem. We describe a subgraph matching algorithm capable of resolving 3D spatial patterns over distance relations and release two 3D spatial pattern matching datasets, one synthetic and one containing real 3D building data from the city of Hamburg, Germany. We test our subgraph matching algorithm on both datasets and present results as a baseline for future methods to build upon. --- ### RunSoC 2.0: Scheduling and Allocating Automotive Software Tasks to Hardware Partitions in Heterogeneous MPSoCs Authors: Daniel Krüger, Lucas Mauser, Stefan Wagner Published: 2026-06-24 Categories: cs.AR, cs.NE arXiv: https://arxiv.org/abs/2609.01614v1 Centralized automotive architectures increasingly consolidate compute-intensive workloads onto heterogeneous Multi-Processor System-on-Chip (MPSoC), creating strict execution, memory, and communication constraints. This paper presents RunSoC 2.0, a customizable framework for early-stage design-space exploration of task scheduling and allocation on heterogeneous MPSoCs. Building on RunSoC 1.0, which targeted allocation on homogeneous hardware, RunSoC 2.0 extends the framework to heterogeneous platforms by modeling processor-specific execution times, cluster-level organization, and domain-specific processing properties. It represents task sets as directed acyclic graphs (DAGs) subjected to strict end-to-end latency and core-affinity constraints, and formulates task scheduling and allocation as a multi-objective optimization problem that minimizes hierarchical memory-budget violations and inter-core/inter-cluster communication penalties. The framework supports multiple solving backends, including COIN-OR Branch and Cut (CBC), Google OR-Tools CP-SAT, and a Genetic Algorithm (GA), enabling comparative evaluation of exact, constraint-programming, and meta-heuristic approaches. We evaluate RunSoC 2.0 using synthetic automotive task sets ranging from 10 to 500 tasks, mapped to representative heterogeneous MPSoCs, including the Renesas R-Car V4H, NVIDIA Jetson AGX Orin, and TI TDA4VM. The results show that RunSoC 2.0 can generate feasible and optimal schedules, expose architectural bottlenecks, and support rapid comparison of platform alternatives. Notably, CP-SAT consistently outperforms both CBC and the GA across tightly constrained hard real-time scheduling instances. By incorporating cluster-aware communication and memory modeling, RunSoC 2.0 improves the realism of early-stage MPSoC analysis while retaining practical solution times for large automotive workloads. (..) --- ### I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models Authors: Leonardo Santiago Benitez Pereira, Marcos Escudero Viñolo, Luis Herranz Arribas Published: 2026-06-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.00003v1 Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machine unlearning, the unintended degradation of semantically related concepts that should have been retained (henceforth, interference) remains poorly characterized and inconsistently evaluated. This paper introduces I-CARE, a methodology that formalizes interference as a first-class object of study in generative unlearning. Rather than proposing a new benchmark or unlearning algorithm, I-CARE provides formal definitions for tasks, metrics, and templates for reporting results, enabling the systematic and reproducible study of interference across unlearning settings. While our methodology is designed to remain valid as models and unlearning algorithms evolve, decoupling long-term scientific insight from transient empirical results, we present a feasibility demonstration with state-of-the-art algorithms and frequently used datasets. The results demonstrate that I-CARE enables meaningful analysis of interference patterns across multiple unlearning settings, establishing the practical applicability of the framework. The software implementation of the methodology is provided in an open-source framework, together with a web-based graphical interface that enables exploration of the outcomes of this study without requiring direct interaction with the codebase or specialized data analysis tools. --- ### Agent Seer: Synthesizing Scenarios from Specification Understanding Authors: Harish Karumuri, Mahesh Vemula, David Lopes Pegna Published: 2026-06-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.26133v1 Evaluating AI agents that use external tools requires realistic test scenarios that capture how practitioners compose tools and iterate across conversation turns. Constructing such scenarios by hand demands deep domain expertise, does not scale across tool ecosystems, and produces static benchmarks that cannot track evolving APIs. We observe that tool specifications -- function names, natural-language descriptions, and typed parameter schemas -- already encode sufficient semantic information to synthesize realistic evaluation scenarios without manual curation or live tool execution. Agent Seer builds off this latent information: from a single Model Context Protocol (MCP) specification, with no examples, no live tool access, and no domain-specific tuning. This pipeline enriches raw schemas, generates graded scenarios with synthetic tool outputs, and expands them into mock-data-grounded multi-turn dialogues that exhibit strong tool-calling correctness and conversational coherence. Evaluation quality is measured by applying this pipeline on seven MCP specifications spanning diverse domains and tool-suite sizes and measuring the tool-calling correctness and conversational coherence. The pipeline achieves strong quality across all domains, with complete tool coverage on small and medium specifications. Two findings emerge within this analysis: parameter schema complexity is the strongest correlate of quality variation -- tool-suite size plays a smaller, orthogonal role -- and argument value accuracy is the dominant failure mode among imperfect scenarios, a sub-dimension invisible to coarse-grained name-match metrics. --- ### SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning Authors: Michal Podstawski Published: 2026-06-24 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.26132v1 Labeled property graphs combine relational structure with heterogeneous textual and categorical properties attached to both nodes and relationships. Conventional graph neural networks typically represent these properties as static feature vectors, limiting their ability to determine which semantic evidence should influence message propagation for a particular prediction target. We propose SLM-Conditioned Hierarchical Relation Routing, an architecture that integrates a small language model directly into graph message selection. A topology GNN provides a stable structural representation and prediction anchor. For each target node, incident messages combine the neighbor's structural state, node-property encoding, relationship-property encoding, and relationship type. A parameter-efficient SLM processes structured graph soft tokens and produces a target-conditioned routing query. This query first selects relevant messages within each relationship type and subsequently routes information across relation-level summaries. The resulting representation provides a bounded residual update to the topology anchor, preserving structural evidence while allowing contextual semantic information to modify the prediction. The architecture supports interpretable analysis at both the neighbor and relationship-type levels and provides a general mechanism for integrating language-derived semantics into property-rich graph learning. --- ### Evaluating Language Models in Realistic Conversational Contexts Authors: Ilija Subasic, Andrew Rabinovich, Zhao Chen Published: 2026-06-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.26131v1 As Large Language Models (LLMs) are increasingly deployed to serve open-ended, multi-turn interactions, evaluating conversational quality at human scale has become a central challenge. Existing evaluation frameworks built for summarization, translation, or short-form QA tasks fall short of adequately measuring the consistency of human-scale dialogue, especially when derivation and validation of these metrics themselves often rely on synthetic rather than human sources. We fill the gap by introducing UPHELD (UPwork Human-Scale Evaluated Long Dialogues), a large, reference-full benchmark for evaluating human-scale conversational ability beyond factual correctness. UPHELD consists of hundreds of complete human-to-human dialogues authored by professional script writers, with realistic turn densities and 36,000+ per-turn human annotations across 30,000+ expert-generated dialogue turns. Using UPHELD, we systematically evaluate classical automatic metrics and reference-free LLM-as-a-judge approaches, and find them unreliable when correlated with expert human judgment. Building off this analysis, we use UPHELD to develop a Mixture-of-Judges framework that combines multiple evaluative signals and improves correlation with human assessments by approximately 30%. Overall, UPHELD provides a robust, human-grounded foundation for evaluating human-scale conversational intelligence that fills a crucial gap in the pre-existing LLM dataset landscape. --- ### Gate Voltage Effect on Pulse Detection Efficiency of Perimeter-Gated SPADs Authors: Hunter Guthrie, Md Sakibur Sajal, Zexi Liu, Marc Dandin Published: 2026-06-24 Categories: physics.ins-det, cs.CV arXiv: https://arxiv.org/abs/2608.21371v1 Perimeter-gated single-photon avalanche diodes (pg-SPADs) are known for their dynamic dark noise modulation capabilities. They are reported to trade noise for photon sensitivity under continuous illumination. However, the implications of this trade-off have not heretofore been studied with pulsed optical systems. This work bridges this gap. We demonstrate that pg-SPADs fabricated in a 0.35 $μ$m standard CMOS process trade-off pulse detection efficiency for a reduction in the the spread of spurious events within a burst window. Consequently, herein, we propose guidelines for the optimal use of pg-SPADs in pulsed LIDAR applications in view of the observed trade-off. --- ### TH-GNN: Heterogeneous Temporal Graph Neural Networks for LLM-Agent Shilling Attack Detection Authors: Shivam Swarup, Divya Prakash Shrivastava, Rakesh Thakur Published: 2026-06-24 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.20376v1 LLM agents can now generate realistic shilling profiles, fluent reviews, and coherent ratings at scale, systematically defeating recommender-system defenses. Text-only detectors that flag semantic drift in review embeddings are blind to graph structure and temporal coordination, while graph-only detectors that exploit neighborhood anomalies cannot reason over review semantics or the cross-modal inconsistencies produced by LLM-generated content. We propose TH-GNN, a heterogeneous temporal graph neural network with a two-layer Heterogeneous Graph Transformer backbone that applies per-type and per-relation attention augmented with learnable sinusoidal temporal encodings on every edge. Cross-modal attention fuses structural user embeddings with frozen RoBERTa representations of reviews and item descriptions, while a GRU operating over log inter-arrival times captures temporal burstiness. Evaluated across five attack families and four benchmark datasets, TH-GNN achieves a grand-mean F1 score of 0.870, outperforming the strongest text-only baseline on Agent4SR attacks by 10.9 percentage points and 11.5 percentage points at the lowest injection rate. These results demonstrate the effectiveness of jointly modeling temporal, structural, and semantic signals for detecting sophisticated LLM-driven shilling attacks. --- ### GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring Authors: Xuming Ye, Zeming Ma, Runjie Yu, Yuan Liu, Tianle Li, Shuhan Bai, Jian Zhou, Fei Wu Published: 2026-06-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.20375v1 Tree-based speculative decoding raises the mean accepted tokens of standard speculative decoding by verifying multiple draft paths, and existing tree builders typically construct these paths through parent-conditioned expansion, where each child token is generated conditioned on its parent path. This construction is incompatible with diffusion language model (DLM) drafters such as DFlash, which produces all future-position distributions in a single forward pass. DDTree bridges this gap by treating high-probability tokens from each future-position distribution as candidate nodes and selecting edges between consecutive positions under a fixed node budget. However, its edge selection relies on token probability alone without modeling parent--child compatibility, so target-compatible tokens can be attached to wrong parents; moreover, its fixed budget ignores that the throughput-optimal tree size varies with the decoding state. We propose GRAFT, a draft-tree construction framework for DLM-based speculative decoding. GRAFT introduces Target-Distilled Edge Scoring (TDES), which distills parent--child preferences from target-model traces to select target-compatible edges, and State-Aware Budget Allocation (SABA), which sets the per-round tree budget by balancing expected draft gain against verification cost. Across multiple models and tasks, GRAFT achieves $2.13\times$--$6.36\times$ end-to-end speedup over autoregressive decoding while adding less than $0.5$\,ms of overhead per round, approximately $1.4\%$ of the target-model verification latency. --- ### 6G Native AI and Channel Foundation Models Authors: Shugong Xu, Jun Jiang, Yuan Gao Published: 2026-06-24 Categories: eess.SP, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2608.14591v1 The integration of artificial intelligence (AI) and wireless communications is widely regarded as a core objective of sixth-generation (6G) systems. However, both the meaning of native AI and the type of AI capability that should be embedded into future wireless systems remain open to interpretation. This paper discusses 6G native AI from a system-design perspective and argues that native AI should be co-designed, optimized, and deployed as an intrinsic component of the wireless system rather than as a removable post-deployment add-on. From this perspective, conventional task-specific supervised models are difficult to use as the main technical basis of native AI because they depend heavily on labeled data, generalize poorly across propagation conditions, and require fragmented designs for different channel-related tasks. Motivated by these limitations, we position channel foundation models (CFMs) as a channel-centric foundation-model paradigm for 6G native AI. We define the scope of CFMs, clarify their differences from task-specific wireless AI models and large language models, and summarize three pretraining families: generative, discriminative, and hybrid pretraining. We further discuss how CFMs may support physical-layer processing, radio access network intelligence, and integrated sensing and communications. Preliminary CSI-CLIP-based results are included as bounded evidence that CFM-style pretraining can improve positioning and beam prediction when task-specific labels are limited. --- ### When More Becomes Less: Position-Dependent Repetition Effects in Language Models Authors: Han-yu Wang Published: 2026-06-24 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.04021v1 Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits. We show this assumption fails. Our two-probe design holds a repeated-target prefix fixed and varies only the readout position: the adjacent probe places the slot immediately after the repeated block; the displaced probe places it inside a fresh sentence frame. Adjacent repetition behaves as priming intuition predicts: $P(\text{target})$ climbs with $N$ and plateaus. Displaced repetition produces an inverted-U: $P(\text{target})$ rises to an early peak and then declines as more copies are added. The displaced inverted-U shows a per-word drop with bootstrap CI excluding zero in all 13 open-access encoder and decoder models we test, and replicates across Spanish, Chinese, German, and French in 42 of 42 multilingual cells. A six-condition causal ablation isolates the effect to exact lexical repetition rather than length, generic redundancy, or semantic-neighbour exposure. A frame-pragmatics control rules out an artefact of the readout frame. Internally, per-target-token attention falls with $N$ while the total budget assigned to the repeated block grows in causal LMs but not in the masked LM we probe. Probes that vary repetition count cannot treat the readout position as orthogonal to what they measure. --- ### Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process Authors: Prateek Roy, Akash Singirikonda Published: 2026-06-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00015v1 Both optimization modeling and constraint modeling are non-trivial problems requiring deep domain expertise and proficiency in modeling formalism languages. Despite their importance across logistics, healthcare, and supply chain management, current large language models regularly produce structurally inconsistent or incomplete optimization formulations, particularly in combinatorial settings. This paper evaluates whether a Retrieval-Augmented Generation pipeline built on a curated synthetic dataset can meaningfully improve LLM optimization modeling performance. A total of 500 optimization problems were synthesized using seed descriptions from the Text2Zinc dataset and professional personas created using an LLM, specified in JSON and associated with validated Python solver scripts. These problems were encoded in a Chroma vector database. For each inference problem, semantically similar problems were retrieved and used as contextual guidance for a LangChain LLM agent. Three benchmark testbeds were used to evaluate the proposed pipeline under the Qwen 3 30B Instruct model. Accuracy rose from 40% to 72% on NL4OPT, 40% to 56% on MAMO Easy, and 32% to 56% on MAMO Complex. The use of semantically validated synthetic examples greatly improves both solution accuracy and structure. The combination of synthetic dataset generation with retrieval augmentation provides an effective alternative to fine-tuning, suggesting that domain-specific synthetic corpora paired with retrieval augmentation can serve as a practical pathway for deploying LLM-based optimization tools in real-world decision-support contexts without costly model retraining. --- ### CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection Authors: Qihua Pan, Zhenheng Tang, Peijie Dong, Xiang Liu, Huacan Wang, Bo Li, Xiaowen Chu Published: 2026-06-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00014v1 Evaluating Large Language Models (LLMs) incurs prohibitive computational overhead during continuous development processes. While coreset selection accelerates evaluation, existing methods either suffer from a severe ``cold start'' bottleneck requiring massive historical logs (e.g., Item Response Theory) or exhibit a surface lexical bias that misses the underlying reasoning manifold of tasks. We propose CoT-Core, a novel training-free core question selection framework. Recognizing that lexically disparate questions can share equivalent underlying logic, CoT-Core prompts LLMs to unroll zero-shot Chain-of-Thought (CoT) reasoning trajectories. Projecting these paths into a latent space effectively clusters questions by intrinsic logical equivalence rather than superficial text similarity. Extensive experiments on GSM8K, MMLU, MMLU-Pro, and GPQA demonstrate that CoT-Core drastically reduces evaluation costs while maintaining high-fidelity score estimation, and delineate the boundary conditions of reasoning-aware pruning, revealing that its efficacy is intrinsically gated by task complexity. --- ### What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs Authors: Ziran Li, Qiang Wang, Zhengyu Chen, Shanglin Lei, Borun Chen, Jingang Wang, Xunliang Cai Published: 2026-06-24 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.00013v2 Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fundamentally unprincipled: compute-based scaling laws fail to generalize across model families, and no framework exists for directly predicting VLM performance before training begins. We propose the Capability-Driven Multimodal Scaling Law, the first cross-family framework that predicts VLM benchmark accuracy from directly observable textual capability. Given a low-dimensional capability score $S$ extracted from LLM textual benchmarks via PCA, we model VLM performance as a function of $S$, with a per-backbone transfer rate and an absorption rate that quantifies data-scaling efficiency. To fit and validate the framework, we train over 150 VLMs on 34 LLMs spanning 7 model families under a strictly controlled recipe. Evaluations on more than 200 textual and 50 multimodal benchmarks show that the law accurately extrapolates transfer rate from models up to 8B parameters to 72B-scale backbones, predicts full VLM training trajectories with high fidelity, and generalizes to entirely held-out model families. Beyond the scaling law, our analysis surfaces actionable insights: certain textual benchmarks negatively correlate with multimodal performance, exposing latent benchmark-gaming behavior; base LLMs outperform instruction-tuned counterparts as VLM backbones due to higher absorption rates and lower data-scaling decay; and different model families occupy distinct positions in the transfer--absorption space. The framework turns backbone selection from costly empirical sweeps into a principled, quantitative decision. Code and data are available at https://github.com/wangq-dev/CDMScaling. --- ### What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs Authors: Ziran Li, Qiang Wang, Zhengyu Chen, Shanglin Lei, Borun Chen, Jingang Wang, Xunliang Cai Published: 2026-06-24 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.00013v1 Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fundamentally unprincipled: compute-based scaling laws fail to generalize across model families, and no framework exists for directly predicting VLM performance before training begins. We propose the Capability-Driven Multimodal Scaling Law, the first cross-family framework that predicts VLM benchmark accuracy from directly observable textual capability. Given a low-dimensional capability score $S$ extracted from LLM textual benchmarks via PCA, we model VLM performance as a function of $S$, with a per-backbone transfer rate and an absorption rate that quantifies data-scaling efficiency. To fit and validate the framework, we train over 150 VLMs on 34 LLMs spanning 7 model families under a strictly controlled recipe. Evaluations on more than 200 textual and 50 multimodal benchmarks show that the law accurately extrapolates transfer rate from models up to 8B parameters to 72B-scale backbones, predicts full VLM training trajectories with high fidelity, and generalizes to entirely held-out model families. Beyond the scaling law, our analysis surfaces actionable insights: certain textual benchmarks negatively correlate with multimodal performance, exposing latent benchmark-gaming behavior; base LLMs outperform instruction-tuned counterparts as VLM backbones due to higher absorption rates and lower data-scaling decay; and different model families occupy distinct positions in the transfer--absorption space. The framework turns backbone selection from costly empirical sweeps into a principled, quantitative decision. Code and data are available at https://github.com/wangq-dev/CDMScaling. --- ### Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams Authors: Fengxiang Wang, Qiuyang Yu, Yueying Li, Mingshuo Chen, Chengchi Fei, Kaiyi Xu, Lixin Gu, Wangxu Wei, Junchao Gong, Lipeng Ma, Jiong Wang, Fenghua Ling et al. Published: 2026-06-24 Categories: cs.CL, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2608.00012v1 Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster emergency response remains insufficiently evaluated. Existing remote sensing benchmarks largely rely on static, post-hoc, and expert-processed products, such as gridded reanalysis data, which are difficult to align with operational disaster scenarios where hazards evolve rapidly and decisions must be made under strict time constraints. To bridge this gap, we introduce Obshazard-bench, a real-time, observation-driven benchmark for evaluating disaster intelligence in MLLMs. Unlike image-centric or post-event benchmarks, Obshazard-bench directly integrates raw, high-frequency satellite sounding streams from diverse satellite sensors with concurrent ground-station observations, historical disaster records, and socio-economic indicators, bypassing delayed expert-processing and physical-inversion pipelines. The benchmark covers 8 major disaster categories and 28 sub-categories across more than 60 countries, incorporating over 120 historically documented extreme-event cases and thousands of lifecycle-oriented VQA samples. Moreover, Obshazard-bench further defines a three-stage evaluation taxonomy aligned with the operational disaster workflow: Predictive Crisis Anticipation for pre-disaster risk detection and early forecasting, Active Evolution Reasoning for in-situ disaster tracking and termination prediction, and Multi-faceted Impact Quantification for post-disaster magnitude deduction, humanitarian burden estimation, and socio-economic impact assessment. Experiments on representative general-purpose and Earth-focused foundation models reveal substantial limitations in transforming raw multi-channel physical observations into temporally grounded and decision-relevant disaster reasoning. --- ### SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models Authors: Jinwei Kong, Runqi Meng, Fanyi Wang, Wentao Qiu, Haotian Hu, Yongjian Zhou, Zhenhua Ge Published: 2026-06-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.24787v2 Sparse Mixture-of-Experts (MoE) models expand foundation model capacity through conditional expert activation, but their full expert pools remain difficult to deploy under limited accelerator memory. Although expert offloading alleviates memory pressure by moving inactive experts to host memory or storage, it introduces a routing-dependent transfer bottleneck: required experts are known only after native top-\(K\) routing, which serializes routing, expert loading, and expert execution during inference. To address this bottleneck, we propose SpecPrefetch, a parameter-efficient prefetching framework for offloaded MoE inference. SpecPrefetch uses a shared lightweight adapter to predict next-layer expert candidates only for asynchronous transfer, while the frozen native router still determines the final executed experts. By separating transfer prediction from execution routing, SpecPrefetch reduces exposed expert-loading latency without changing pretrained routing semantics, so prediction errors affect transfer efficiency rather than model outputs. In addition, a window-aware scheduler prioritizes feasible transfers under cache and bandwidth constraints. Across Qwen3-VL-30B-A3B and DeepSeek-VL2-Tiny, SpecPrefetch achieves the best average expert recall in 9 out of 10 model-benchmark settings with substantially fewer trainable parameters than learned predictor baselines. On a Snapdragon 8 Elite device, SpecPrefetch further improves decoding throughput by up to \(20\%\) over a compute-optimized offloading runtime, demonstrating practical benefits for storage-constrained MoE deployment. The code and model weights are available at https://github.com/wei390/SpecPrefetch. --- ### Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Authors: Yijia Dai, Zhaolin Gao, Yahya Sattar, Jennifer J. Sun, Sarah Dean Published: 2026-06-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.22646v1 Large language models (LLMs) display a striking ability to predict next observations from Hidden Markov Models (HMMs) via in-context learning (ICL), but the algorithm underlying this capability remains undetermined: prior work has proposed several candidates without consensus, and none has been grounded in the model's internal activations. We close this gap with a three-stage pipeline. First, we empirically compare LLM behavior against a suite of candidate algorithms and narrow the space to three classes -- though no single class explains LLM behavior across all HMM settings and sequence lengths. Second, we derive theoretical connections between the three classes and show how each can be implemented in-context by a Transformer, validating the construction in a small trained Transformer. Third, returning to pre-trained LLMs, we introduce the Principal Activations Probe (PAP), a layer-wise probing and intervention method that isolates algorithmic signals in model activations. PAP reveals low-dimensional linear representations that causally drive model predictions and track empirical ICL performance. PAP further reveals how these representations shift with properties of the underlying HMM regime; distinct computational stages are localized to different layers. Together, our results connect the in-context behavior of pre-trained LLMs to the underlying internal mechanisms and advance our understanding of how LLMs perform ICL on HMMs. --- ### DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification Authors: Mohammed Yousif, Prabhjot Singh, Arjun Pankajakshan, Madhu Reddiboina Published: 2026-06-24 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.22644v1 Real-world document classification pipelines typically apply the same sequence of models to every incoming document, regardless of its complexity or type. This leads to inefficient use of compute and human resources: simple documents are over-processed while difficult ones may not receive enough scrutiny. We introduce DocHRL, a hierarchical reinforcement learning framework that learns to adaptively and dynamically select the most cost-effective classification policy on a per-document basis. DocHRL formulates document classification as a sequential decision problem with a two-level policy hierarchy: a top-level policy selects among broad options (vision classifiers, LLMs, OCR, and human-in-the-loop review), while option-specific sub-policies choose the concrete model or tool to invoke. The reward signal is the negative total expected cost, which captures inference cost, cost of misclassification, and cost of human labelling. Trained with Proximal Policy Optimisation on the RVL-CDIP benchmark, DocHRL achieves a macro F1 of 0.973 across 16 document classes while reducing average per-document cost to 2.74 normalised units compared to substantially higher costs incurred by fixed standalone classifiers. Our results demonstrate that cost-aware reinforcement learning can simultaneously improve classification performance and operational efficiency in document understanding systems. --- ### Reason Before You Retrieve: Agentic Planning for Multi-modal RAG Authors: Tianyu Yang, Shir Simon, Zhenzhen Li, Minhao Cheng, Xiangliang Zhang Published: 2026-06-24 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.22643v1 Multimodal retrieval-augmented generation (mRAG) aims to answer image-text queries with external knowledge, but most existing systems still retrieve directly from raw multimodal input over a flat evidence space. This design often struggles with two key challenges: the retrieval target is under-specified because the question intent must be grounded to the correct visual referent, and the search space is weakly structured, forcing semantically distinct evidence to compete in a single global ranking step. We propose MM-R2, a multimodal agentic retrieval framework that reasons before retrieval by explicitly modeling both what to retrieve and where to search. MM-R2 first constructs an intent-grounded retrieval state from the image-question pair, capturing the information need, grounded referent, and retrieval constraints. It then performs retrieval over a structured KnowledgeMap, where the agent selects relevant retrieval units before issuing grounded queries within them. To enable this capability, we build MM-R2-Traj, a large-scale trajectory dataset of multi-step retrieval processes, and adopt a two-stage post-training strategy with supervised fine-tuning and GRPO. Experiments on Infoseek and Encyclopedic VQA datasets show that MM-R2 substantially outperforms strong baselines on answer accuracy while also yielding more interpretable and verifiable retrieval trajectories. --- ### CRAFT: Learn the Schema, Execute the Plan Authors: Aakash Kolekar, Sahika Genc, Shahriar Shariat, Bunyamin Sisman, Tibor Mezi, Barbara Poblete, Shree Vandana Kachroo, Calvin Chi, Parth Parmar, Ari Singer, Prayaas Jain, Cindy Barker et al. Published: 2026-06-24 Categories: cs.AI, cs.CL, cs.LG, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2607.22642v1 Enterprise coding agents translate natural-language analytical requests into executable code over proprietary APIs, schemas, and metric definitions. Yet the prevailing deployment pattern injecting exhaustive schema and tool documentation into each prompt increases inference overhead, complicates schema evolution, and undermines reliability in multi-turn analysis. We investigate whether stable schema knowledge and tool-use behavior can instead be acquired through post-training while preserving the consistency required for production-facing analytics. We present CRAFT, a two-stage post-training recipe for schema-grounded coding agents. First, schema-stripped PLAN supervised fine-tuning learns domain-structured plans and executable behaviors from validated trajectories without exhaustive prompt-time schema injection. Second, execution-shaped reinforcement learning aligns the policy for tool selection, code quality, plan-code consistency, and recovery from failed executions. Training trajectories are curated through a Tri-Gate filter combining execution validation, data-integrity checks, and LLM-judge reasoning audit. We evaluate CRAFT for planned rollout in advertising analytics, covering campaign performance analysis, metric drill-downs, entity-level performance analysis, and multi-turn analytical refinement. The enterprise evaluation environment incorporates beta APIs as the agent-facing tool surface and spans 25 schema-linked core entities and 30 agentic workflows. Relative to a schema-stuffed baseline, CRAFT improves composite Agent Score by +9.6 pp, consistency by +4.1 pp, and multi-turn coherence by +4.2 pp, while reducing input-token burden by approximately 9x and schema-discovery loops by up to 5x. We further report deployment tradeoffs, reward-shaping limitations, and training-infrastructure extensions required for multi-turn tool-use reinforcement learning in enterprise settings. --- ### From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language Authors: Zachary Wojtowicz, Ayush Nayak, Jacob Andreas Published: 2026-06-24 Categories: cs.LG, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2607.16232v1 The growing use of statistical learning algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge: choice alternatives typically differ in many ways simultaneously, so it is generally unclear which factors actually drove an observed decision and should be credited as preferences. Compounding this problem, the opacity of these methods leaves human operators unable to inspect, contest, or correct models when they err. We introduce \emph{weights to words}, a method that takes a dataset of choice problems as input and automatically discovers a collection of domain-relevant preference dimensions, each described in natural language and paired with a vector in the model's representational space. These dimensions address both under-determination and opacity: they can be applied to concentrate attribution on a small set of meaningful factors, and they can externalize the model's inferences in natural language so that users can inspect and edit them in real time. We first qualitatively illustrate the method's versatility on four diverse domains: moral dilemmas, movies, wines, and free-form LLM responses. We then report two pre-registered human-subjects experiments, on moral dilemmas ($N=450$) and movie selection ($N=449$), that demonstrate its benefits for learning preference models: (1) regularizing a preference model toward the learned basis increases prediction accuracy on held-out choices, and (2) incorporating participants' structured edits further improves accuracy. In head-to-head comparisons, participants prefer the method's inferred preference profiles and endorse its predictions as more accurate. --- ### Orthogonal Gradient Constraints Shape Noisy-Label Memorization Dynamics Authors: Richard Mai Published: 2026-06-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.16231v1 Modern neural networks can fit corrupted training labels, making noisy-label learning a useful setting for studying memorization-driven overfitting. Most regularization methods modify the objective, architecture, or data distribution; here we instead study a geometric intervention on the optimizer update itself. We evaluate OrthoGrad, which removes the component of each weight gradient parallel to the current weight vector, in noisy-label image classification. On MNIST with small-data regimes, OrthoGrad improves test accuracy most clearly for CNNs while reducing corrupted-label fitting. Mechanism diagnostics based on weight norms and gradient-weight cosine similarity suggest that the projection has the strongest effect when the raw gradient contains a nontrivial radial component, and becomes weaker in larger-data regimes where gradients are already nearly orthogonal to weights. Additional CIFAR-10 ResNet-18 experiments show that the method can alter memorization trajectories but does not prevent eventual noisy-label memorization. These results support orthogonal update constraints as a useful diagnostic for studying learning dynamics, while showing that OrthoGrad is regime-dependent rather than universally regularizing. --- ### RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce Authors: Xianling Zeng, Zihan Yu, Sichen Zhao, Yalun Qi, Zhiming Xue Published: 2026-06-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.16230v2 Accurate pre-order shipping cost estimation is important in e-commerce because it affects price presentation, margin planning, and conversion. In practice, shipping cost is shaped not only by distance but also by destination demand mix, billable weight, dimensional pricing, surcharge triggers, and latent operational effects such as shipment consolidation. Static lookup methods therefore miss important sources of variation, while monolithic regressors may exploit strong but non-causal correlations. We propose RouteCost, a production-inspired multi-stage framework that decomposes the problem into time-aware demand forecasting, fee-card-informed baseline pricing, Stage 2 residual correction, and proxy-based box-consolidation inference. Route-level cost estimates are aggregated through a route-weighted expectation formulation to produce product-level shipping cost predictions. Across over 250,000 orders, 260 products, and 18 months of order history, the framework improves predictive quality and aggregate calibration while preserving route-level interpretability. --- ### RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce Authors: Xianling Zeng, Zihan Yu, Sichen Zhao, Yalun Qi, Zhiming Xue Published: 2026-06-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.16230v1 Accurate pre-order shipping cost estimation is important in e-commerce because it affects price presentation, margin planning, and conversion. In practice, shipping cost is shaped not only by distance but also by destination demand mix, billable weight, dimensional pricing, surcharge triggers, and latent operational effects such as shipment consolidation. Static lookup methods therefore miss important sources of variation, while monolithic regressors may exploit strong but non-causal correlations. We propose RouteCost, a production-inspired multi-stage framework that decomposes the problem into time-aware demand forecasting, fee-card-informed baseline pricing, Stage 2 residual correction, and proxy-based box-consolidation inference. Route-level cost estimates are aggregated through a route-weighted expectation formulation to produce product-level shipping cost predictions. Across over 250,000 orders, 260 products, and 18 months of order history, the framework improves predictive quality and aggregate calibration while preserving route-level interpretability. --- ### FinBench: Time-Gated Calibration and Uncertainty Benchmarking for Agentic Financial Forecasting Authors: Rishab Ghosh, Vinay Devarakonda Published: 2026-06-24 Categories: stat.AP, cs.LG, q-fin.CP, q-fin.PM arXiv: https://arxiv.org/abs/2607.16229v1 Large language models (LLMs) are increasingly used as components of agentic systems that observe, plan, and act. In finance, even "assistive" systems become decision-relevant once their outputs are used to size trades or allocate risk. A key failure mode is the confidence--competence gap: a model that is only slightly better than chance but consistently overconfident will, under typical bet-sizing rules, generate negative long-run growth. Existing benchmarks emphasize semantic understanding or point accuracy, but do not directly test probabilistic calibration under the temporal constraints and non-stationarity that define real markets. We introduce FinBench, a benchmark designed to evaluate calibration and uncertainty quality for financial forecasting in a setting that is (i) strictly time-gated to avoid look-ahead bias and (ii) evaluated with strictly proper scoring rules that penalize hallucinated confidence. FinBench tasks require models to output (a) a probability of positive return and (b) an 80% prediction interval for realized log return; evaluation uses the Brier score and the Winkler interval score, along with skill scores against hard baselines. This paper describes the benchmark specification and reports a small pilot run (one trading day; three liquid tickers; 33 forecasts) as a sanity check of the pipeline. The pilot illustrates how calibration-sensitive metrics distinguish between "confident but fragile" behavior and uncertainty-aware forecasting. --- ### A Physics-Informed Neural Network with a Modified Lorentzian Activation for Nonlocal Gradient-Flow Equations in Dynamic Density Functional Theory Authors: Dimitrios Gourzoulidis, Soumaya Elkantassi, Serafim Kalliadasis Published: 2026-06-24 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2607.15291v1 We develop a physics-informed neural network (PINN) framework for nonlocal partial differential equations arising in dynamic density functional theory (DDFT). Such equations are challenging for standard PINN methods because they involve nonlinearities, nonlocal interaction terms, and an underlying gradient-flow structure, often leading to slow convergence and difficult optimization. We adapt the PINN methodology to DDFT gradient-flow equations and introduce two computational components: a modified Lorentzian activation function that behaves approximately linearly for small inputs and decays toward zero as the input magnitude increases, and a precomputed discrete operator for evaluating the nonlocal convolution term efficiently during training. The method is tested on four examples in one and two space dimensions. In the first example, the exact stationary solution is known, while in the remaining cases the neural-network approximations are validated against reference solutions computed using continuous and discontinuous Galerkin finite element discretizations. Accuracy and physical consistency are assessed through $L^1$, $L^2$, and $L^\infty$ errors, together with mass conservation and free-energy dissipation. The results show that the proposed activation function accelerates convergence relative to the standard $\tanh$ function, while the overall framework maintains good agreement with the reference solutions and captures the expected gradient-flow behaviour. These findings demonstrate the potential of the proposed PINN framework for solving nonlocal gradient-flow equations arising in DDFT. --- ### Feedback-Coupled Memory Systems in Continuous Time Authors: Stefano Grassi Published: 2026-06-24 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.09714v1 The Feedback-Coupled Memory Systems (FCMS) architecture formalizes closed-loop coordination through four abstract operators, two of which - the agent update operator $f_i$ and the environmental update operator $Ψ$ - are left axiomatically undefined in the original framework. To address this, $f_i$ is defined by Mechanism-Based Intelligence (MBI), where agents update locally through a decentralized price mechanism and economic principles, and $Ψ$ is defined by the Coupled Memory Graph Process (CMGP), a non-Markovian framework where the environment is treated as a physical substrate that records and responds to trajectory history coherently without external forcing. The resulting continuous-time FCMS instantiation achieves Lyapunov global dissipativity governed by the computable threshold $4β^2 < 2ημγ^2$. This generalizes both the discrete FCMS stability condition $4ηβ^2 < γ$ and CMGP's physical bifurcation threshold $α_c = 1/K$, confirming that memory dissipation must outpace feedback gain as a universal organizing principle. Numerical simulation with $N=2$ agents and mean-field validation at $N=10^6$ confirm the stability threshold and the self-reinforcing coordination cascade that emerges when it is violated. --- ### Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction Authors: Yuchen Wang, Javal Vyas, Tong Liu, Mehmet Mercangoz Published: 2026-06-24 Categories: cs.AI, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2607.09713v1 A key step toward autonomous industrial operation is the ability to create and reconfigure control policies from natural-language requirement specifications, with minimal or no manual redesign. In this setting, policy generation by AI agents can be a credible path when paired with a plant-aware validator (e.g., a digital twin) that can check generated candidate actions before execution. However, practical deployment is constrained by inference latency and compute footprint: large cloud-based models are often too slow, opaque, or data-sensitive for edge closed-loop use. This work investigates whether a compact Small Language Model (SLM) can be retrained for control reasoning and embedded in a validator-guided correction loop. We use a Qwen2.5-1.5B model aligned via Group Relative Policy Optimization (GRPO), combined with (i) an action agent, (ii) a symbolic/digital-twin-style validation layer, and (iii) a reprompting agent that iteratively steers outputs toward valid actions. In randomized thermal-control simulations (30 experiments with 500 steps each), the framework achieves 91.5% average action-alignment accuracy (86.3%--100% across cases) at 3.84\,s mean inference latency. Under symbolic re-mapping, it maintains a 95% in-range rate, indicating robust physical regulation despite reduced token-level agreement. These results support SLM+validator architectures as a practical path toward reconfigurable autonomous control at the edge. --- ### Direct Time-of-Flight Measurement Accuracy Improvement With Perimeter-Gated SPADs Authors: Md Sakibur Sajal, Hunter Guthrie, Zexi Liu, Marc Dandin Published: 2026-06-24 Categories: physics.ins-det, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.02546v1 Direct time of flight (dToF) measurements are susceptible to errors because of system-level and circuit-level timing jitters. In addition, device-level uncertainty stemming from the dark noise of single-photon avalanche diode (SPAD) contributes to the aggregated error. We demonstrate that perimeter gating can help reduce the device-level detection inaccuracy for SPAD devices by reducing the dark noise probability. Specifically, in this work, we developed a general framework to accurately estimate the dToF jitters stemming from different source levels and analyzed a counter-based time to digital converter (TDC) circuit that are commonly used in such systems. We have also measured dToFs using a perimeter-gated SPAD (pg-SPAD) detector fabricated in a 0.35 $μ$m standard CMOS process. Experimental results show that pg-SPADs can improve measurement accuracy in both free-running and time-gated operations. --- ### Transformer-based Multisensor Data Fusion of Ultrasonic Guided Wave and FBG-based Strain Measurements for Multitask Aerospace Structural Health Monitoring Authors: Xin Yang, Morteza Moradi, Tongtong Yan, Jinbo Du, Yunlai Liao, Dimitrios Zarouchas, Dimitrios Chronopoulos Published: 2026-06-24 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2607.02545v1 Structural health monitoring (SHM) has emerged as an essential tool for ensuring the integrity and reliability of critical engineering structures, particularly in aerospace applications. Since each sensing technology has its limitations, the fusion of different modalities enables capturing a more complete picture of inhomogeneous materials, like composites. However, effective multisensor data fusion in SHM is often hindered by heterogeneous sensing modalities that operate at disparate sampling frequencies and acquisition intervals. To address these challenges, this paper proposes a Transformer-based data fusion framework that integrates multisensor data streams from piezoelectric transducer (PZT) capturing ultrasonic guided wave signals and fiber Bragg grating (FBG) sensors for strain measurements. By incorporating an attention-mechanism visualization, the proposed framework enables transparent, multitask learning for both health indicator (HI) prediction and damage localization. The framework was experimentally validated using aircraft composite structures subjected to compression-compression fatigue cyclic loading. For HI prediction, the framework consistently achieved a mean absolute error (MAE) and root mean squared error (RMSE) below 0.1, representing a nearly 60% performance improvement over single-sensor approaches (PZT or FBG alone) and baseline deep learning models. For damage localization, the model demonstrated the highest accuracy, maintaining an MAE and RMSE below 0.0465 and 0.1571, respectively. These results demonstrate that the proposed Transformer-based data fusion framework significantly outperforms single-source models and state-of-the-art deep learning models in both HI prediction and damage localization accuracy. --- ### Not Every Sync Is Safe: Calibrated DiLoCo Scheduling for Shared AI Infrastructure Authors: Maxwell Twelftree, David Lemphers, An-chi He, Yue Yang Published: 2026-06-24 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2607.02544v1 DiLoCo-style training reduces communication by letting learner islands train locally before occasional outer synchronization, making it attractive for fragmented industrial AI fleets where training shares hardware with latency-sensitive serving. The question for such fleets is when an outer merge is worth its system cost, and whether choosing \emph{which} windows to defer matters at all. Existing scheduling studies evaluate workload-aware policies against fixed-period baselines, but most omit the control that isolates timing from budget: matched random deferral, which inherits the controller's synchronization budget but is not itself deployable. This omission is consequential: across controlled stress tests and real vLLM sidecar replays, matched random ties or beats every forecast-free policy we test, so gains reported against weaker baselines cannot be attributed to window choice. We fill this gap with Workload-Aware DiLoCo (WA-DiLoCo), a score-based controller that weighs learner progress against fleet pressure, and a calibration protocol that determines when matched random can be beaten, then demonstrate that it can. In the bursty regime where calibration exposes request-overlap structure, adding a one-step EWMA burst forecast to the online controller beats matched random in real vLLM sidecar replay, reducing SLO violations from 6.54\% to 5.09\% (8 of 10 seeds, $p=0.021$); offline Calibrated-WA, a non-deployable bound, shows the remaining headroom at 4.45\% versus 6.26\%. The deployable lesson remains the protocol: report real-sidecar effect-size transfer, a no-sync load match, and a matched-random envelope before claiming serving-SLO improvement. --- ### iFLYTEK-Embodied-Omni Technical Report Authors: Yuan Zhang, Jingfei Ni, Guanchen Lu, Shiqi Zhang, Qingshan Xu, Chi Liu, Xin Nie, Wenjie Xu, Lin Gao, Zhiyuan Cheng, Mingxin Zhou, Jiajia Wu et al. Published: 2026-06-24 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.02542v1 General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-language reasoning, video-based world modeling, or action generation, while cascaded pipelines that first synthesize future observations and then infer actions can introduce interface bottlenecks and compound prediction errors. We present iFLYTEK-Embodied-Omni, a unified multimodal foundation model that jointly models vision(videos and images), language, and action within a single Omni framework. Its modality-specific visual-language, video-generation, and action-generation components communicate through shared multimodal self-attention. This design establishes brain-cerebellum collaboration: the vision-language modeland video generation model form a high-level brain for instruction understanding, task planning, progress tracking, and future visual-state prediction, whereas the action generation modelserves as a low-level cerebellum that directly converts planned subgoals and shared multimodal context into executable action chunks. To develop these capabilities, we combine action-annotated and action-free embodied videos from human demonstrations and robot interactions with embodied reasoning, embodied perception, and general-purpose image-text data to construct a comprehensive dataset. We further adopt a four-stage strategy that progressively trains the VLM, VGM, and AGM before jointly fine-tuning the complete model. --- ### Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models Authors: Davie Chen Published: 2026-06-24 Categories: cs.LG, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2606.28406v1 Text-to-image and multimodal generative models are increasingly used to produce scientific figures such as mechanism diagrams, experimental-design schematics, conceptual frameworks, and graphical abstracts. Yet existing image-generation benchmarks (e.g., GenEval, T2I-CompBench, DPG-Bench) evaluate natural images and measure compositionality, object counting, or photorealism. None of them measure what makes a generated scientific figure usable: correct and legible text labels, faithful depiction of entities and their relations, coherent diagrammatic structure, and adherence to disciplinary drawing conventions. We introduce SciDraw-Bench, a benchmark of 32 structured scientific-figure generation tasks spanning eight figure types and ten disciplines, where each task pairs a natural-language prompt with a machine-checkable specification of required labels, relations, components, conventions, and negative constraints. We propose a four-dimensional evaluation protocol: Text Fidelity (OCR-based label recall and character error rate), Semantic Correctness (vision-language-model judging against the specification), Structural Quality, and Convention Adherence, together with a meta-evaluation protocol and a preliminary inter-judge reliability analysis (human-rating validation is ongoing). We evaluate a domain-specific system, SciDraw AI, against representative general-purpose text-to-image models, and outline a code-to-figure baseline as a planned extension. In a pilot over all eight figure types, the domain-specific system substantially outperforms the general-purpose baselines on every dimension and figure type, with the largest gaps on semantic correctness and convention adherence; text fidelity remains the hardest dimension for all systems. --- ### Enhancing Layer Interaction Using Key-Correlated Layer Attention Authors: Jianlong Xiong, ChuanBo Xie, Le Yu, Quansong He, Tao He Published: 2026-06-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28405v1 Recent advances in network architecture design have introduced layer attention to enhance inter-layer interactions. In such frameworks, each layer queries all preceding layers to establish cross-layer connections. However, layer attention results in quadratic computational complexity with respect to network depth. To mitigate this issue, prior works have proposed Recurrent Layer Attention (RLA) and linear attention mechanisms, which suffer from static information updates and limited long-range cross-layer dependency modeling. To overcome these limitations, we propose Key-Correlated Layer Attention (KCLA), inspired by our observation that Key representations in layer attention exhibit high cosine similarity. KCLA achieves linear computational complexity while preserving dynamic information updates, directly derived from the foundational definition of layer attention. Furthermore, KCLA maintains long-range cross-layer connections and features a fixed spatial complexity, independent of network depth. Empirical evaluations demonstrate that KCLA delivers good performance across diverse tasks, including image recognition, object detection, and medical image segmentation. The code is publicly available at https://github.com/bgx666/KCLA. --- ### Financing Artificial Intelligence Infrastructure: Mapping AI Infrastructure Investment and Compute Governance Across Africa Authors: Kai-Hsin Hung, Sumaya Nur Adan, Krupa Suchak, Armita Sadeghian Barzoki, Kofi Yeboah, Mohammad Amir Anwar Published: 2026-06-24 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.28404v1 Artificial intelligence depends on large-scale compute resources and their supporting infrastructure. However, AI governance debates treat compute primarily as a technical input rather than as an outcome of investment, ownership, and financial control. This paper examines AI infrastructure investment flows across Africa through a systematic analysis of 46 publicly announced projects totalling USD $12.7 billion between 2019 and 2025. Using a value chain framework, we analyze who invests in AI-relevant infrastructure and where investments concentrate. Our findings reveal a highly concentrated landscape dominated by global data center operators, hyperscale technology firms, and development finance institutions, clustering in South Africa, Kenya, Nigeria, and Egypt. We introduce asymmetrical interdependence to describe a structural condition in which capital and physical infrastructure account for 73% of total funding while control remains concentrated in the compute layer among a small number of global technology firms. We argue that compute governance must account for capital flows, ownership, and control, not only geographic access, because these dynamics shape AI compute equity. Infrastructure presence is necessary but insufficient for meaningful governance capacity. --- ### Reinforcement Learning for Software Vulnerability Analysis: A Systematic Review with Emphasis on C/C++ Source Code and Static Analysis Authors: Bruno Caro-Vásquez, Carola Figueroa-Flores, Gastón Marquez Published: 2026-06-24 Categories: cs.SE, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2606.28403v1 Vulnerability detection in C/C++ software remains a major security challenge due to code complexity, manual memory management, and the limitations of traditional static analysis. Reinforcement Learning (RL) has emerged as a promising approach, particularly for fuzzing, test generation, program exploration, and, more recently, vulnerability detection and localization. Following PRISMA 2020 guidelines, this work reviews RL techniques for software vulnerability analysis, focusing on C/C++ source code and static analysis. We identified 21 primary studies published between 2015 and 2026 from major scientific databases and complementary searches. We analyze the addressed tasks, algorithms, state-action-reward-environment formulations, code representations, datasets, and evaluation metrics. Results show that 15 studies focus on fuzzing and guided exploration, only 3 on direct vulnerability detection, and just 1 on statement-level localization. Moreover, statically extracted structural representations such as Control Flow Graphs (CFGs) and Abstract Syntax Trees (ASTs) are rarely used as agent states, and benchmarks lack comparability. We propose a task- and formulation-oriented taxonomy and identify a key research gap: the absence of RL agents that use source-code CFGs as states to detect and localize vulnerable nodes. --- ### DCSNet: Multiscale Feature Aggregation for Small Medical Object Segmentation with Detection-guided Hierarchical Cropping Authors: Shanfeng Zhang, Bo Gou, Yue Cao, Lei Zhang, Zhang Yi, Tao He Published: 2026-06-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28402v1 Small object segmentation in medical imaging is primarily hindered by class imbalance and inherent boundary complexity. Consequently, conventional global networks frequently fail to detect sparse targets or suffer from severe edge degradation. To overcome these limitations, we propose the Detection-guided Cropping Segmentation Network (DCSNet), an end-to-end framework that transforms global dense prediction into a localized refinement process. This framework integrates two core components, namely Detection-guided Hierarchical Cropping (DGHC) and Multiscale Feature Aggregation (MSFA). The DGHC module leverages region proposals to dynamically extract object-centric features, effdataectively filtering out massive background interference to mitigate class imbalance. Subsequently, the MSFA module operates strictly within these purified regions, synergizing a Transformer encoder with a pixel-adaptive fusion strategy. This mechanism dynamically aggregates multiscale features to capture both semantic context and fine-grained details for sharp boundary delineation. Extensive experiments across three diverse medical datasets demonstrate that DCSNet significantly outperforms existing state-of-the-art methods, yielding substantial improvements in boundary precision and offering a highly robust solution for clinical micro-lesion segmentation. --- ### Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs Authors: Yunhun Nam, Jongheon Jeong Published: 2026-06-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.28401v1 Vision-Language Models (VLMs) have shown strong performance in visual understanding, yet they still suffer from hallucinations, generating content that is not grounded in the image. Preference alignment is a promising approach to improve visual faithfulness, but its success depends heavily on how preference pairs are constructed. Existing methods exhibit two key limitations; (a) intervention-based methods often introduce significant deviation from the policy distribution, and (b) sampling-based methods often underuse visual information during the construction. In this paper, we propose ViPSy (Vision-driven Preference Synthesis), a framework for constructing preference data that are both policy-aligned and visually grounded. Our framework consists of two stages; in the first stage, ViPSy derives a visual cue from recurring object-level content across semantically aligned image variants, so preference construction can rely on visual information rather than language priors. In the second stage, ViPSy conditions the policy's own rollouts on this cue, allowing candidates to be guided by visually grounded content while staying close to the policy's response distribution. The resulting candidates remain close to the policy's response distribution while better leveraging visual information from the image. Experiments show that the resulting VLM, preference-aligned with ViPSy-constructed preference pairs, achieves a new state-of-the-art in hallucination mitigation. Compared with the previous state-of-the-art method, it reduces hallucination rates on AMBER and Object HalBench by 35.7% and 24.5%, respectively. The resulting model further improves on general visual grounding benchmarks, e.g., MMStar, MMVP, and CV-Bench, while also yielding gains in semantic segmentation and ImageNet linear probing, underscoring the effectiveness of our framework in enhancing the model's visual capabilities. ---