Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Saturday 22 August

Computer Vision

Trustworthy Visual Quality Inspection under Data Scarcity in Manufacturing

Panagiotis Sapoutzoglou, Jessy Ribaira, Martin Kanounnikoff et al. (+3 more)

Automated visual inspection in manufacturing aims to replace slow and inconsistent manual checks, but its economic value depends on whether its decisions can be trusted enough to automate routine inspection while reserving human expertise for ambiguous cases. In production-line settings, defective samples are scarce, since the process is optimized to produce good parts, which limits any learning-based inspector trained on real data alone. Compounding this, defect decisions emitted as hard labels with no confidence estimate carry an asymmetric cost: a false reject wastes a good product, while a false accept may increase the risk of undetected defects progressing through the production process. We address both problems by mitigating data scarcity through the generation of synthetic defective samples with a diffusion model, and meeting the need for confidence-aware decisions with a Bayesian classifier that defers ambiguous units to human review rather than misclassifying them. These components are embedded in a staged pipeline of successive, complementary checks. We evaluate how synthetic augmentation affects classification and localization on a test set of real defects, and examine the system's trustworthiness at three points: the decision, the synthetic data, and the pipeline structure. This work-in-progress reports preliminary results suggesting that diffusion-generated defects, combined with uncertainty-aware classification, can lower the cost of reaching a trustworthy, deployable inspection model under data scarcity.
Read the full abstract

All authors Panagiotis Sapoutzoglou, Jessy Ribaira, Martin Kanounnikoff, Bas Tijsma, Christian Geiß, Maria Pateraki

Artificial Intelligence

Repo2Skill-Evo: Repository Skills Go Stale in Silence

Chenyuan Duan, Ge Shi, Zineng Mao et al. (+10 more)

Large language model (LLM) agents increasingly operate over evolving software repositories, where success depends on repository-specific procedural knowledge: which APIs to call, which scripts to run, and which conventions the current release expects. Agent skills externalize this knowledge into reusable units, and prior work shows that they can improve agent performance. What remains unclear is whether that improvement is durable. The same version specificity that makes a skill useful also makes it fragile: after a release, it may become stale without raising any explicit signal, while continuing to provide obsolete guidance. Externalizing knowledge into a skill can therefore make its decay invisible. We study whether agents can keep this externalized knowledge current. Repo2Skill-Evo casts each release transition as a skill-maintenance task: given a V1 skill set and the official V1-to-V2 patch, an agent must update obsolete skill content while preserving guidance that remains valid. Across 57 real-world repositories and 105 selected release transitions, every evaluated transition invalidates part of the V1 skill set. Yet six frontier agents reach only 29.9%-69.7% avg@3 macro F1 under a patch-grounded removal metric that balances stale-content recall against over-editing precision. Across runs, two opposing errors dominate: incomplete coverage of affected files in the skill set leaves stale content untouched, while overbroad editing is associated with higher recall but lower precision. Repository skills go stale in silence, and even frontier agents cannot reliably maintain them.
Read the full abstract

All authors Chenyuan Duan, Ge Shi, Zineng Mao, Ge Zhang, Hao Liang, Yinzhu Piao, Yuchen Wu, Zhixin Yao, Kaiyu Huang, Wenhao Huang, Linzhuang Sun, Shen Yan, Wentao Zhang

Hardware Architecture

NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus

Elisavet Lydia Alvanaki, Je Yang, Biruk Seyoum et al. (+1 more)

Large language models (LLMs) are increasingly used to generate register-transfer-level (RTL) designs from natural-language specifications. However, assessing functional correctness at early stages remains a fundamental challenge. Existing oracle-free approaches rely either on simulation-based agreement, which depends on LLM-generated testbenches that can fail or vary across models, or on LLM-as-a-judge heuristics, which produce inconsistent predictions. We introduce NoTB, an oracle-free triage framework that infers correctness from cross-model formal consensus. NoTB generates RTL implementations from multiple independently trained LLM families and applies Sequential Equivalence Checking (SEC) to identify designs that are provably equivalent. We show that the diversity of model families within an SEC-equivalent cluster induces a calibrated correctness signal, enabling risk-coverage tradeoffs without requiring testbenches. On 78 CVDP RTL-generation tasks, four-family formal consensus achieves 94.7% precision at 27% coverage; three-family consensus achieves 87% precision at 33% coverage. These operating points give designers a tunable accept/defer rule before a trusted testbench or golden RTL is available. Overall, NoTB demonstrates that formal cross-model agreement provides a reliable basis for high-confidence triage without model-dependent oracles
Read the full abstract

All authors Elisavet Lydia Alvanaki, Je Yang, Biruk Seyoum, Luca P. Carloni

Numerical Analysis

Smallest Singular Value Estimates for Nonuniform Fourier Matrices via Periodic Nonuniform Sampling

Liang Chen, Rongrong Lin and Haizhang Zhang

We study the smallest singular value of nonuniform Fourier matrices in two settings: clustered nodes and perturbations of an equispaced grid. By reducing the problem to spectral norm estimates for periodic nonuniform interpolation matrices, we obtain nearly optimal bounds in both cases. For clustered nodes, we derive the first local separation condition in which each required gap depends only on the sizes of the two neighboring clusters. For perturbations with the bound \(1/4\leq L<1/2\), our result confirms the conjecture of Austin and Trefethen on the \(2\)-norm Lebesgue constant up to a logarithmic factor.
Read the full abstract

Social and Information Networks

JECHO: Scalable Echo Chamber Detection via Jaccard-based Homophily and Seed Expansion

Ali Safarpoor Dehkordi, Atsushi Miyauchi, Francesco Bonchi et al. (+1 more)

Detecting echo chambers is critical for understanding and limiting negative social phenomena, such as online polarization, misinformation, and conspiracy theory diffusion. However, the echo chamber detection (ECD) problem yet lacks a rigorous algorithmic foundation. We address this gap by formalizing a unified definition of echo chambers based on three principles: internal opinion homogeneity, opinion extremism, and structural isolation. Under such a definition, we establish the theoretical hardness of the ECD problem, proving it is NP-hard via a reduction from the conductance minimization problem. To circumvent this computational barrier, we derive a theoretical lower bound on the Jaccard-based homophily (JHO) of nodes that reside within valid echo chambers. This guarantee motivates JECHO, a novel algorithm that detects echo chambers via local seed expansion rather than global enumeration. JECHO first identifies seeds that exceed the JHO threshold and then applies a score-based expansion to optimize structural isolation. Extensive experiments on real-world and synthetic networks demonstrate that our theory-guided approach detects more structurally isolated echo chambers than state-of-the-art methods while reducing runtime by orders of magnitude.
Read the full abstract

All authors Ali Safarpoor Dehkordi, Atsushi Miyauchi, Francesco Bonchi, Ahad N. Zehmakan

Artificial Intelligence

SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality

Hyunwoo Kim, Byoungchan Ko, Minseok Kang et al. (+5 more)

Recent advances in sequence modeling have highlighted Mamba as a state space architecture offering efficient long-range dependency modeling and providing a viable alternative to Transformers. Building upon this, Mamba-2 introduces the Structured State Space Duality (SSD), which integrates recurrent and attention modes to achieve efficiency and scalability. However, this architectural expansion substantially increases memory and latency overhead, underscoring the need for efficient compression strategies tailored to SSD. In this work, we present SSDi8, the first post-training quantization framework specifically designed for SSD to maintain a persistent INT8 path. SSDi8 introduces a reformulation that decouples element-wise multiplications from matrix multiplications, enabling reuse of quantized activations across modules. Moreover, SSDi8 adaptively quantizes channel-varying activations at cost-effective points, further reducing latency. On the accuracy side, SSDi8 explicitly leverages the intrinsic dimensional decomposition of SSD, exploiting distinct outlier distributions across axes, and incorporates an error correction term based on per-channel error statistics. Comprehensive experiments demonstrate that SSDi8 achieves accuracy comparable to FP16 while delivering up to 1.4x speedup in W4A8 and W8A8 settings. We further validate its robustness in resource-constrained environments by deploying it on the Orin NX device.
Read the full abstract

All authors Hyunwoo Kim, Byoungchan Ko, Minseok Kang, Minwoo Kim, Dongjin Lee, Jaehoon Lee, Sungroh Yoon, Dahuin Jung

Computation and Language

Bulbul: A Dataset for Dialectal Arabic Speech Recognition

Ahmed Ashraf, Aisha Alansari, Fadel Al Abbas et al. (+30 more)

Arabic automatic speech recognition (ASR) faces unique challenges due to diglossia, extensive regional dialect variation, and limited speech resources. Existing speech datasets often focus on single dialects or large-scale broadcast/web data, leading to trade-offs between linguistic diversity and annotation quality. We present BULBUL, a multi-dialect Arabic ASR dataset collected from 275 speakers in 11 Arab countries. BULBUL includes structured dialect and sub-dialect coverage, as well as recordings of classical Arabic and modern standard Arabic spoken by participants in their native dialectal accents to support accent-aware modeling. The quality of the recordings was ensured through a two-level human verification process. We further benchmark a range of recent ASR systems, establishing strong baselines for modern dialectal and accented Arabic ASR.
Read the full abstract

All authors Ahmed Ashraf, Aisha Alansari, Fadel Al Abbas, Nada Almarwani, Samah Aloufi, Saad Ezzini, Maged S. Al-Shaibani, Doaa Dalaq, AbdelRahim A. Elmadany, Muhammad Abdul-Mageed, Mohamed Mehdi Trigui, Dania Refai, Layan Refai, Mohamed Akrout, Mustafa Jarrar, Wasfi G. Al-Khatib, Alaa Dalaq, Darin El-Nakla, Samir Abdaljalil, Abdulrahman Al-Fakih, Nour El Imane Zeghib, Moussa Redah, Salmane Chafik, Mohamed El-Attar, Rima Grati, Sarah Kohail, Malak Alkhorasani, Khadijah Al Safwan, Ismail M. Mudhaffar, Ali Altam, Ahmed Al-Shaikh, Adnan Saeed, Hamzah Luqman

Software Engineering

Ontology-supported Design Parameter Management for Change Impact Analysis

Jan Novacek, Ali Ahari, Alessandro Cornaglia et al. (+4 more)

This paper presents an ontology-supported approach to the management of design parameters in engineering. This approach aims specifically at enabling Change Impact Analysis through Requirements Traceability and acquainted expert knowledge of design parameters. The approach is suitable for both software and hardware designs. The activities and features are mainly obtained by (1) the application of an ontology-based universal system modeling procedure proposal for model integration, (2) the utilization of a knowledge base for capturing expert knowledge and (3) a semantic Mission Profile Aware Design platform. OWL is used to represent information and the underlying data model can improve knowledge transfer among heterogeneous systems which are common in complex engineering projects. At the same time, effort to perform reasoning on such models can be reduced. A demonstration and hands-on description of two illustrative use cases complements the paper.
Read the full abstract

All authors Jan Novacek, Ali Ahari, Alessandro Cornaglia, Frederik Haxel, Alexander Viehl, Oliver Bringmann, Wolfgang Rosenstiel

Computer Vision

Sparse Multi-Stage Expert-Agent Routing for Complex Clinical Reasoning

Sike Xiang, Shuang Chen, Qian sun et al. (+3 more)

Complex clinical reasoning requires models to update diagnostic hypotheses as new evidence emerges and to coordinate different medical specialities under limited consultation resources. Existing LLM-based clinical reasoning systems typically perform single-pass prediction or rely on fixed multi-agent workflows, making expert participation either static or unnecessarily exhaustive. We propose Sparse Multi-Stage Expert-Agent Routing, a language-based clinical reasoning framework that models diagnosis as a stage-wise routing process. Given progressively available clinical evidence derived from multiple modalities, the framework maintains an evolving case state and adaptively activates a sparse set of medical expert agents, supported by expert-specific memory across stages. To evaluate free-text diagnostic conclusions beyond surface similarity, we further introduce ClinFEScore, a fact-aware semantic evaluation protocol for clinical reasoning outputs. On reconstructed multi-stage cases from MAC and AgentClinic-NEJM, our framework reduces the average number of activated experts from 17.0 to 3.0 whilst maintaining strong fact-level diagnostic quality. On 200 real-world hospital MDT cases, ClinFEScore correlates strongly with clinician judgements (Spearman's $\rho=0.81$; Pearson's $r=0.87$), whilst our method achieves 91.5% clinician-verified diagnostic accuracy with approximately five expert-agent/LLM calls per case. These results support sparse stage-wise coordination as an efficient and clinically relevant approach to LLM-based clinical reasoning.
Read the full abstract

All authors Sike Xiang, Shuang Chen, Qian sun, Jia Cheng, Yusi Wei, Amir Atapour-Abarghouei

Computation and Language

EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning

Can Xie, Yuyi Zhou, Wen Yang et al. (+5 more)

Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exploration patterns embedded in interaction trajectories are largely discarded after a single policy update. Existing experience-augmented approaches retrieve historical guidance at inference time, but they apply experiences without accounting for the policy's evolving capability and create persistent dependencies on external retrieval. We propose EDGE (Experience-Distillation for Guided Exploration), a framework that treats retrieved experiences as temporary training-time scaffolds and progressively internalizes their benefits into the parametric policy. Concretely, EDGE partitions each rollout group into experience-conditioned and experience-free trajectories to estimate and admit only positive marginal gains without extra sampling, then distills the induced behavior into the base policy via a reverse-KL objective on its own empirical support. A co-evolutionary experience bank further synthesizes guidance from emerging failure modes and prunes obsolete entries as the policy evolves. Across embodied, web, and search-based QA tasks, EDGE improves over strong RL baselines by up to 12.5 points and remains effective without inference-time scaffolds or a proprietary reflector. The code is available at https://github.com/xvolcano02/EDGE.
Read the full abstract

All authors Can Xie, Yuyi Zhou, Wen Yang, Ziyi zhang, Siyao Song, Yingzhuo Deng, Shuo Ren, Jiajun Zhang

Software Engineering

Ontology-based Requirements Transformation

Jan Novacek, Alexander Viehl, Oliver Bringmann et al. (+1 more)

This paper presents an ontology-based approach to the supply chain-aware transformation of functional and environmental load requirements given by so-called Mission Profiles (MPs). The approach aims at improving the efficiency of the engineering process through supporting the transformation process and enabling a better integration of the transformation into existing Model-based Systems Engineering (MBSE) processes. We propose a methodology and a supporting system which aids in the transformation process while the latter feature is obtained by constructing and working on models. Consequent utilization of the standardized language OWL to express model representations further enables better knowledge integration and transfer among hetero-geneous systems. In addition to that, this favors knowledge reuse across projects which can reduce overall costs. Moreover, the system enables stripping off irrelevant information from MPs, thus improving protection of intellectual property.
Read the full abstract

All authors Jan Novacek, Alexander Viehl, Oliver Bringmann, Wolfgang Rosenstiel

Artificial Intelligence

TessIndex: Capability Verified Identity System for the Agent Economy

Mehul Goenka, Tejas Pathak and Siddharth Asthana

Software systems have traditionally been organized around applications where human users act as principal decision-makers. Recent developments in agentic capabilities alter this paradigm: software agents now autonomously translate high-level goals into structured tasks, orchestrating tools, services and sub-agents to execute complex workflows. This evolution gives rise to an agent economy where these autonomous agents capture real economic value. However, the infrastructure required to support the agent economy fails across three critical dimensions: the absence of persistent identity infrastructure prevents systemic accountability in agentic workflows; capability claims remain self-declared not backed by verifiable execution evidence; and the disconnect between creator identities, agent performance, and project value hinders the economic valuation of agents as assets. While existing registries provide naming and discovery, unifying these features around a persistent identity anchor remains largely unaddressed. TessIndex is a capability-verified identity system for agent primitives that utilizes a dual-plane architecture: the blockchain records compact commitments for identity, ownership, and verification, while centralized servers maintain dynamic metadata for discovery, commerce, and reputation. It establishes: persistent identities across agent primitives to enforce systemic accountability in autonomous workflows; a predicate-based verification process replacing self-declared claims with cryptographic capability proof; an identity infrastructure that links agent performance to both project and creator identities while capturing value through tokenization. Ultimately, TessIndex serves as an integrated infrastructure that binds an agent's existence across capabilities, execution, and reputation into a single persistent identity.
Read the full abstract

Artificial Intelligence

Multimodal Prompt Learning with Irregular EHRs for Robust Monitoring of Critical Care Patients

Yixin Yang, Yueyang Sun, Weichen Liu et al. (+2 more)

Accurate assessment of patients in intensive care units (ICUs) is essential for timely clinical intervention and improved patient outcomes. Multimodal electronic health records (EHRs), including structured physiological time series and longitudinal clinical notes, provide complementary information for critical care prediction. However, in real-world clinical settings, individual modalities may be partially observed or entirely unavailable, resulting in substantial performance degradation for existing multimodal models. To address this challenge, we propose a multimodal prompt-learning framework for robust clinical prediction under diverse missing-modality scenarios. The proposed framework introduces four complementary types of prompts: generative prompts, missing-signal prompts, missing-type prompts, and temporal prompts. Generative prompts construct surrogate latent representations for unavailable modalities, while missing-signal prompts distinguish observed representations from generated ones. Missing-type prompts condition the model on different modality-availability configurations, whereas temporal prompts perform condition-specific aggregation over temporally encoded clinical sequences. Together, these prompts enable the model to capture missingness-aware intramodal dependencies and cross-modal interactions within a unified architecture. Extensive experiments demonstrate that our method outperforms existing approaches across evaluation metrics on two missingness settings. Ablation and robustness analyses further verify the complementary contributions of the four prompt types and the effectiveness of the proposed framework for clinical prediction from incomplete multimodal EHR data.
Read the full abstract

All authors Yixin Yang, Yueyang Sun, Weichen Liu, Xianbing Zhao, Sicen Liu

Information Retrieval

Enhancing Group Recommendation with Memory-Augmented Reasoning in LLM Agent

Qimeng Niu, Bowen Hao, Zixuan Zhang et al. (+2 more)

The core challenge in group recommendation lies in modeling the dynamic evolution of user preferences and explain?ing the consensus formation process. Existing Large Language Model (LLM)-based methods, despite improved interpretability, treat interaction history as fixed text, ignoring the natural evolution of group/user preferences over time, and lacking explicit modeling of the complex group decision-making process. To address these issues, we propose AGR, a LLM-based agent, which consists of a Memory Module and a Reasoning Module. The Memory Module employs a token-based hash table to dynamically manage the historical interactions of groups and users. This design supports fundamental operations including insertion, updating, retrieval, forgetting of irrelevant records, and summarization of evolving group and user profiles for efficiently tracking. Based on these retrieved dynamic profiles, the Reason?ing Module then performs a multi-step reasoning process includ?ing Group Interests Collection, Group Consensus Refinement, Multi-dimensional Evaluation and Explainable Recommendation Generation, thereby moving beyond black-box inference to de?liver fully interpretable recommendations. In practice, we adopt the Reinforcement Fine-Tuning (RFT) paradigm, where we first use Supervised Fine-Tuning (SFT) to equip the model with basic capabilities for invoking the Memory and Reasoning modules, and then employ Group Relative Policy Optimization (GRPO) to enhance its autonomous ability to coordinate these modules. Experiments on LastFM and Douban datasets demonstrate that AGR significantly outperforms existing state-of-the-art methods in both recommendation accuracy and explainability. Our model is open-sourced at https://huggingface.co/niuqimeng/AGR.
Read the full abstract

All authors Qimeng Niu, Bowen Hao, Zixuan Zhang, Shuyu Qu, Hongzhi Yin

Computer Vision

C$^2$Path: Class-Conditional Pathway Decoupling for Vision-Language Incremental Object Detection

Lecheng Xu, Feifei Shao, Ouyangzi Ye et al. (+5 more)

Incremental Object Detection (IOD) aims to enable detectors to continuously learn novel categories while preserving previously acquired knowledge. However, existing methods suffer from two forms of class knowledge coupling: class boundary erosion induced by shared parameter updates and class representation entanglement arising from mixed feature encoding. We argue that effective incremental learning requires class-specific computational pathways that enable isolated parameter updates and separated class-wise injection. To this end, we propose \textbf{C$^2$Path}, a class-conditional pathway decoupling framework for vision-language incremental object detection that leverages token-level class cues to establish dedicated and updatable computational pathways for different categories. Specifically, C$^2$Path introduces a category expert library and a class-conditional decoupling module. The expert library consists of learnable low-rank computational nodes that capture category-specific knowledge, while the decoupling module generates class-aware routing signals to dynamically compose ClassLoRA adapters from these experts, thereby forming class-specific computational pathways for isolated updates and separated injection across categories. Extensive experiments on COCO 2017 under multiple incremental learning settings demonstrate that C$^2$Path consistently outperforms state-of-the-art methods, providing an effective and scalable solution for continual category expansion in vision-language detectors.
Read the full abstract

All authors Lecheng Xu, Feifei Shao, Ouyangzi Ye, Zhen Wang, Lin Li, Kexin Li, Zhao Wang, Changqin Huang

Distributed Computing

Systematization of Knowledge: Formal Verification of Consensus Protocols

Nikita Bondarev, Kirill Ziborov and Yury Yanovich

Formal verification is increasingly critical for blockchain consensus protocols, where subtle bugs can cause irreversible financial loss and network failure. Yet the literature on verification methods is fragmented across tools, protocol families, and property classes, hindering cumulative progress. This Systematization of Knowledge paper analyzes over 20 verified consensus protocols–from crash-fault-tolerant Raft to Byzantine-fault-tolerant HotStuff, DAG-based FairDAG, and proof-of-stake Beacon Chain–to establish a unified taxonomy of verification approaches. We introduce a verification maturity scale ranging from informal reasoning to machine-checked code proofs, and present a Protocol–Property–Method matrix mapping protocols to verified safety, liveness, and economic properties. Our analysis reveals persistent gaps: liveness verification remains underdeveloped despite its importance for progress guarantees; specification-implementation disconnects undermine real-world assurance; and scalability limits restrict verification to small networks. We provide practical recommendations for tool selection and proof engineering, and outline a research roadmap toward scalable, economically-aware verification. This work aims to guide both researchers and practitioners in building more rigorously verified consensus systems.
Read the full abstract

Data Structures and Algorithms

Computing the Determinant via the Generalized Euclidean Algorithm

Janina Reuter

We present an algorithm with a natural geometric interpretation for computing the determinant of a matrix $B\in\mathbb{Z}^{d\times d}$. It improves upon the current fastest deterministic algorithms by a factor of $d^{\omega(1)+1-\omega(2)}\approx d^{0.1213}$, where $\omega(k)$ denotes the exponent required for multiplying a $d\times d$ matrix with a $d\times d^k$ matrix. Our approach builds on a recent result of Klein and Reuter (STOC 2025), who introduced a novel algorithmic idea for lattice basis computation that can be viewed as extending the Euclidean algorithm from $\mathbb{Z}$ to $\mathbb{Z}^d$. By adapting their techniques, we compute the determinant with the same bit complexity as applying the generalized Euclidean algorithm to an input matrix $A\in\mathbb{Z}^{d\times 2d}$ with $\|A\| = \|B\|$, namely $\tilde{O}(d^{\omega(2)}\log\|B\|)$. Prior to this work, the fastest deterministic algorithm for computing the determinant required $\tilde{O}(d^{\omega(1)+1}\log\|B\|)$ bit operations.
Read the full abstract

Numerical Analysis

A diffusion time-changed stochastic SIS epidemic model: well-posedness, long-time behavior, and numerical approximation

Xiaotong Li, Huaqian Zhou and Ruchun Zuo

In this paper, we propose and analyze a diffusion time-changed susceptible-infected-susceptible (SIS) epidemic model driven by time-changed Brownian motion. We prove that the proposed model admits a unique global positive solution for any initial value in $(0,N)$. The extinction and persistence of the disease are then investigated. To approximate the diffusion time-changed SIS model, we construct a positivity-preserving logarithmic Euler-Maruyama (LEM) method. Assuming that the time-changed is given by the inverse of a standard $\alpha$-stable subordinator with $\alpha\in(0,1)$, we prove that the numerical solution converges strongly to the exact solution with order $\alpha$. Finally, numerical experiments are provided to confirm the predicted convergence rates and illustrate the positivity-preserving property of the proposed method.
Read the full abstract

Cryptography and Security

SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agents

Yuanjin Zheng and Jingbang Chen

Agent skills extend coding agents with task-specific instructions, scripts, and resources, but they also create a trusted instruction channel that can be abused beyond conventional security attacks. This paper studies token amplification through skill injection: an economic resource-abuse threat in which a malicious skill causes an agent to consume substantially more tokens than needed for normal task execution. We present SkillBloat, a two-phase framework that first screens a library of diverse attack-type conditions across multiple amplification mechanisms and then refines the strongest candidate through LLM-guided full-document skill rewriting. Evaluated on a real-world skill benchmark, SkillBloat achieves 5.4184x-10.1455x average best amplification across multiple coding-agent target configurations. An ablation shows that the second-stage refinement loop consistently improves average best amplification over Phase 1 attack-type screening alone, demonstrating that iterative optimization provides additional benefit beyond initial attack-type selection. These results show that skill ecosystems expose a practical resource-amplification attack surface that is orthogonal to existing security-oriented skill poisoning.
Read the full abstract

Artificial Intelligence

GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI

Zhesheng Zhang, Jiahao Lu, Wei Liu et al. (+8 more)

In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied safety by varying visual contexts or evaluating execution-time dynamics, but the complementary axis of fixing the scene and varying only the instruction remains underexplored. We introduce GuardianBench, an instruction-contrastive benchmark grounded in international safety standards that isolates this latent contextual risk through 3,024 instruction-scene examples organized as same-scene Safe/Unsafe contrastive pairs across various hazard categories. Benchmarking state-of-the-art vision-language models (VLMs) reveals instruction-insensitive verdicts: models disproportionately approve both instructions under a given scene; across the primary models, average pair accuracy is only 24.1%. Our systematic rationale audit localizes the dominant failure: models fail to bind the instruction-relevant cues that differentiate safe from unsafe compositions. As a post-training case study, Verdict Log-Odds Supervision (VLOS), a lightweight verdict-level objective, substantially improves performance on open-weight backbones. Together, our latent contextual risk task formulation, standards-grounded contrastive benchmark construction, pair-level and rationale-level failure diagnosis, and benchmark-enabled verdict calibration establish GuardianBench as a controlled evaluation suite for exposing and improving safety reasoning over instruction-scene compositions under latent contextual risk.
Read the full abstract

All authors Zhesheng Zhang, Jiahao Lu, Wei Liu, Cong Pan, Jianhua Yang, Yixiang Chen, Hongyuan Yu, Mengqi Zhang, Kailin Lyu, Zhumin Chen, Keji He

Machine Learning

Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery

Yutao Lai, Kezhao Lai and Hai-Lin Liu

Zero-cost proxies enable neural architecture search (NAS) to rank candidate networks from statistics computed at initialization, avoiding repeated training. However, different proxies capture different properties and often produce inconsistent rankings across search spaces. Ensemble proxies can combine complementary signals, but automated discovery must optimize both discrete aggregation structures and their continuous coefficients, making structural quality difficult to separate from parameter calibration. We propose Bi-EZP, a bilevel framework that decouples these decisions. At the upper level, a large language model generates executable aggregation programs over four complementary base proxies with program-specific parameter bounds. At the lower level, covariance matrix adaptation evolution strategy (CMA-ES) optimizes the continuous parameters of each fixed program on an inner training split. The calibrated programs are then evaluated using Kendall's rank correlation on a disjoint validation split, enabling evolutionary selection to favor structures that generalize beyond their calibration data. Experiments on NATS-Bench and Network Design Spaces evaluate ranking performance across heterogeneous search spaces, and DARTS experiments assess downstream architecture search. Results show that separating program discovery from numerical calibration provides an effective approach to automated ensemble zero-cost proxy construction. The source code is available at: https://anonymous.4open.science/r/Bi-EZP-318D
Read the full abstract

Computer Vision

AirAlign: Geometry-Aware Relative Pose Alignment for UAV Last-Meter Navigation

Jinyi Zhou, Shuo Feng, Yufei Wu et al. (+1 more)

Unmanned aerial vehicle (UAV) navigation in modern low-altitude environments requires more accurate pose alignment in the final approach stage for target information acquisition or manipulation, making "last-meter" navigation increasingly important. However, severe viewpoint and appearance variations make this task challenging. To tackle this problem, we propose AirAlign, a framework for RGB-only image-pair relative pose alignment for UAVs. AirAlign uses a pretrained visual geometry reconstruction model as the backbone to extract geometry-aware features from source-target image pairs. In addition, to better utilize the limited training data, we split the training set into multiple scene-disjoint folds for unseen cross-validation and model selection. During inference, the predictions of the selected models are averaged to form the ensemble output of the overall framework. Experiments on the PairUAV challenge at the ACMMM 2026 Workshop on UAVs in Multimedia demonstrate the effectiveness and robustness of our method, while comprehensive ablation studies validate the contribution of each component.
Read the full abstract

All authors Jinyi Zhou, Shuo Feng, Yufei Wu, Piji Li

Artificial Intelligence

ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation

Weichu Liu, Yuxuan Hu, Yirong Sun et al. (+6 more)

Emotional Support Conversation (ESC) systems aim to provide holistic support by balancing professional therapeutic competence with natural empathy. However, existing methods struggle to simultaneously achieve structured, stage-aware reasoning and seamless empathy-expertise alignment, often resulting in an artificial splicing of clinical strategies and generic reassurance. To overcome these limitations, we propose ESCRAG-R1, a unified framework that integrates retrieval-based psychological guidance into Group Relative Policy Optimization (GRPO). By incorporating retrieval into the reinforcement learning loop, ESCRAG-R1 transforms external knowledge into a robust learning signal that stimulates explicit internal reasoning prior to generation and fundamentally reshapes the model's internal policy. To provide the reliable supervision required for this optimization, we construct ESC-Preference, a high-quality dataset based on a Client–Counselor–Judge evaluation framework that delivers precise, empathy-aware reward signals. Extensive experiments demonstrate that ESCRAG-R1 significantly outperforms existing baselines by mitigating superficial splicing and realizing a natural integration of professional guidance and empathetic expression. Code and datasets are released at https://github.com/Matcha-Liu/ESCRAG-R1.
Read the full abstract

All authors Weichu Liu, Yuxuan Hu, Yirong Sun, Ningning Mao, Ziyun Zhang, Jian Chen, Mingyang Xu, Qishan Zhong, Chengming Li

Computation and Language

Modeling Claim Dependency Structure for Patent Litigation Prediction with Graph Attention Networks

Takao Arai and Hiroyasu Inoue

Patent litigation imposes substantial costs on firms and distorts R&D incentives, making early risk identification a practically important task. While prior work has applied BERT-based models to patent claim text, two fundamental limitations remain: flat sequence encoding loses the dependency structure between independent and dependent claims that legally determines patent scope, and feeding the entire claim set to a single encoder discards legally critical text. A six-model ablation on 1.34 million USPTO utility patents confirms that per-claim encoding, graph connectivity, attention, and Attentional Aggregation each provide independent, additive predictive value. We propose ClaimGAT, a Graph Attention Network that encodes each claim independently, constructs a directed claim dependency graph, processes it with GATConv layers, and aggregates independent claims via Attentional Aggregation to yield both a litigation risk score and claim-level gate weights that enable post-hoc structural analysis. ClaimGAT achieves an AUC-ROC of 0.818 and a lift of 4.89x at the top 10%, using only information observable at the time of patent grant. It reveals a tendency in high-risk patents for structural selection and content sensitivity to diverge, a pattern consistent with defensive claim drafting.
Read the full abstract

Machine Learning

Beyond Fixed Directions: Adaptive Representation Analysis of Reasoning and Memorization in LLMs

Shaheen Nabi

Recent work has proposed that reasoning and memorization in language models can be characterized by a single representation direction, including methods that keep this direction fixed during reinforcement learning. We test two assumptions behind this view. First, are reasoning-oriented and factual-recall task groups approximately single-direction separable? Second, does the resulting geometry remain stable after GRPO? Using Qwen3-0.6B and a controlled 400-example dataset, we find that a one-dimensional projection can match a full 1024-dimensional linear probe with AUROC = 1.00 on the studied task groups. However, after GRPO, the corresponding direction is substantially reorganized: mean-direction cosine averages 0.453, probe-direction cosine 0.445, while direct representation drift reaches 0.511 at the final layer. Probe AUROC nevertheless remains 1.00. The evidence therefore supports single-direction decodability for the studied task groups but challenges fixed-direction stability: the information persists while its geometric realization changes.
Read the full abstract

Multiagent Systems

OptiMAS: Automatically Optimize Multi-Agent System

Yuxin Cheng, Chang Liu, Hanxin Yu et al. (+9 more)

Automated evolution of Multi-Agent Systems (MAS) holds significant potential for reducing the manual effort required to design and optimize LLM-based agent architectures. However, extant search-based paradigms face a fundamental trade-off, where an expanded optimization scope exacerbates evolutionary instability, while discrete branch-and-discard search isolates insights across lineages. To address these limitations, we propose a continuous, data-driven optimization paradigm built upon a unified ReAct-based infrastructure that reconciles a broad optimization scope with operational stability. Under this paradigm, we present OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution. Equipped with a novel dual-track memory mechanism, OptiMAS sustains performance improvement over extended optimization horizons. Evaluation on four heterogeneous agentic benchmarks with three varying scale and accessibility LLM backbones, demonstrates that OptiMAS consistently achieves competitive or superior accuracy relative to both domain-specialized hand-crafted systems and existing evolutionary methods. Our work establishes a practical milestone toward robust, automated MAS evolution.
Read the full abstract

All authors Yuxin Cheng, Chang Liu, Hanxin Yu, Haochen Tan, Taiqiang Wu, Weiqiang Jin, Jie Ran, Kaibo Wang, Xiaoguang Li, Haoli Bai, Graziano Chesi, Ngai Wong

Computational Engineering

GenomeHarness: Harnessing Al Agents for Reliable Adaptation of Genome Language Models

Weicai Long, Yusen Hou, Houcheng Su et al. (+2 more)

Pretrained genome language models provide reusable representations for DNA sequence analysis, but turning them into reliable downstream predictors remains non-trivial. Their practical performance depends strongly on fine-tuning recipes, and default recipes reported in prior studies may be suboptimal for new tasks or model backbones, making weak downstream results difficult to interpret. These requirements place a substantial operational burden on many intended users, whose expertise is often centered on biological questions and interpretation rather than machine-learning engineering. Reliable use of genome language models therefore requires more than conventional AutoML-style tuning: it requires a systematic, budget-aware, and auditable procedure that lowers the barrier to downstream adaptation. We present GenomeHarness, an agentic harness for adapting genome language models through controlled search over fine-tuning recipes. GenomeHarness combines an AI agent for proposing and repairing recipe edits, a harness for protocol-constrained execution, resource management, and test isolation, and a Monte Carlo tree search controller for allocating search effort across recipe lineages. We evaluate GenomeHarness on DNABERT2 and NTv2-100M-Multi across the NT Benchmark and Genomic Benchmarks. Final evaluation is performed using three random seeds after recipe freezing. Across 52 model-task settings, GenomeHarness improves mean test MCC in 47 settings, including 24 of 26 DNABERT2 settings and 23 of 26 NTv2-100M-Multi settings. The gains are especially pronounced on Genomic Benchmarks and on tasks where the root recipe is unstable or poorly matched, such as human ocr ensembl task. Search traces further show that GenomeHarness progressively identifies stronger recipes, turning downstream adaptation into a controlled and auditable workflow rather than a manual tuning process.
Read the full abstract

All authors Weicai Long, Yusen Hou, Houcheng Su, Junning Feng, Yanlin Zhang

Artificial Intelligence

Consistency Is Not Coherence: Orientation Search for Certified Alignments Between 4D Defence Upper Ontologies

Fabio Rovai

We align three upper ontologies that sit under UK and NATO defence data infrastructure: the Information Exchange Standard (IES), the Higher Quality Data Model (HQDM) that underpins the National Digital Twin, and Basic Formal Ontology (BFO). No public alignment between IES and HQDM existed. Promoting a hand-curated 17-correspondence crosswalk to OWL and reasoning over the complete merged ontologies with HermiT produces three results that we believe matter beyond this pair.
Read the full abstract

Computer Vision

Entity-Constrained CBCT Retrieval for Low-Resource Dental Record Completion

Nhi Ngoc-Yen Nguyen, Thai Nguyen, Kiet Huynh Cao Tuan et al. (+1 more)

Completing dental records from cone-beam computed tomography (CBCT) is difficult when annotation is scarce and individual clinical fields are supported by different types of evidence. MMDental Task 3 requires seven-field record completion from only 50 labeled CBCT cases and scores the correctness of structured FDI positions and ICD codes; consequently, a visually plausible retrieved record can still be harmful when it introduces an unsupported entity. We propose Entity-Constrained CBCT-Guided Retrieval (ECCR), a parameter-free framework that separates evidence availability from evidence authority. A corpus-derived prior first supplies the complete record. A frozen 3D encoder retrieves image-conditioned Diagnosis evidence, which is appended only if it does not expand the prior FDI or ICD entity set, so the asserted entity set is invariant by construction. On public validation, ECCR reaches a weighted score of 0.3134, improving on both full-record multimodal retrieval (0.2237) and a static text-only prior (0.2915); the guard blocks 63.3% of retrieved candidates, each of which would otherwise have injected an FDI position or ICD code absent from the prior. On the final test evaluation, ECCR obtains 11.37 of a 97.4-point attainable maximum, securing second place overall. The result indicates that, in an extreme low-resource setting, controlling what multimodal evidence is allowed to modify can be more reliable than transferring an entire retrieved record.
Read the full abstract

All authors Nhi Ngoc-Yen Nguyen, Thai Nguyen, Kiet Huynh Cao Tuan, Huy-Hieu Pham

Data Structures and Algorithms

The Parameterized Periodicity Lemma

Rikuya Hamai, Yuto Nakashima and Shunsuke Inenaga

Fine and Wilf [Proc. Amer. Math. Soc. 1965] showed that any string of length at least $p+q-d$ with periods $p$ and $q$ also has period $d=\gcd(p,q)$. For parameterized strings, Apostolico and Giancarlo [Discrete Appl. Math. 2008] proved an analogue with length bound $p+q$, assuming that the two induced bijections commute. Ideguchi et al. [SPIRE 2023] removed this assumption and gave the bound $p+q+\min(p,q)(\sigma-1)$, where $\sigma$ is the number of distinct letters. This was later improved by Hamai et al. [SPIRE 2024] to $p+q+\min(p,q)(\sigma-2)$, which was used to bound the number of non-equivalent parameterized squares. In this paper, we establish the optimal Fine–Wilf type bound for parameterized strings. Namely, if a string $s$ containing $\sigma$ distinct letters has parameterized periods $p$ and $q$ and satisfies $|s| \ge p+q+(\sigma-3)d+1$, where $d=\gcd(p,q)$, then $d$ is also a parameterized period of $s$. We also give matching lower-bound instances, proving that our bound is optimal for any $\sigma \geq 2$.
Read the full abstract