跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 23:50 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 00:24 — 2026-11-10 00:24（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 23:50最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 23:48（北京时间）
版本更新 · v2arXiv:2610.22335

Illumination-Aware Active Perception for Spacecraft Inspection

Sagarika Rao Valluri, Benjamin Riviere

原文摘要

Harsh and rapidly varying orbital illumination introduces failure modes during spacecraft inspection. Existing planners rely on line-of-sight inspection metrics which perform occlusion checks against a known target and conflate geometric visibility with task-relevant information. These metrics overlook illumination effects including eclipse, self-shadowing, and specular reflection from spacecraft materials and tend to declare components as inspected despite the corresponding images lacking sufficient information. We propose an inspection-planning framework that replaces geometric visibility with a learned measure of camera information derived from a classifier variational autoencoder (VAE) that operates directly on the captured image. The encoder model is trained to classify spacecraft surface components from rendered patches, and its total latent variance is used to learn the varying illumination of said components, replacing binary visibility checks with a continuous, image-grounded quantity. We evaluate the approach by implementing a Guidance, Navigation, and Control architecture in a photorealistic physics simulator, and vary lighting and viewing geometries with multiple orbits. We show that, although all approaches successfully maximize their own objective, our approach results in better illumination: a mean brightness of $0.57$, with $81.6\%$ of observations above $0.25$, compared with $0.02$ ($3.0\%$) for geometric planning with an illumination band and $0.04$ ($6.0\%$) for purely geometric planning.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31743

Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems

Mingxiu Cai, Haoyang Xian, Xinyu Ma, Yutong Wang, Zhenxi Song, Jing Li, Xuebo Liu

原文摘要

Large language model (LLM)-based multi-agent systems (MAS) rely on role-specific prompts and execution models to solve complex tasks collaboratively. However, prompt optimization typically keeps model assignments fixed, leaving differences in role requirements and their associated inference costs outside the search. We present UniMASO, a Unified framework for heterogeneous Multi-Agent System Optimization through the joint adaptation of prompts and model assignments. UniMASO evaluates candidate updates through local, downstream, and global feedback, using cost-aware Pareto search to retain useful quality-cost trade-offs. Topology-aware co-evolution then coordinates these updates according to agent roles and dependencies. Cross-level trajectory memory further supplies historical successes and failures to guide subsequent optimization. Experiments on five benchmarks and five execution topologies show that UniMASO achieves competitive task performance at substantially lower deployment cost than the strongest homogeneous configurations. Under centralized execution, it improves the average score from 69.79 to 70.40 while reducing token-weighted deployment cost by 85.2% relative to DeepSeek-V4-Pro with MASPO. These results support joint prompt-model adaptation as an effective approach to efficient multi-agent collaboration. The code is available at https://github.com/Achilles008/UniMASO_main.

cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.17713

Certified bounds on optimization problems in quantum theory

Younes Naceur, Jie Wang, Victor Magron, Antonio Acín

原文摘要

Semidefinite relaxations of polynomial optimization have become a central tool for addressing the non-convex optimization problems over non-commutative operators that are ubiquitous in quantum information theory and, more in general, quantum physics. Yet, as these global relaxation methods are solved numerically, the bounds issued by the semidefinite solver can - and often do - exceed the global optimum, undermining their certifiability. To counter this issue, we introduce a framework for extracting rigorous certified bounds on non-commutative optimization problems from inexact numerical data, and apply it to several paradigmatic problems in quantum information theory. An extension to sparsity and symmetry-adapted semidefinite relaxations is also provided and compared to the general dense scheme. Our results establish rational post-processing as a practical route to reliable certification, pushing semidefinite optimization toward a certifiable standard for quantum information science.

quant-ph · cs.SC · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35098

Interpreting LLM Scores in Peer Review: Alignment and Divergence Across Prompts, Domains, and Manuscript Features

Wenqiang Qin, Renlong Jie, Yanjun Qian, Salma Srifi

原文摘要

Large language model (LLM) scores are being studied as information for scholarly evaluation. Interpreting these scores requires evidence about agreement with human judgments and its variation across evaluation conditions. Guided by an argument-based approach to validation, we compare four LLMs on 7,083 public ICLR 2024 submissions under a standard review condition and examine ten prompt conditions using DeepSeek-V3.2. We distinguish average score divergence, paper-level absolute error, and rank correlation, then examine domain differences and adjusted manuscript-feature associations. For DeepSeek-V3.2, Area Chair guidance reduces mean rating divergence from 1.460 to 0.199 points and mean absolute error from 1.577 to 0.942, while rank correlation changes from 0.377 to 0.387. Historical references combined with downward scoring instructions yield mean divergence of 0.052 and rank correlation of 0.321. Domain differences remain after global calibration. Longer titles have positive adjusted associations with rating divergence, and formula density has negative associations across all four configurations. These findings connect score interpretation to the scoring procedure, evaluation context, and manuscript information represented in the comparison. They show why aggregate alignment, manuscript ordering, and correspondence within manuscript groups require distinct evidence when evaluating LLM-generated scholarly assessment information.

cs.DL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35094

RAGing Against Misogyny: Improving Implicit Misogyny Explanations

Ivana Crescenzi, Arianna Muti, Maarten Sap, Tommaso Caselli, Debora Nozza

原文摘要

Implicit misogyny often requires background knowledge to be understood. To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework for detecting and explaining implicit misogyny in English and Italian, leveraging encyclopedic, slang and feminist knowledge sources. Using the ImplicIT-Mis and SBIC+ datasets, we evaluate the contribution of each knowledge source to detection and explanation quality, investigating also whether RAG addresses known LLM failure modes in implicit misogyny. Results show that RAG improves recall on ImplicIT-Mis, but does not improve detection performance on SBIC+. However, human evaluation shows that RAG-based explanations are preferred over no-RAG explanations in both languages. Feminist literature emerges as the most consistently useful source for detection and explanation.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35093

Improving Instruction Hierarchy by Learning from Goal-Goal Conflicts

Sizhe Chen, Sanjay Kariyappa, Liwei Jiang, Chong Xiang, Jihye Choi, Chaowei Xiao, G. Edward Suh

原文摘要

The recent incident in which OpenAI agents autonomously compromised Hugging Face's infrastructure illustrates the importance of instruction hierarchy (IH): an LLM should follow lower-priority instructions, such as user requests, only when they do not conflict with higher-priority instructions, such as system policies. IH can be effectively improved by fine-tuning LLMs on simulated examples of instruction conflicts, whose diversity is key to teaching LLMs to properly handle conflicts at test time. However, our decomposition of a task into goals and constraints reveals a conflict type -- goal-goal conflicts -- that is absent from existing IH training sets from OpenAI and NVIDIA. We show the importance of this conflict type: fine-tuning Qwen3.5-9B and Gemma4-12B-it on examples of this conflict type significantly improves IH on a wide range of real-world tasks unseen in training; adding these examples to existing IH training sets for fine-tuning also gives better IH adherence. The IH gains come with trivial mean utility changes on no-conflict tasks across eight benchmarks. Our work advocates including this new conflict type in IH training, even if these examples do not reflect typical LLM use.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35092

Uncertainty Evaluation to Support Safety of the Intended Functionality Analysis for Determining the Applicability of Performance Targets Across Triggering Conditions in ML-Based LiDAR Object Detection

Milin Patel, Rolf Jung

原文摘要

For safety of the intended functionality (SOTIF) analysis according to ISO 21448, a machine learning object detector for light detection and ranging (LiDAR) point clouds can meet a performance target, a limit on the mean per-frame share of wrong detections among accepted detections, by rejecting detections above an uncertainty threshold. A threshold selected on data of one condition carries a statistical guarantee only for data distributed like its selection data, whereas SOTIF analysis covers every triggering condition. This paper presents an uncertainty evaluation in which the threshold is transferred into a triggering condition, a test decides at a stated error probability whether the target is applicable there, not applicable or not determined, and a lower bound counts the independent units an applicable outcome requires. For PointPillars ensembles on KITTI and nuScenes, counted in recorded sequences, as the dependence between frames requires, neither dataset held enough independent units for any target limit, and no transfer had a not applicable outcome. Counted in frames, the same data gave not applicable outcomes at limits fixed in advance after transfers into far distance, into rain and between two separately trained detectors, thresholds that met the target limit after a transfer rejected most correct detections, and in rain the area under the receiver operating characteristic curve did not decrease. A performance target met under one condition therefore counts as evidence under a triggering condition only after a test there, reported with its share of accepted correct detections and its number of independent recorded sequences.

cs.CV · cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.17469

Local Search with Correlated Randomness

Yunbei Xu

原文摘要

The running-time distribution of a randomized algorithm is computed under independent randomness, but independence is rarely what a source guarantees. We study sources $ν$ satisfying $ν[w]\le DP[w]^s$ for every finite prefix $w$ of the random tape, where $P$ is an independent reference law, $0<s\le1$, and $D\ge1$; individual choices may be predictable, even determined by the past. The worst-case probability of any closed tape event $E$ is exactly $\min\{1,DC_s(E)\}$, where $C_s(E)$ is the infimum cost of covering $E$ by prefixes of varying depth, a tree max-flow/min-cut identity that makes worst-case survival probabilities exact and optimizable over the algorithm's choices. Three applications follow. For $n$ tasks on one machine, each retried until the next random symbol lies in its success set, every schedule has the same makespan distribution under independent randomness, yet under our constraint two fixed orders miss a linear deadline with worst-case probabilities $1$ and $\exp[-Θ(n)]$; a static priority rule is optimal at every deadline. For the standard local walk on a $k$-CNF with an assignment that satisfies a majority of each clause, we determine the sharp source threshold $s_*$. Below $s_*$, on some instances a single admissible source forces nontermination however clauses are selected; at $s_*$, with fixed $D$, the expected number of flips is at most cubic in the initial Hamming distance, against linear under independence, with matching worst-case instances; and any fixed margin above $s_*$ restores linear dependence on the distance. Third, verified backtracking for noisy predecessor search remains correct under a sufficiently strong bound on the comparison errors. In every setting the algorithm may also restart, which supplies no fresh randomness; restarting restores exponential tails exactly when the nontermination event has a prefix cover of cost below one.

cs.CC · cs.LG · math.CO · math.PR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.02418

Reduced-Feedback Hybrid Precoding for Wideband mmWave MIMO-OFDM Systems via Hierarchical Interpolation

Po-Heng Chou, Jia-Qing Lin, Wei-Chen Lin, Wan-Jen Huang, Ronald Y. Chang

原文摘要

In this paper, we propose a feedback-efficient hybrid precoding framework for wideband millimeter-wave (mmWave) multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. To reduce the hardware cost of radio-frequency (RF) chains and the feedback burden associated with frequency-selective digital precoding, frequency-flat analog precoders and combiners are first constructed from the dominant angle-of-arrival (AoA) and angle-of-departure (AoD) directions associated with the strongest propagation paths. For digital precoding, a shared quantized codebook is designed using the Lloyd algorithm, and a binary-search-based hierarchical interpolation method is developed to identify codeword switching locations between adjacent pilot subcarriers. By avoiding exhaustive codeword comparisons over all intermediate subcarriers, the proposed method reduces online search complexity and enables compact digital-precoder feedback. For the considered system configuration, the proposed method achieves a worst-case feedback reduction of approximately 98.34% relative to full-grid per-subcarrier feedback. Simulation results further demonstrate competitive spectral efficiency and bit error rate (BER) performance, low computational cost, and robustness under imperfect effective channel state information (CSI).

cs.IT · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35090

Test-Time Prompt-Agnostic Decomposition

Junze Wang, Lei Fan, Dezheng Zhang, Donglin Di, Yang Song, Sidong Liu, Cong Cong

原文摘要

Test-Time Prompt Tuning (TPT) adapts large pretrained models to unseen target distribution shifts by updating only lightweight prompt tokens. Existing TPT methods are effective, but they mainly optimize each prompt update locally. Across test-time steps, prompts updated at the current step are reused for the corresponding predictions and updates, so noisy or biased unlabeled objectives can accumulate and destabilize the prompt-update trajectory. We identify two failure modes: magnitude expansion, where updates move the prompt too far, and directional drift, where consecutive updates point in inconsistent directions. To analyze and control these failures, we propose Test-Time Prompt-Agnostic Decomposition ($\mathtt{TPD}$), which characterizes observed prompt-update trajectories from a dynamical-systems view and decomposes base prompt updates into magnitude and direction. $\mathtt{TPD}$ computes a spectral radius to measure update expansion and decomposes update directions into persistent, oscillatory, and residual components. Building on this decomposition, Adaptive Koopman Control ($\mathtt{AKC}$) regulates update magnitude by shrinking updates under expansive recent dynamics, while Hankel Update Router ($\mathtt{HUR}$) refines update direction by preserving persistent components and suppressing oscillatory and residual components. Together, $\mathtt{AKC}$ and $\mathtt{HUR}$ produce a stabilized prompt update. As a prompt-agnostic framework, $\mathtt{TPD}$ can be plugged into visual and text TPT methods without modifying the backbone, prompt architecture, or adaptation loss. Experiments on 15 datasets show that $\mathtt{TPD}$ consistently improves 10 baselines, with accuracy gains of $3$--$8\%$ for visual prompts and over $2\%$ for text prompts.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35089

Learning to Remember: Advances in Memory Mechanisms for Large Language Models

Chenye Han, Hongche Yu, Mengyue Wu, Dell Zhang, Jixiang Luo

原文摘要

Memory has become a central mechanism for extending large language models (LLMs) beyond fixed context windows, stateless interaction, and static parametric knowledge. This survey organizes the literature around three complementary dimensions: the life cycle of memory, the storage substrate, and the system role that memory plays in LLM-based agents, while using cognitive-science-inspired memory concepts as a lightweight conceptual motivation rather than as a separate technical contribution or implementation family. On this basis, we distinguish three mechanism families: nonparametric memory, where information is stored outside model parameters in text, graph, multimodal, or database-like structures; parametric memory, where information is stored or accessed through activations, key-value caches, learned modules, adapter-based parameterizations, or model weights; and memory for agent evolution, where stored experiences support reinforcement learning, continual learning, procedural reuse, context engineering, and agent harness design. Evaluation is treated as a separate cross-cutting component rather than as a memory mechanism. Unlike surveys that focus primarily on retrieval-augmented generation or long-context modeling, this paper emphasizes the full memory life cycle: construction, maintenance, retrieval, consolidation, forgetting, governance, and evaluation. By aligning conceptual motivations, computational memory mechanisms, benchmarks, and deployment concerns, the survey provides a structured roadmap for designing memory-augmented LLM agents that are persistent, adaptive, auditable, and safe to update over time.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2410.21657

A-UTE: Advection Informed, Uncertainty Aware Temperature Emulator

Hira Saleem, Cormac Purcell, Steven Sherwood, Flora Salim

原文摘要

Physics-based Earth system models (ESMs) are essential for attributing climate change and generating scenario projections, yet their reliance on high-resolution numerical integration makes multi-decadal experiments expensive. In parallel, deep learning has delivered strong gains in short-range weather forecasting; however, auto-regressive roll-outs can accumulate error and become unstable when extended to decade-scale climate emulation. We introduce A-UTE: Advection Informed, Uncertainty Aware Temperature Emulator, aimed at stable multi-year emulation across heterogeneous climate models and grid resolutions. A-UTE is trained on various physics-based models at varying spatial resolutions to emulate temperature fields over a 10-year horizon. A-UTE formulates climate emulation as a forward-time stochastic dynamical system. We propose an auto-regressive ODE-SDE surrogate in which transport dynamics are constrained by an advection consistent ODE component, while a learned neural SDE term models coarse-grained variability and cross-model discrepancy at monthly resolution. We train A-UTE under negative log-likelihood objective for principled uncertainty estimates and probabilistic evaluation. Experiments across 20 climate models show that A-UTE improves long roll-out stability and accuracy relative to relevant baselines, advancing data-driven climate emulation with explicit physical structure and uncertainty-aware predictions.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.18818

Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs

Divyanshu Bathla, Parag Singla, Jitin Singla

原文摘要

Pre-trained Large Language Model (LLMs) are effective on many tasks in zero-shot and few-shot settings. For machine translation of low-resource languages, the obvious options are few-shot prompting and fine-tuning on a small parallel set. We ask: what if moderate amounts of low-resource monolingual data are also available? We argue that, rather than continued pretraining, a more effective use of this data is the pre-LLM era technique of back-translation (BT). The current fine-tuned LLM translates monolingual sentences in each language, and the resulting pairs train it in the reverse direction. Updates on the parallel set are interleaved for stable learning. With 1K parallel pairs on Odia and Swahili, BT beats continued pretraining into the low-resource language by 7.7 to 16.4 XCOMET-XXL points in domain. With beam-decoded intermediate translations, it also beats a model with 10 time more parallel data. In-context examples retrieved from the parallel data further improve BT. We also analyze the source, quality and amount of monolingual text. Across five low-resource languages, with Hindi as a high-resource control, and two 3B backbones, BT improves translation into the low-resource language by 16 to 173% XCOMET-XXL over parallel-only fine-tuning. Blind human evaluation on Odia and Sanskrit agrees with the automatic metrics.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35085

Reading the Registers of Honorius III without Manual Line Transcription: Forced-Aligned HTR, End to End, Modular or Hybrid

Tamas Kovacs, Daniel Luger

原文摘要

Unlocking medieval archives at scale is bottlenecked by the cost of line-level diplomatic transcriptions and manual abbreviation expansion. Focusing on the registers of Pope Honorius III (1216-1227) over 5,000 letters surviving in full only as manuscript images - we show that existing, line-break-free expert transcriptions (edition drafts) suffice to train end-to-end hand-written text recognition (HTR) that jointly transcribes and expands heavily abbreviated Latin. Using forced alignment on 860 unaligned edition entries across 394 pages of Reg. Vat. 9, we automatically bootstrap 13,122 training lines without manual alignment of segmented lines. While the generic CATMuS baseline struggles on this domain (18.9% CER) and a modular space-free HTR + word-segmentation pipeline (cf. Camps et al. 2021) plateaus at 15.6% WER, our from-scratch hybrid Conformer - combining CTC with bidirectional subword attention decoders, iterative self-realignment and n-best LM rescoring - achieves 4.7% CER and 8.7% WER (8.4% WER with ROVER system combination), nearly halving errors on clause-final words (22.7% to 12.2% WER). These figures are measured on the test lines that align with the transcription (86% of all test lines for the best hybrid). Furthermore, we address a tension between paleographic fidelity and editorial normalization: training on targets that preserve scribal name initials reduces the WER against the manuscript text on the 31 affected test lines from 13.3% to 9.2%, at a small cost against the expanded transcription (WER +0.3 points, CER +0.4). Finally, extensive ablations show that none of an auxiliary diplomatic CTC head, a copy mechanism, a permutation decoder or masked-image pretraining improves on direct end-to-end supervision, while strict padding-mask propagation and per-line beam termination make inference batch-invariant.

cs.CV · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35084

A JiT-Based Denoising Defense Method Against Adversarial Examples for Radio Signal Automatic Modulation Classification

Shiwei Liu, Linyuan Wang, Nuolin Sun, Libin Hou, Bin Yan

原文摘要

Automatic modulation classification (AMC) of radio signals is a core technology for spectrum monitoring and electromagnetic situational awareness. Deep neural networks (DNNs) play an important role in this field owing to their powerful feature extraction capabilities and end-to-end learning paradigm. However, their vulnerability to adversarial attacks poses serious security challenges to practical deployment. Adversarial training, a common defense, has limitations including poor generalization across attack types and high training costs. Inspired by Just image Transformers (JiT), a diffusion generative model that directly predicts clean images, this paper proposes a JiT-based denoising defense against adversarial examples for radio signal modulation classification. During training, a signal-specific 1D Transformer denoising network is optimized via flow matching to directly predict clean signal samples. It thereby learns a mapping that projects arbitrary examples back onto the low-dimensional manifold of clean signal examples. During inference, arbitrary examples are fed into the trained network and directly projected onto this manifold. This enables denoising defense without prior knowledge of attacks. Experiments on the RML2018.01A dataset were conducted without attack information, using a single empirically selected, fixed denoising start time. Compared with PGD-based adversarial training, the proposed method achieves a relative improvement of at least 20.58% in robust accuracy under PGD attacks. It also achieves a relative improvement of 10.20% in classification accuracy on clean examples. When evaluated against attack types unseen during adversarial training, the proposed method provides stronger defense than adversarial training. In particular, at higher attack strengths, it achieves a relative improvement of at least 39.72% in robust accuracy.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.29107

PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos

Shangjia Liu, Jinxi Li, Siyuan Zhou, Bo Yang, Bing Wang

原文摘要

Recovering dynamic 3D scene geometry, appearance, and the physical motion states that govern scene evolution from multi-view videos is important yet challenging. A key difficulty is that appearance can be deceptive. Under rendering supervision alone, a model may fit the observed images by changing color or opacity to compensate for inaccurate deformation, rather than recovering the true evolving geometry and motion. This issue is especially severe in scenes with fast or locally complex motion, where inaccurate trajectories can still produce plausible images over the observed frames, but lead to unreliable reconstruction and discontinuous future prediction. In this paper, we propose PhyMo, a framework for learning evolving dynamics from multi-view videos. We introduce a Motion-Aware Trajectory Representation that drives the model to recover accurate motion from deformation, rather than relying on appearance shortcuts to explain observed motion. On top of this, we propose a Continuous Motion Evolution module with bidirectional kinematic continuity constraint to promote temporally consistent evolution of displacement, velocity, and acceleration. Together, these designs yield geometrically faithful interpolation and continuous motion extrapolation. Experiments on four dynamic scene benchmarks demonstrate state-of-the-art performance.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35082

CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems

Yujia Zheng, Tianhao Li, Shangzhi Xu, Yuekai Huang, Ziyou Jiang, Zhaoyang Li, Yuyao Ge, Junran Peng 等 9 位作者

原文摘要

Agent Skills allow LLM agents to combine reusable capabilities, but checking each Skill in isolation cannot rule out policy violations when they are composed. We term such failures Conflict of Skills (CoS): artifacts or assessment signals produced for one purpose may be reused downstream without preserving the restrictions or authorization needed for their new use. Using controlled executions of publicly available Skills and matched single-Skill controls, we identify four recurring mechanisms behind CoS. Building on these findings, we introduce the Conflict of Skills Attack (CoSA), which adds locally admitted Skills to an existing pool to supply missing business operations (capability supplementation) or reshape artifact exchange, decision reuse, and target/action bindings (relationship reshaping). CoSA leaves existing Skills and runtime permissions unchanged. To evaluate this threat under autonomous Skill selection, we introduce CoSA-Bench, built from real-world Skills and controlled services, with 288 tasks across recruiting, finance, IT, and business, covering data leakage, unauthorized state modification, and unsafe execution. Across five LLMs and three agent harnesses, additions capped at 5% of each original pool raise the policy-violation rate from 35.02% to 58.45%, an increase of 23.43 percentage points. Trace analysis links compliant-to-violating transitions to cross-Skill dependencies involving the additions. Finally, we develop a lightweight harness-level guard that checks information flow and authorization before consequential actions. On OpenClaw recruiting tasks across five models, the guard reduces violations from 65.28% to 6.67%, while policy-compliant task completion on matched benign controls changes from 66.67% to 65.00%.

cs.CL · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.18005

Surface Reconstruction from Range Scans Under Visibility Constraints

Gabriel Lenain, Edmond Boyer, Jean Ponce

原文摘要

Surface reconstruction from range scans is challenging in the presence of noise and outliers, as fidelity to observations must be balanced against sensitivity to measurement errors. Yet, most neural approaches discard the sensor positions and corresponding visibility information, compensating for this loss with geometric priors or regularization terms. We instead formulate surface reconstruction as robust regression of the predicted first surface intersection along each acquisition ray against its measured depth, which penalizes predicted surface intersections within the segment between the sensor and the observed point. We represent the surface as the zero set of a 1-Lipschitz multi-layer perceptron, allowing the use of linearly convergent sphere tracing to compute the first hit, and use a robust Huber loss for regression. Our formulation requires neither oriented normals, sampled off-surface points, nor an eikonal loss. Comparisons with the state of the art on synthetic and real data with varying levels of noise and outlier contamination demonstrate competitive performance on clean data and much improved fidelity and robustness under even moderate corruption. Our analysis further confirms a trade-off between fidelity and robustness: greater fitting capacity improves data fidelity in the clean case but increases sensitivity to the measurement errors inherent in real acquisitions, with a sweet spot typically emerging at intermediate capacity.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35080

Zero-Shot Multi-Class Wafer Map Classification with Rule-Ordered Prompts for Large Multimodal Models

Tianjian Cao, Jun Tao

原文摘要

Wafer-map defect classification often requires labeled data and retraining when production conditions change. We present a training-free six-class framework that combines connected-component highlighting with morphology-, location-, and exclusion-aware prompts for a frozen large multimodal model. On Mixed-WM38 (6,866 maps), multi-region prompting achieves 92.9% macro and 93.8% overall accuracy. On WM811K (9,000 maps), it achieves 79.1% and 81.3%, respectively. Eight alternative rule orders achieve 90.1-91.9% overall accuracy, compared with 93.8% for the selected order.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35079

Toward Fast Human Reaction Modeling from High-Frequency Digital Interaction Data

Emanuel Dopater, Daniel Gavlas, Lukáš Jochymek, Kannan Paul, Miloslav Szczypka, David Vojáček, Josef Žáček, Jan Plucar 等 10 位作者

原文摘要

We investigate whether limbic-like signatures of rapid, salience-driven behavior can be identified in high-resolution Counter-Strike 2 telemetry. This exploratory study introduces Ego-Knowledge, a leak-reduced reconstruction of each player's plausible perceptual state, supported by a millisecond-precision visibility engine and a reaction-centered extraction pipeline. Using a neuroscience-motivated 60--120 ms window, we derive coarse fight-or-flight labels from visibility- and damage-triggered events, with back-damage cases enabling constrained reaction-time analysis and manual label checks. We train two telemetry-native models using only information available by the trigger: EMBER (gradient boosting) and ORBIT (a custom transformer). On the full validation set, EMBER achieves 73.5% accuracy and ORBIT 71.2%, versus a 51.5% majority-class baseline, and both generalize to held-out players. The strongest LLM baseline achieves 62.7% on 1,000 validation cases; on these same cases, EMBER (73.6%) and ORBIT (70.9%) perform better (McNemar p=1.3e-9 and 1.5e-6, respectively), with orders-of-magnitude lower inference time and cost, though the comparison is not compute-matched. Including a short post-trigger window changes forecasting into early response recognition, raising accuracy monotonically to 85.15%. We propose this curve as a candidate probe of the transition from rapid to deliberative control, but roughly uniform per-tick gains do not establish that interpretation. The neuroscience framing is hypothesis-generating, not mechanistic: physiological ground truth, suitable control distributions, and reverse-inference limitations remain open. We outline extensions to auditory reconstruction, larger datasets, and telemetry-native foundation models.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35077

Improving VLMs on Scientific Chart Analysis via Autonomous Evolution

Abhinav Sudhakar Dubey, Vidushi Goel, Kiran Rana, Shikhar Mathur, Vaggos Chatziafratis

原文摘要

Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, open vision-language models (VLMs) are known to perform poorly when it comes to question answering based on such data types. Motivated by an initial observation that many of their errors are due to inexact answering, we raise the following natural question: how much accuracy can we recover without changing the model at all? In this paper, we study this question by searching over inference programs and the code around a "frozen" version of the model. Using ideas from autonomous evolution (famously used in AlphaEvolve), we first start from a baseline inference program, and in each round we show an LLM judge the code together with a few failures on training questions, and ask for an improving evolutionary move. As usual in autonomous evolution approaches, the candidate programs are kept in a small pool ranked by training accuracy, and the next edit is performed on top-scorers from this pool. We run this approach on three VLMs and four popular benchmarks on scientific charts, and we measure the fraction of descriptive questions whose answer exactly matches the ground truth. The accuracy improves in all experimental settings. On average, it rises from 16.6% with the starting program to 41.3% with the evolved one, and the largest single increase is 55.2 percentage points. As a side benefit, our evolved program is 3.8x faster than the starting program, because short answers are easier to grade and faster to generate. Our results demonstrate that a large part of the observed errors arise due to the inference pipeline, and that optimizing it can improve the "frozen" VLM without the need to retrain it.

cs.CV · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2508.05953

SCALEFeedback: A Large-Scale Dataset of Synthetic Computer Science Assignments for LLM-generated Educational Feedback Research

Keyang Qian, Kaixun Yang, Wei Dai, Flora Jin, Yixin Cheng, Rui Guan, Sadia Nawaz, Zachari Swiecki 等 11 位作者

原文摘要

Using Large Language Models (LLMs) to give educational feedback to students for their assignments has attracted much attention in the AI in Education (AIED) field. Yet, there is currently no large-scale open-source dataset of student assignments that includes detailed assignment descriptions, rubrics, and student submissions across various courses. As a result, research on generalisable methodology for automatic generation of effective and responsible educational feedback remains limited. In this paper, we introduce a synthetic computer science university assignment dataset for LLM-based educational feedback research, called SCALEFeedback (Synthetic Computer science Assignments for LLM Educational Feedback Research). The dataset is generated via Sophisticated Assignment Mimicry (SAM) framework specifically designed to synthesise this dataset and that utilizes one-to-one LLM-based imitation from real assignment descriptions, rubrics, and student submissions. Our open-source dataset contains 10,000 synthetic student submissions spanning 155 assignments across 59 university-level computer science courses. Technical validation confirmed that the synthetic dataset closely resembles real data while successfully eliminating personally identifiable information present in the source material. The creation of this dataset is a valuable contribution to researchers who aim to develop LLM-based generalisable methods for offering high-quality, automated educational feedback in a scalable way.

cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35076

Blendshape Generation for Models with Disconnected Parts: Adding ARKit/MediaPipe Blendshapes to Anime-Style Character Models

Pramook Khungurn

原文摘要

Blendshape generation for 3D models has been extensively researched, but very few works address generating blendshapes for models with multiple disconnected parts. We present a case study of generating fixed facial expression blendshapes for commercial anime-style 3D character models with up to 11 parts per face. To make sure that our system can handle models in a way that is agnostic to topology, we train neural networks to generate deformation fields around the input meshes. We employ at least one network to independently process each part, and the relative positions of their outputs are coordinated by having each network also process the geometry of an anchor part. We use two mechanisms to improve accuracy: having the networks predict whether the output displacement is zero or not, and classifying blendshapes into different size groups and dedicating a network to each group. We also introduce a method to improve blendshape quality by enhancing bilateral symmetry. Our method is simpler than recent neural-network-based works and solves a real problem of the user community of these models.

cs.CV · cs.GR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35075

Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data

Dianyi Yang, Mengya Liu, Zhumei Wang, Yu Liu, Xiaochen Zhang, Yixuan Li, Le Ma, Yuhang Yang 等 12 位作者

原文摘要

Learning generalizable humanoid loco-manipulation remains bottlenecked by costly real-world demonstrations. Simulation provides a scalable alternative, but requires visually faithful, physics-ready scenes and executable whole-body motions. We present Zero-HLM, a real-to-sim-to-real framework that transforms smartphone captures and simulated source demonstrations into scalable training data for humanoid loco-manipulation. Gaussian-guided agentic real-to-sim reconstruction aligns visual and physical scenes; motion-environment co-adaptation uses rollout feedback to correct whole-body references and interaction geometry. We generate 4,800 physically validated demonstrations for zero-shot transfer across three Unitree G1 tasks. Simulation-trained GR00T N1.7 achieves 66.7% mean full-task success, versus 46.7% with real-data training. On generalized configurations, expanded simulation training raises pooled success from 23% for base-trained real-data policies to 69%, without additional real demonstrations. Project page: https://young-bit.github.io/zero-hlm/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35074

A Diagnostic Protocol for GNNs in Electricity Load Forecasting: Separating Parameter Sharing from Neighborhood Access

Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude, Itai Zehavi, Argyris Kalogeratos

原文摘要

A graph neural network (GNN) forecasting a collection of load series combines two mechanisms, sharing parameters across series and reading neighboring series, and a gain over a non-graph model may come from either; telling them apart decides whether a graph is worth maintaining. We propose a model diagnostic protocol that compares the GNN with three reference models: a per-node network, a network shared across nodes without neighbors, and the same GNN without edges. Degree-preserving rewiring tests whether neighbor identity matters. After a tuned benchmark on regional load in France and on low-voltage feeders in the UK, we apply the protocol to deliberately short node histories, as when non-stationary demand leaves only recent observations relevant: the feeders, within one week, and a public dataset of client consumption series. On the feeders, sharing parameters recovers most of the error gap between node-specific models and GNNs, about two thirds against a regularized one. Adding the edges to an otherwise identical backbone brings a smaller gain, half or more of which disappears under rewiring. On the client series, the neighbor mean degrades the per-node model on the shorter window and the edges' gain is not consistently distinguishable from zero; on the regions of France, where each node's own history is already informative, the ranking between per-node models and GNNs changes with tuning. A synthetic study points to noisy local measurements as one regime where neighbors help. In an exploratory online aggregation, graph and non-graph forecasters appear complementary, and the weight assigned to GNNs is not proportional to their contribution. In none of the three datasets do the edges account for most of a GNN's advantage over node-specific models, so a forecasting gain should be credited to the graph only after comparison with per-node and shared references.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.27703

SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them

Yang Zhou, Zixuan Huang, Sunzhu Li, Zhuo Yang, Chen Zhang, Shunian Chen, Caijun Yan, Jianyao Xu 等 13 位作者

原文摘要

Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning. However, a fundamental capability mismatch remains: general VLMs can reason about the overall task but often miss the visual details that determine success, while specialist vision models can capture those details but cannot translate them into task-level decisions. In this work, we propose SpatialCLI, a framework that teaches VLMs to reason with spatial tools and progressively internalize the specialist perceptual capabilities they provide. SpatialCLI proceeds in three stages: (1) Call exposes specialist vision models as spatial tools to augment the VLM's perception; (2) Learn uses Cold-Start SFT and agentic RL to improve tool use; and (3) Internalize verbalizes successful tool-use trajectories to internalize specialist perceptual capabilities. We further introduce SpatialCLI-Bench, a 516-example benchmark for compositional perception across localization, segmentation, depth, and pose. On MindCube, SpatialCLI raises Qwen3-VL-8B-Instruct from 29.3% to 84.6% with tools, surpassing GPT-5.6 Sol with tools (72.1%), while retaining 73.8% without tools after internalization.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35073

Priority-Aware Scheduler for Serverless Functions Provision and Load Balancing

Cheryl Lee, Zishan Su, Zhouruixing Zhu, Tianyi Yang, Yuxin Su, Pinjia He, Michael R. Lyu

原文摘要

Serverless computing has emerged as a pivotal cloud deployment paradigm due to its efficient utilization of on-demand resources. However, the persistent cold start problem continues to hinder system performance. Current strategies often employ oversimplified preloading/unloading mechanisms that inadequately exploit invocation patterns, failing to optimize the critical trade-off between startup latency and resource efficiency. Furthermore, existing approaches disregard practical constraints of memory-limited multi-worker environments, exacerbating function eviction and load imbalance issues. To address these limitations, we present SPES-Ext, a rule-based priority-aware scheduler designed for memory-constrained distributed worker nodes. Our methodology stems from two key observations: (1) serverless systems exhibit concentrated invocation patterns enabling behavioral predictability, and (2) these patterns permit function categorization for granular instance management. This insight posits that characteristic-driven prioritization enables optimal scheduling rules, leading to our system design, which integrates three coordinated components: predictive function provisioning, eviction optimization, and dynamic load balancing. Experimental validation demonstrates the superiority of SPES-Ext over state-of-the-art solutions: 80% reduction in $75^{th}$-percentile cold starts, 83.92% decrease in memory waste, and 52.49% improvement in worker load variance.

cs.DC · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16090

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation

Hao Yang, Zhuo Ma, Yang Liu, Yilong Yang, Guancheng Wang, JianFeng Ma

原文摘要

Large vision-language models (LVLMs) have emerged as a powerful paradigm for multimodal intelligence, but their growing deployment also expands the attack surface of prompt injection. Despite this growing concern, existing attacks still suffer from a critical limitation: the injected prompt for one modality only steers the model's interpretation of that singular input. Alternatively, these attacks remain multimodal but fail to achieve cross-modal prompt perturbation. To bridge this gap, we introduce a novel cross-modal prompt injection attack CrossMPI, which can steer the model's interpretation of both textual and visual inputs via image-only prompt injection. Our design is underpinned by the following key breakthroughs. First, we turn the focus of the injected prompt perturbation optimization from the visual embedding space (typically with only $10^5$ parameters) to the model hidden state space (for multimodal information integration and with $10^7$ parameters). Then, two strategies are adopted to mitigate the optimization challenges posed by the larger parameter space. To constrain the optimized model parameter space, we introduce a layer selection strategy that identifies the layers most critical to multimodal integration. Interestingly, deviating from the past experience, our analysis reveals that the optimal layers for LVLM prompt perturbation reside in the middle of the model rather than the last. To constrain the image perturbation space, we propose a new distance-decremental perturbation budget assignment strategy that allocates budgets decrementally as the pixel distance to semantic-critical regions increases. Extensive experiments across multiple LVLMs and datasets show that our method significantly outperforms baseline approaches.

cs.CR · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35071

GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation

Linghui Jiao, Kang Wei, Fushuo Huo, Ruijie Zhao, Yiyang Ni, Jingcai Guo, Yipeng Zhou, Jun Li

原文摘要

Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models (LLMs) by incorporating external evidence, but also exposes them to corpus poisoning attacks. In particular, coordinated attacks can introduce multiple mutually reinforcing poisoned documents into retrieved contexts, making reliable evidence filtering challenging. To address this problem, we propose GuardRAG, a training-free and plug-and-play post-retrieval defense that exploits the semantic structure of retrieved evidence to identify suspicious document groups. Specifically, GuardRAG first expands the retrieval range and removes near-duplicate candidates, then partitions the retained documents using Hierarchical Agglomerative Clustering (HAC) with a query-adaptive threshold. Finally, it scores and prunes suspicious clusters based on query relevance, cluster size, and semantic compactness. Experiments across three question-answering datasets, multiple poisoning attacks, and six LLMs demonstrate that GuardRAG substantially reduces attack success rates while maintaining answer utility under clean retrieval.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35070

Joint Dynamic Lane Reversal and Variable Speed Limit Control: A Graphormer-Based Approach

Hamed Araab, Abbas Ahmadi, Mohammad Hossein Basiri

原文摘要

Connected and automated vehicles could allow reassigning lane directions and speed limits on every road frequently, but the benefit hinges on how traffic reroutes, and one-way roads can isolate junctions. We formulate network-wide dynamic lane allocation and directional speed limit control with one-way roads, lane clearing before each reversal, and a navigable graph kept strongly connected at all times. An action-resolution algorithm grounded in graph orientation theory admits a proposal closing a direction only if the network stays strongly connected and otherwise relaxes or reverts it, keeping all junctions mutually reachable within the model, even during clearing. All road controllers share one transformer whose attention, Global Endpoint Relation-Aware Spatio-Temporal Self-Attention (GERASTSA), spans all road-time tokens, biased by the endpoint relations between roads. It is pretrained on action-conditioned traffic forecasting and fine-tuned with per-road proximal policy optimization under a mixed reward that also credits neighboring roads and the network. On a 6 x 6 grid with commuter rush hours, the learned policy makes about two thirds of roads one-way in the peak direction and cuts daily delay by 90% against the initial configuration held fixed and by 85% against a tuned two-way load balancer. Restricted to two-way roads at test time, it gains only about as much as this balancer, whereas its learned speed limits add delay. Pretraining roughly halves the updates needed to surpass the fixed configuration. Of the ablations, only removing the relational bias or the spatial embedding clearly matters, multiplying delay about fivefold.

eess.SY · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗