跳到正文
研踪PaperTrail

论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 03:14 — 2026-11-16 03:14（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：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
版本更新 · v2arXiv:2610.32417

Measuring the Energy Cost of Completing Tasks with Quantized Language-Model Agents

Stephen Abkin, Aldric Yang, Alex Flesher, Nitheesh Kodarapu, Deepak Panigrahy, Aakash Tyagi, David Kebo Houngninou

原文摘要

Quantization reduces the memory and energy needed to serve large language models (LLMs) and AI agents for coding and data analysis can now run on locally hosted LLMs. In practice, this benefit is commonly benchmarked per output token. Yet an agent calls its model repeatedly, runs tools, and revises its work, and quantization can change both how much the agent generates and whether it succeeds. Existing energy studies either compare quantized models on single requests or measure agents at one fixed precision, overlooking how a change in precision plays out across a complete agent task. To address this gap, this paper presents the first characterization of the task-level energy trade-offs of model quantization in locally hosted agents. We develop 29 agent tasks with automatic pass/fail checks in six families, ranging from single-answer SQL analytics to multi-step repository bug fixing, and measure CPU and GPU energy per output token and per completed task for 4-bit and 8-bit versions of two open-weight models on bare-metal NVIDIA A100 nodes with llama$.$cpp. Our findings reveal that 4-bit precision generally saves energy per token, though whether it saves energy per completed task is task dependent and changes with the model and the execution budget (i.e., limits on turns, tokens, and time). We trace this discrepancy to the extra tokens needed to complete a task in full, which translates into using up to 3.5 times as much energy per completed task. These findings offer actionable guidance for developers and operators choosing model precision for agents, showing how tokens per completed task, set against the per-token saving, reveal whether lower precision completes the work with less energy.

cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2408.02846

What's in a Package? Getting Visibility Into Dependencies Using Security-Sensitive API Calls

Imranur Rahman, Ranidya Paramitha, Henrik Plate, Dominik Wermke, Laurie Williams

原文摘要

The Log4Shell vulnerability occurred because the JNDI (Java Naming and Directory Interface) lookup feature was used, even though it was not needed for log4j's core functionality. This case illustrates why developers may want visibility into the sensitive capabilities available through a dependency. The presence of a call alone does not establish that the call is unnecessary or risky. Security-sensitive APIs provide access to security-sensitive resources, such as filesystem, network, or process-related resources. If developers know which types of sensitive resources a dependency can access, they can control their dependencies at a finer grain, and they can consider an alternative dependency when a dependency makes unnecessary or suspicious security-sensitive API calls. However, prior work has not provided a documented, repeatable procedure for deriving an ecosystem-specific security-sensitive API list, so developers lack systematic visibility into the sensitive capabilities of their dependencies. The goal of this study is to aid developers in understanding sensitive resources accessible to their dependencies by identifying security-sensitive APIs in packages through an empirical study of Java packages. In this study, we present a novel and repeatable methodology to construct a security-sensitive API list for an ecosystem, and we apply it to Java. We then compare the security-sensitive API calls of functionally similar Java packages. The number of security-sensitive API calls (call level) ranges from 0 to 368 in one capability and from 0 to 429 in total among packages with similar functionality. These packages also differ in capability breadth, the number of the 15 capabilities that a package reaches. For example, capability breadth ranges from 0 to 10 in the "Dependency Injection" category and from 0 to 13 in the "Web Frameworks" category.

cs.CR · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34809

Position Matters More Than Channel: Talking a Language Model Out of a Correct Answer

Xinyi Ni

原文摘要

Language models now answer questions alongside other claims: a note in the system prompt, a message from another agent, their own earlier answer. We ask what it takes to talk a model out of an answer it gets right on its own, and separate three factors that earlier studies vary together: where the advice sits in the prompt, who is said to have written it, and what the model has already written. On Qwen3.5-27B and four-option MMLU-Pro items, with the rest of the advice held fixed in each comparison, we find three things. First, position matters far more than the API channel, in opposite directions for a bare claim and an argument: a bare "the answer is X" does most harm just before the model answers, while the same claim with a false rationale does most harm before the question, where it raises error on items the model otherwise almost never misses from 1% to 67%; moving the claim between the system message and the user message at the same position changes error by a few points. Second, attributing the note to an authority rather than to another participant, and phrasing it assertively, each raise error by 10-27 points, while the two authorities we tested differ by under two. Third, replaying a correct worked answer before the advice protects it whether the text is shown as the model's own or as someone else's, and the same replay keeps wrong answers from being corrected by a bare correct note. The position result replicates under an independently written prompt. Code, items and all result tables are released at https://github.com/coolkillercat/safety.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.13829

ArrayTac: A Closed-Loop Piezoelectric Tactile Platform for Continuously Tunable Rendering of Shape, Stiffness, and Friction

Tianhai Liang, Shiyi Guo, Baiye Cheng, Zhengrong Xue, Han Zhang, Huazhe Xu

原文摘要

Human touch depends on the integration of shape, stiffness, and friction, yet existing tactile displays cannot render these cues together as continuously tunable, high-fidelity signals for intuitive perception. We present ArrayTac, a closed-loop piezoelectric tactile platform that simultaneously renders these three tactile dimensions with continuous tunability on a 4 by 4 actuator array. Each unit integrates a three-stage micro-lever amplifier with end-effector Hall-effect feedback, enabling up to 5 mm displacement, an array refresh rate greater than 500 Hz, and a closed-loop bandwidth of 123 Hz. In psychophysical experiments, naive participants identified three-dimensional shapes and distinguished multiple stiffness and friction levels through touch alone without training. We further demonstrate image-to-touch rendering from an RGB image and remote palpation of a medical-grade breast tumor phantom across a distance of more than 1,000 km, in which all 11 participants correctly identified the number and type of tumors with a sub-centimeter mean localization error. Together, these results establish ArrayTac as a programmable multidimensional tactile rendering platform that bridges digital representations, physical environments, and human tactile perception, enabling intuitive tactile communication between humans and machines.

cs.RO · cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05911

PREFER: Personalized Review Summarization with Online Preference Learning

Millend Roy, Agostino Capponi, Vineet Goyal

原文摘要

Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring information most relevant to their individual needs. Existing e-commerce summarization systems typically produce generic, static summaries that fail to account for the fact that (i) different users prioritize different product characteristics, and (ii) these preferences may evolve with interactions. To address these challenges, we propose an online learning framework that generates personalized summaries for each user by representing user interests in a latent aspect space and selecting preference-aligned review evidence. Our system then iteratively refines its understanding of user preferences by incorporating feedback on the generated summaries directly over time. We evaluate our framework on Amazon Reviews'23 using controlled feedback simulations and robustness checks with held-out-history, independent-embedding, and external LLM-based evaluators. These experiments show improvements in preference-aligned evidence selection under the evaluated feedback settings. A separate human-based study finds that scenario-conditioned summaries are preferred over generic (uniformly-aggregated) alternatives in 69.9% of paired comparisons.

cs.AI · cs.GT · cs.LG · eess.SY · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.28402

StreamEval: Evaluating Interactive Streaming Video Generation Models

StreamEval Team

原文摘要

We introduce StreamEval with four key features: (1) First interactive streaming video generation benchmark. (2) Fully open source. Benchmark data, evaluation code, protocols, and scoring rules are publicly available. (3) Comprehensive coverage. Five tasks cover avatar dialogue, avatar performance, world generation, instruction editing, and reference editing, with 300 scripted cases lasting 15 to 300 seconds. Ten metrics assess task execution, state consistency, visual fidelity, and audiovisual coordination. (4) Monthly updates. We will evaluate new and updated models and publish leaderboard results monthly. Results from 37 models show that high visual quality and identity retention do not necessarily coincide with reliable request execution or sustained state consistency. The leaderboard is available at https://streameval.ai.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34807

ImageTTS: Repurposing Pretrained Image Diffusion Transformers for Speech Synthesis

Hanchen Pei, Shujie Liu, Yayue Deng, Fangyun Wei, Yanqing Liu, Jianwei Yu, Gongping Huang

原文摘要

Pretrained image-generation models have been successfully repurposed for various downstream visual tasks. Whether their learned representations and generative priors can transfer beyond vision to other modalities remains largely unresolved, particularly for speech synthesis, which requires linguistic fidelity and preservation of speaker identity from a short reference. We present ImageTTS, which repurposes FLUX.2 for speech synthesis by encoding pseudo-RGB log-mel spectrograms with its frozen image VAE and adapting only its pretrained Diffusion Transformer (DiT) using conditional latent flow matching. This formulation disentangles two forms of vision-to-speech transfer: representation transfer through the image VAE and generative-prior transfer through DiT initialization. The frozen image VAE largely preserves intelligibility and speaker identity with 0.99 STOI and 0.95 speaker similarity, while image-pretrained DiT initialization accelerates convergence and improves linguistic accuracy, reducing WER from 4.2\% to 2.7\% at 100k matched updates relative to random initialization. The same framework supports both zero-shot and instruction-guided TTS and, when scaled to 100K hours of speech data, achieves 1.12\% WER on Seed-TTS test-en and a Style-ACC of 0.66 on CapSpeech, outperforming speech-native baselines trained on comparable data across both tasks. These results suggest that pretrained image models can transfer beyond architectural reuse, supplying useful latent representations and generative priors for intelligible and controllable speech synthesis.

cs.SD · cs.MM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30729

Width and Depth Limits Commute During Training in Linear Residual Networks

Ruijia Zhang, Soufiane Hayou

原文摘要

Recent work established that the infinite-width and infinite-depth limits of residual networks commute at initialization when residual branches are scaled by $1/\sqrt{depth}$. In particular, the network output converges to the same limit whether width and depth tend to infinity sequentially or jointly. We extend this commutativity result to training in linear residual networks. Under the same $1/\sqrt{depth}$ residual-branch scaling (Depth-$μ$P) and the $μ$P width parameterization, we prove that, for any fixed number of gradient-descent steps with gradient clipping, the network output converges in $L^2$ along every joint width--depth growth path as both width and depth tend to infinity. Consequently, the infinite-width and infinite-depth limits commute throughout any finite training horizon. Without gradient clipping, the corresponding $L^2$ convergence does not hold in general, but we establish the weaker convergence in probability.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.13700

C-MambaPose: Phase-Preserving Complex Mamba for Cross-Environment Wi-Fi Human Pose Estimation

Phuc H. Nguyen, Van-Dinh Nguyen

原文摘要

Cross-environment generalization remains a fundamental challenge for Wi-Fi-based human pose estimation (HPE), as environmental multipath can drastically alter Channel State Information (CSI) for the same human motion. Existing approaches often discard CSI phase or collapse complex signals into real-valued features early, losing motion-sensitive phase dynamics. We present C-MambaPose, a phase-preserving complex-valued state-space framework for robust cross-environment Wi-Fi 3D HPE. Our key insight is to preserve complex phase relationships throughout spatiotemporal modeling, rather than using phase only as an input feature. C-MambaPose sanitizes synchronization-induced phase errors and employs a Spatiotemporal Complex Mamba encoder with dynamic multi-scale receptive fields to capture long-range phase-amplitude dynamics. Cross-attention then maps the learned representations to human joints, followed by a skeleton-aware GraFormer decoder for anatomically coherent pose estimation. Experiments on MM-Fi show that C-MambaPose achieves strong performance across all settings, with the largest gains in unseen environments, reaching $298.5$ mm and $317.6$ mm MPJPE on the two cross-environment protocols using only $3.78$ M parameters and no pretraining. Ablations further show that prematurely discarding complex phase relationships substantially degrades performance, demonstrating their importance for cross-environment Wi-Fi HPE.

eess.SP · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34805

On the Existence of Complete Coverings of Lee Spheres

Jing Zhang, Yue Zhou

原文摘要

Every perfect $r$-error-correcting Lee code in $\mathbb{Z}^n$ induces a finite configuration around each codeword: a family of pairwise disjoint radius-$r$ Lee spheres, all disjoint from the central sphere, that covers every lattice point at Lee distance $r+1$ from the codeword. We call such a configuration a complete covering. Under projection onto a suitable Cartesian product of cycles, a complete covering corresponds to an optimal local structure in the sense of Špacapan. The existence of a complete covering is necessary but, in general, not sufficient for the existence of a perfect Lee code, as our construction for $(n,r)=(3,2)$ shows. We prove that no complete covering exists whenever $n\ge 8$ and $r^2+\lfloor 25r/34\rfloor-3\ge 2n$. For the corresponding Cartesian products of cycles, this strengthens Špacapan's nonexistence theorem by replacing the linear radius condition $r\ge n$ with a threshold of order $\sqrt{2n}$. We also obtain an improved large-radius nonexistence bound for perfect Lee codes, strengthening the bound of Horak and Kim. Furthermore, we show that, for every $\varepsilon>0$, no complete covering exists when $n\ge 3$, $r$ is sufficiently large, and $r^2+(2/\mathrm{e}-\varepsilon)r\ge 2n$. On the positive side, we use near-optimal ternary constant-weight codes to construct almost complete coverings whose pairwise disjoint shadows cover a $1-o(1)$ proportion of the first outer Lee shell as the dimension tends to infinity, for every fixed radius.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34801

When Does Data Value Reduce to Class Balance? A Coverage View of Per-Point Data Valuation

Yingjie Bai, Weiming Zhi

原文摘要

Per-point data-valuation scores -- Data Shapley, influence, leverage -- are routinely used to select training data: keep the points with the top $k$ scores. We argue that top-$k$ by a fixed, mode-blind per-point score is the wrong selection rule precisely in the regime where data selection matters. The reason is that a point's value is not a fixed number but depends on what else has been selected -- a near-duplicate of an already-chosen point adds almost nothing, however high its score -- and a per-point scalar cannot express this interaction. The theory quantifies this failure exactly: in an equal latent-mode model, fixed top-$k$ selection incurs a closed-form excess risk over adaptive coverage because it repeatedly spends budget on already-covered modes. The gap is largest when the budget is tight, the learner representation is redundant, and missing a mode is costly. The practical rule is simple: use balance when the labels available at selection identify the learner's modes, and use explicit coverage when they do not. On standard classification tasks with strong pretrained features, class-balancing the same per-point scores recovers the missing coverage and matches or outperforms generic set coverage across our datasets. Without labels, label-free coverage improves accuracy by up to +0.20 while raw top-$k$ can fall below random; when labels are coarser than the modes, coverage within coarse strata performs best. We turn this distinction into a pre-specified diagnostic and validate it across both favorable and stress-test settings. The limits are part of the claim: the advantage is representation-relative. Coverage fails when the relevant modes are not expressed in the learner geometry, as with spurious subgroups, or when data quality varies independently of coverage -- exactly as the theory predicts.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34800

Phantom Forgetting: How BatchNorm State Fakes Deletion in Edge Split Machine Unlearning

Anand Agrawal, Anil Kumar Chillara, Naresh Mandan

原文摘要

Split learning is a natural fit for edge intelligence: a resource-constrained edge device runs the first layers of a network and offloads the remainder to a server, so that raw data never leave the device. When such a system must unlearn revoked or sensitive data for example to honor a right-to-erasure request, the deletion is commonly assessed through changes in forget-set accuracy. However, inference on an edge-server split also depends on non-learnable model state distributed across the two parties, and this state is especially volatile on edge devices subject to data drift, over-the-air updates, and checkpoint rollback. This paper isolates a state-integrity question with direct edge-security implications: can Batch Normalization (BN) running statistics create a target-specific forgetting signal even when every learnable weight remains fixed? We define a state-only diagnostic that separates learnable-parameter change from BN- buffer change and localizes the effect to the edge (client) side, the server side, and joint placements. We also introduce a state-induced forgetting gap (SIFG) that discounts simultaneous retain-set degradation. Over all ten CIFAR-10 forget classes, centralized BN recalibration on forget data reduces mean forget accuracy by 61.50 percentage points with zero weight change; in a split model, edge-only, server-only, and joint recalibration produce mean drops of 37.27, 41.71, and 51.90 points. The server-side state yields the largest selective gap relative to retain degradation, while joint recalibration causes the largest overall prediction change. These results establish distributed normalization buffers including those held on the edge device as security and privacy-relevant inference state, and show that forget accuracy should not be interpreted, or accepted as a deletion certificate, without an explicit edge-aware state-integrity audit.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34799

Centralized Critics for N-Agent Ad Hoc Teamwork

Andrew McAlinden, Caroline Wang, Steven Shi, Arrasy Rahman, Elad Liebman, Peter Stone

原文摘要

Centralized training with decentralized execution (CTDE) has become the dominant paradigm in multi-agent reinforcement learning (MARL), motivating extensive study of what privileged information should be made available to the critic during training. While prior work has examined the role of global state in fully cooperative settings, the design of centralized critics for N-agent ad hoc teamwork - in which dynamically varying set of learning agents must coordinate with an arbitrary set of uncontrolled teammates drawn from an unknown distribution - remains poorly understood. We study this question by comparing two natural classes of advantage estimators: controlled history estimators, which condition only on the observation and action histories of the learner's own agents, and joint history estimators, which additionally condition on the histories of the uncontrolled teammates. We prove that both estimators are unbiased and characterize the conditions under which the joint history estimate attains strictly lower variance than its controlled counterpart. Empirically, joint history critics match or outperform controlled history critics across a range of NAHT tasks, yielding improved sample efficiency and final returns. Together, these results provide both a theoretical justification and an empirical recommendation for incorporating uncontrolled agent histories into centralized critics for N-agent ad hoc teamwork.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.08479

No Provenance Left Behind: Revisiting Reference Monitor Guarantees with Learned Kernel Scheduling

Jinsong Mao, Benjamin E. Ujcich, Shiqing Ma

原文摘要

Provenance plays a critical role in maintaining traceability of a system's actions for root cause analysis of security threats and impacts. Provenance collection is often incorporated into the reference monitor of systems to ensure that an audit trail exists of all events, that events are completely captured, and that logging of such events cannot be bypassed. However, recent research has questioned whether existing state-of-the-art provenance collection systems fail to ensure the security guarantees of a true reference monitor due to the 'super producer threat' in which provenance generation can overload a system to force the system to drop security-relevant events and allow an attacker to hide their actions. One approach towards solving this threat is to enforce resource isolation, but that does not fully solve the problems resulting from hardware dependencies and performance limitations. In this paper, we show how an operating system's kernel scheduler can mitigate this threat, and we introduce Aegis, a learned scheduler for Linux specifically designed for provenance. Unlike conventional schedulers that ignore provenance completeness requirements, Aegis leverages reinforcement learning to learn provenance task behavior and to dynamically optimize resource allocation. We evaluate Aegis's efficacy and show that Aegis significantly improves both the completeness and efficiency of provenance collection systems compared to traditional scheduling, while maintaining reasonable overheads and even improving overall runtime in certain cases compared to the default Linux scheduler.

cs.CR · cs.OS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34797

TimeWorld: Towards Action-Conditioned Multimodal World Models for Time Series Forecasting

Hang Ni, Weijia Zhang, Hao Liu

原文摘要

Time series forecasting supports decision-making in web applications such as online retail and network management, where planned actions can reshape future dynamics. World models provide a natural paradigm for predicting such action-dependent changes beyond extrapolating historical patterns. However, existing time series world models (TSWMs) typically rely on fixed, domain-specific covariate schemas that limit flexible intervention specification, while multimodal forecasters treat text primarily as passive predictive context. To investigate these gaps, we introduce TSWM-Bench, a cross-domain benchmark for multimodal TSWMs spanning seven real-world datasets, with textual interventions grounded in recorded action--outcome data. Our evaluation reveals that conventional multimodal forecasters underperform history-only time series foundation models (TSFMs) despite dataset-specific training, whereas simple text-prefix adaptations improve forecasting across all evaluated TSFM backbones. These findings suggest that pretrained TSFMs encode implicit world knowledge of temporal dynamics, offering a strong foundation for action-conditioned modeling beyond conventional multimodal fusion. Building on this insight, we propose TimeWorld, a plug-in framework that adapts pretrained TSFMs through explicit action-response modeling. Specifically, the Prototype-Guided Latent Modulation (PLM) module grounds textual actions in temporal dynamics by composing representative response prototypes to modulate future representations based on the action and historical patterns. The Action Contrastive Learning (ACL) component strengthens action-specific response modeling by contrasting these updates under alternative interventions sharing the same history, distinguishing action types while preserving relative intensity relationships.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34795

Towards Spatio-Temporal Intelligence Systems in Urban Space: A Twin-Agent Perspective

Zhen Dong, Haiping Wang, Wei Tu, Yuan Liu, Bing Wang, Xuan Sun, Jinzhou Cao, Ronald Clark 等 17 位作者

原文摘要

Cities must coordinate domains like infrastructure, mobility, environmental management, emergency response, and public services as conditions evolve. An urban Spatio-Temporal Intelligence (STI) system helps the city monitor citywide states, analyze problems, plan and execute interventions, and adapt through feedback, making urban governance more timely, effective, and transparent. Recent urban twinning and agentic AI techniques provide foundations for such systems. From a twin-agent perspective, this survey takes a system-level view of how these disparate techniques can be coherently integrated into an urban STI system. Specifically, we review how the twin reconstructs and represents a persistent, information-enriched urban environment, and how the agent understands the twin via interfaces, reasons over it, acts reliably, and continuously evolves with the city. Built upon this synthesis, we summarize a two-loop blueprint, where an inner agent loop for grounding, reasoning, and verification, and an outer system loop linking data, twin, agentic action, feedback, and update. We then use this to structure an STI research agenda and show how a shared prototype supports diverse urban domains.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.00326

Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification

Charles Weng, Dingwen Li, Alexander Martin

原文摘要

Safety pipelines often block content by thresholding a model's first-token unsafe score. We show that a single prompt's score is not a reliable probability and compare two repairs: mean ensemble and calibration with development labels. Across seven vision-language models and two benchmarks, an input's unsafe probability varies across 15 task-preserving rewordings with a standard deviation of 0.16-0.30 on average; the inputs that vary most are more often misclassified. The 15-prompt mean has lower negative log-likelihood (NLL) than the best single prompt, even one chosen with evaluation labels, on 13 of 14 model-benchmark pairs. Development labels change the picture: jointly selecting and calibrating a single prompt outperforms the similarly calibrated mean for all seven models on held-out data from the development benchmark. Under cross-benchmark evaluation without refitting, however, the advantage reverses, with the calibrated mean outperforming the single prompt on six of seven models. We recommend evaluating first-token scores as a prompt family, using the mean ensemble as the label-free baseline, calibrating one prompt when development labels exist and deployment data match, and calibrating the mean when they may not.

cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34791

Text Is the Bottleneck: A Small-Scale Replication of LLM Game Playing in Riichi Mahjong

Mingge Xu

原文摘要

We replicate the riichi-mahjong track of "Can Large Language Models Master Complex Card Games?" (arXiv:2509.01328) under a drastically smaller budget: models of at most 2B parameters, one 16 GB consumer GPU, about five GPU-days. (1) With matched data and labels, text is the bottleneck: on the same 100k-decision training set, a 2.6M-parameter convolutional board encoder agrees with the strong AI Mortal on 80.6% of test decisions, above every text-prompt LLM we train (best 77.8%), and places better at the table (2.85 over 1,000 games vs. ~3.0 for the LLMs; paired difference at n=100 not significant). Scaled to 1.71M decisions, a 4.9M-parameter Transformer reaches 94.7% agreement, beats the 0.8B LLMs on identical seeds (-0.45 ranks, sign test p=0.005), and is statistically equivalent to parity against three Mortal champions (TOST within 0.10 ranks, p=6e-4); parity against a teacher-opponent is roughly the ceiling of pure imitation. (2) Training toward the teacher raises teacher agreement more than a 2.5x parameter increase does (+2.5 vs. +1.5 points); on human-record agreement both effects are +1.0, and neither is visible at the table. (3) Few-point agreement differences do not resolve into playing strength within a family: +2.5 agreement points coincide with a paired placement difference of +0.02 +/- 0.12 ranks (p=1.0), and +2.0 points at 2B with -0.06 (p=0.37) - both below the ~0.25-rank resolution of 100 paired games. We also document a paper-code mismatch in the original winner filter, reconstruct its two private engine patches, and show that a divide-and-conquer pipeline makes template-generated Japanese rationales 93% sentence-exact (43% without facts). Per Tenhou's terms we release no trained weights - only code, configurations, and evaluation protocols.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34790

BehaviorMem: Building and Evaluating User Memory from Real-World E-Commerce Behavior Streams

Sizhe Wang, Xinghao Fang, Rui Qiu, Zhenjia Ma, Dagui Chen, Kun Kuang, Hongcheng Guo

原文摘要

User memory helps personalized systems build on their understanding of users over time. In e-commerce, users convey their preferences and needs through both explicit language and implicit interactions with products. We study memory built from logs of these interactions, examining how it can \emph{remember} concrete evidence and established interests, and use that evidence to \emph{infer} underlying needs and preferences that inform judgments beyond well-observed product domains. Existing memory methods primarily target language-based interactions, and evaluations offer limited real behavioral data and limited separation of these capabilities. This leaves open how to jointly support and separately evaluate remembering and inference from behavioral logs. We formulate the problem of continual behavioral user memory around these joint requirements and develop a dedicated evaluation framework and memory method to address them. \textbf{BehaviorMemBench} is a benchmark built from real e-commerce logs covering 1{,}194 users and 17{,}462 behavioral batches over more than three years, with automatic future-behavior labels and a task-independent memory interface to separately evaluate remembering and inference under a common protocol. \textbf{BehaviorMem} is a memory design that organizes explicit behavioral facts and inferred user characteristics across long-term and short-term scopes in a two-axis state, with evidence-grounded formation, continual maintenance, and query-independent readout. Experiments across two builders and two task readers show that BehaviorMem leads the evaluated agentic memories on remember and infer, and reveal different method rankings across the two capabilities and competitive statistical baselines. Validation on a public dataset further supports its usefulness for downstream tasks based on behavioral histories.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.19781

SNACK: A Sequential Notation Framework for Probabilistic Graph Generation

Hohyun Kim, Hyesung Kim, Min-hwan Oh, Seunggeun Lee

原文摘要

We introduce SNACK, a string representation for probabilistic graph generation that enables language models to generate graphs with discrete node and edge features. SNACK linearizes graphs by encoding the nonzero entries of the lower-triangular adjacency matrix, establishing a bijective correspondence between valid sequences and ordered adjacency matrices. This design enables invalid logit masking to enforce structural constraints, such as chemical valence and ordering rules, thereby guaranteeing 100% valid generated sequences while sticking to standard language modeling for effective training. SNACK also enables principled string-based GFlowNet training by explicitly accounting for node-ordering symmetries. Across standard graph-generation tasks and molecular distribution-learning benchmarks, SNACK achieves competitive sample quality, while substantially improving the throughput of GFlowNet training relative to graph-based generation. Probing analyses further show that models trained on SNACK encode meaningful local and global graph structure despite receiving only sequential supervision. These results position SNACK as a practical framework for probabilistic graph generation with deep sequence models.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34789

ISB-NMPC: Interception-Oriented Spherical-Bearing Nonlinear Model Predictive Control for Quadrotors

Li Hong, Linkai Liu, Xiangyu Ren, Shuli Lv, Chen Min, Chunjiang Wu, Yujun Zhang, Dingchen Zeng 等 9 位作者

原文摘要

Quadrotor interceptors equipped with strapdown cameras offer a low-cost solution for physically countering unauthorized UAVs. However, this configuration inherently couples vehicle maneuvering and camera pointing, creating a conflict between rapid closing and maintaining target visibility. We present interception-oriented spherical-bearing nonlinear model predictive control (ISB-NMPC), which couples spherical-bearing prediction with nonlinear quadrotor dynamics to jointly optimize target-directed closing motion and visibility. An attitude-compensated extended Kalman filter on S^2 estimates target bearing motion, compensates for perception delay, and predicts target bearings to guide scale-adaptive detection. Across 30 paired simulation trials, ISB-NMPC achieves an interception success rate of 86.7%, the highest among the evaluated controllers, with a mean per-trial target-visible time of 99.11%. Outdoor flights demonstrate acquisition of a 30 cm target at approximately 150 m, with interceptor speed reaching 17 m/s in the long-range flight and approximately 14 m/s while pursuing a quadrotor-towed maneuvering target. The software and hardware are open source at https://github.com/HOLYNOTBAD/ISB-NMPC and https://github.com/HOLYNOTBAD/holydrone, respectively.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2407.11353

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping

Yingzhen Yang, Ping Li

原文摘要

We study nonparametric regression using an over-parameterized two-layer neural network trained with algorithmic guarantees in this paper. We consider the setting where the training features are drawn uniformly from the unit sphere in $\RR^d$, and the target function lies in an interpolation space commonly studied in statistical learning theory. We demonstrate that training the neural network with a novel Preconditioned Gradient Descent (PGD) algorithm, equipped with early stopping, achieves a sharp regression rate of $\cO(n^{-\frac{2αs'}{2αs'+1}})$, where $α$ parametrizes the polynomial eigenvalue decay of the regular Neural Tangent Kernel (NTK), $λ_j\asymp j^{-2α}$, and $2α=d/(d-1)$ under the spherical uniform design considered here. The target function is assumed to belong to the interpolation space $\bth{\cH_K}^{s'}$ with $s'\ge3$. This rate is even sharper than the currently known nearly-optimal rate of $\cO(n^{-\frac{2αs'}{2αs'+1}})\log^2(1/δ)$~\citep{Li2024-edr-general-domain}, where $n$ is the size of the training data and $δ\in (0,1)$ is a small probability. Our analysis is based on two key technical contributions. First, we present a principled decomposition of the network output at each PGD step into a function in the reproducing kernel Hilbert space (RKHS) of a newly induced integral kernel, and a residual function with small $L^{\infty}$-norm. Second, leveraging this decomposition, we apply local Rademacher complexity theory to tightly control the complexity of the function class comprising all the neural network functions obtained in the PGD iterates. Our results show how PGD changes the effective kernel in the reference training dynamics, inducing an integral kernel with lower complexity than the regular NTK arising from vanilla GD.

stat.ML · cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34785

Natural Jammers: When Non-Robust Features Become Antagonistic

Jiaming Zhang, Fuyao Zhang, Pengjun Xie, Wei Yang Bryan Lim

原文摘要

Deep neural networks are known to rely on non-robust features that align poorly with human perception. Prior work has largely framed these features as opportunistic shortcuts that help standard models on clean data. We show instead that non-robust cues can be antagonistic: they can act as Natural Jammers that actively mislead standard models on clean, unmodified images. Using disagreement between a standard model and robust models as an analysis lens, we identify a Jammed Set on which robust models outperform standard models. We provide causal evidence for Spectral-spatial Locking: jamming arises only when high-frequency components are precisely aligned with specific spatial structures. Disrupting this lock through spectral filtering or small geometric shifts can restore correct predictions. Crucially, we uncover a Substitution Paradox: while individual jammers are fragile to geometric shifts, the aggregate prevalence of jamming remains approximately stable and is redistributed rather than eliminated under such transformations. Our results reframe natural non-robustness as a failure field over the empirical model-data geometry: one that redistributes rather than disappears under small transformations.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.35032

JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments

Zhixi Cai, Fucai Ke, Sukai Huang, Maria Garcia de la Banda, Peter J. Stuckey, Gholamreza Haffari, Hamid Rezatofighi

原文摘要

In complex embodied visual reasoning scenarios, an agent often has only a limited field of view, and the evidence needed to answer a question may be distributed across time, viewpoint, and interacting objects. A model may therefore give a plausible answer without ever observing the relevant object, time, or view that supports it. Current visual reasoning benchmarks largely evaluate passive observations and final answers, overlooking settings that require active reasoning and evidence acquisition. We introduce JRDB-AVR, a benchmark derived from existing real-world JRDB robotics data through a structured question-generation engine that turns this gap into an explicit evaluation: an embodied agentic system receives a visual reasoning question, requests bounded observations by timestamp and viewing angle, and is evaluated on both the final answer and the grounded visual evidence supporting it. The benchmark contains diverse questions over multiple real-world environments involving temporal search, viewpoint selection, and human-oriented compositional reasoning. We also introduce JRDB-AVR-Agent, a reference active reasoning agentic method that maintains an explicit observation-grounded graph-based world model and answers through solving. Experiments reveal a substantial gap between answer accuracy and evidence accuracy in current baselines, showing that current VLMs can produce unsupported correct answers and that active evidence-aware evaluation is necessary for embodied visual reasoning. Code and benchmark are available at https://github.com/ControlNet/JRDB-AVR.

cs.AI · cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34782

ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing

Caiyi Sun, Yujing Sun, Siu-Ming Yiu

原文摘要

Recent generic reference-based image generation models natively support multiple conditions by concatenating all reference image and text tokens into a joint sequence processed by a single Diffusion Transformer (DiT). However, this versatile paradigm comes at an efficiency cost: accommodating multiple references leads to a token explosion, incurring massive $\mathcal{O}(N^2)$ computational complexity. Most acceleration methods operate inside the DiT, showing limited capability in reducing spatial redundancy and failing to alleviate peak VRAM. While some pre-model token reduction alternatives exist, they inevitably introduce external models. This raises a question: Is it possible to achieve acceleration and memory savings while preserving compatibility with in-model techniques and requiring no additional parameters? In this work, we realize this goal by proposing the early Token reduction via Downsampled self-Probing (ToDoPro). By executing a few denoising steps on spatially $2\times$ downsampled reference images, this cheap probing stage utilizes the DiT model itself to effectively and efficiently extract reference token importance. Using the probed importance, we apply a hierarchical reduction before the main denoising stage: we completely discard low-importance tokens, substitute mid-importance tokens with their downsampled counterparts to cheaply preserve global context, and keep high-importance tokens. Experiments across three base models and two benchmarks demonstrate that our early reduction accelerates inference significantly and mitigates peak GPU memory. Furthermore, we can improve generation quality by safely filtering out noisy, uninformative reference tokens, enabling the model to concentrate its limited attention capacity on genuinely useful tokens. The code will be released at https://github.com/scy639/ToDoPro

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34781

Uncovering the Turing Test's Latent Signal: Indistinguishability as a Reward

Emanuele Rimoldi, Riccardo Neumarker, Tomaso Poggio, Daniel Mitropolsky

原文摘要

Can a model learn by trying to fool another model? We show that it can. Inspired by the Turing Test and its recent generalization to arbitrary distinguishers, we introduce a domain-based teacher-Turing-Test, in which a stronger teacher model serves as both the target of imitation and the distinguisher, and a weaker student model is trained to make the teacher attribute responses to itself. We use this self-attribution (or fooling) probability as a reinforcement learning reward, without ever providing the student ground-truth answers, nor requiring the teacher to generate responses. We test our approach independently in four domains with verifiable answers: CommonsenseQA (reasoning), GSM8K (mathematics), KodCode (programming), and Spider (SQL), training a Qwen2.5-1.5B student/imitator model using DeepSeek V4 Flash as teacher/distinguisher. Beyond improving at passing the Turing Test, the student improves on independent, held-out evaluations in all domains and runs. To probe why being mistaken for the teacher can improve capability, our analyses reveal that self-attribution is associated with correctness -- substantially more than formatting changes -- and that it rewards partial correctness. Our results demonstrate a new, simple teacher-student training paradigm with a private and/or high-cost teacher. They also suggest that indistinguishability need not merely measure behavior -- it can also be a mechanism for learning.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.24064

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

Tianyuan Shi, Canbin Huang, Bei Li, Xin Chen, Xiaojun Quan, Jingang Wang, Qifan Wang

原文摘要

Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason. This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills, limiting generalization to novel problems. We propose Strategy-Guided Policy Optimization (SGPO), which replaces instance-level trajectory imitation with reusable strategy distillation. SGPO extracts structured strategy descriptions from strong-model responses and, for each problem, constructs both autonomous and strategy-guided trajectories to enable direct comparison of the model's behavior with and without strategic guidance. The framework then addresses two key questions. For how to distill, a token-level forward-KL objective selectively transfers the distributional shift induced by strategy conditioning into the unguided policy, with proximal constraints ensuring stability. For when to distill, adaptive instance-level weighting strengthens guidance when autonomous exploration falls short and reduces it as the model's own competence grows. Experiments on four mathematical benchmarks across two model families show that SGPO consistently outperforms SFT, on-policy RL, and hybrid-policy baselines, improving the average score by 2.2 points over the strongest baseline on Qwen2.5-7B-Instruct. Analysis reveals that the forward-KL objective provides an inherently selective distillation signal that outperforms direct trajectory imitation, and that strategy distillation exhibits complementary scaling with base model capability.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34778

Arya Forge: Auditing Validation and Release Approval for Financial Instruction Data

Kushagra Bhatnagar, Deekshith Marla

原文摘要

Financial instruction-data pipelines must distinguish content validity from permission to release a particular dataset. Arya Forge combines typed records, current-content checks, and approval coverage bound to a dataset manifest. We evaluate its release boundaries in a financial-data systems case study. An integrity audit covers 100,000 synthetic instruction records; a separate arithmetic implementation agrees with all 15,000 numeric records across twelve formula families. In 240 scenarios with 2,400 treatment rows, adding financial and release-record checks to a short-instruction filtering recipe rejects all injected numeric faults and policy holds while retaining 220 of 240 clean controls. The twenty lost controls comprise every tested cash-conversion-cycle example. Nineteen persisted-release cases show that eleven selected negative cases are blocked, four equivalent representations are rejected, and changes to external evidence after binding are outside ordinary Gold promotion's checks. Local processing measurements and controlled checkpoint resumptions characterize cost and recovery through 100,000 input rows. The results expose a tradeoff between strict producer-contract enforcement and useful-representation retention, and identify the protected inputs required for manifest-bound approval. These findings apply to the tested implementation and workloads; they do not establish general financial correctness, authenticated approval, expert-validated quality, or downstream model improvement.

cs.AI · cs.CY · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34777

Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition

Weihang Niu, Mengxing Ren, Che Qu

原文摘要

This paper introduces Scope-Gap Injection (SGI), an indirect prompt injection method for multi-stage LLM-agent safety pipelines. In the IJCAI 2026 OpenClaw Agent Security Attack Competition, each attack package is judged by a static skill scan (S1), an LLM-judge safety check over the task and skill definition (S2), and a live execution audit (S3). Our observations suggest a scope gap: S2 appears to inspect the task instruction and skill definition without inspecting attachment contents, while the agent reads attachments during S3. SGI keeps the visible task and skill benign, while target identifiers, bypass parameters, and authorization procedures are moved into an attachment written as a business worklist. The S2 judge therefore sees a harmless task, while the agent follows the hidden worklist and triggers the permission bypass. In OpenClaw, SGI bypassed all three stages for 5 of 19 targets. The highest-scoring single submission achieved $F = 0.385$. Across the submission campaign, attachment placement was associated with higher aggregate S2 acceptance than in-skill placement: 78% versus 23%. We close with defenses that align evaluator scope with the channels available to the agent.

cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.15911

Human-AI Synergy in Agentic Code Review

Suzhen Zhong, Shayan Noei, Ying Zou, Bram Adams

原文摘要

Code review is a critical software engineering practice where developers review code changes before integration to ensure code quality, detect defects, and improve maintainability. In recent years, AI agents that can understand code context, plan review actions, and interact with development environments have been increasingly integrated into the code review process. However, there is limited empirical evidence to compare the effectiveness of AI agents and human reviewers in collaborative workflows. To address this gap, we conduct a large-scale empirical analysis of 278,790 code review conversations across 300 open-source GitHub projects. In our study, we aim to compare the feedback differences provided by human reviewers and AI agents. We investigate human-AI collaboration patterns in review conversations to understand how interaction shapes review outcomes. Moreover, we analyze the adoption of code suggestions provided by human reviewers and AI agents into the codebase and how adopted suggestions change code quality. We find that human reviewers provide additional feedback than AI agents, including understanding, testing, and knowledge transfer. Human reviewers exchange 11.8% more rounds when reviewing AI-generated code than human-written code. Moreover, code suggestions made by AI agents are adopted into the codebase at a significantly lower rate than suggestions proposed by human reviewers. Over half of unadopted suggestions from AI agents are either incorrect or addressed through alternative fixes by developers. When adopted, suggestions provided by AI agents produce significantly larger increases in code complexity and code size than suggestions provided by human reviewers. Our findings suggest that while AI agents can scale defect screening, human oversight remains critical for ensuring suggestion quality and providing contextual feedback that AI agents lack.

cs.SE

查看论文
arXiv ↗PDF ↗