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 15:29 · 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 2026-11-08 15:43 — 2026-11-09 15:43（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 15:29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 3,653 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 15:27（北京时间）
版本更新 · v2arXiv:2610.09700

What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?

Nikos Giakoumoglou, Paschalis Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki

原文摘要

Synthetic hard negatives generated in the representation space have proven effective for unimodal self-supervised learning, but transferring this idea to vision-language pretraining is not straightforward. We analyze six representation-space synthesis strategies and identify two failure modes in their transfer to vision-language pretraining: cross-modal constructions that produce overly easy negatives or pull them toward the query, and intra-modal constructions that incorporate the matched positive. We also observe logit-scale saturation when training with synthetic hard negatives and a learnable temperature, and find that fixing the temperature improves downstream performance. Using this geometric analysis we propose SNAP, which generates intra-modal hard negatives that never involve the positive from either modality, avoiding both failure modes entirely. SNAP is model-agnostic, requires no external generative models, and adds less than 10% training time overhead. Evaluated on top of CLIP and FLIP across multiple architectures and datasets, SNAP delivers consistent improvements on zero-shot retrieval, zero-shot classification, and linear probe evaluation.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35267

Before Blaming the LLM, Diagnose the Workflow: A Role-Level Difficulty Profile for Translating Natural Language into Ontology-Grounded Statements

Liang Zhang, Benoît Daireaux, Sergey Alyaev

原文摘要

Natural-language-to-domain-specific-language (NL-to-DSL) semantic parsing systems increasingly translate informal user descriptions into structured artifacts such as Structured Query Language (SQL) queries, Application Programming Interface (API) calls, workflows, formal specifications, and ontology-grounded domain-specific language (DSL) statements. This paper focuses on ontology-grounded Assertion Box (ABox) DSL generation: the translation of natural language domain descriptions into assertion-level DSL statements grounded in a pre-existing ontology vocabulary. In this setting, syntactic validity is often easier to achieve than semantic adequacy. Failures are frequently attributed to weak generator models, but recurring sources of difficulty are also structural: insufficient input, weak domain grounding, output template and vocabulary gaps, weak validation, and non-local repair. We propose a role-level difficulty profile for diagnosing difficulty in ontology-grounded NL-to-DSL semantic parsing at the workflow level. The profile organizes diagnostic variables across five recurring workflow roles: Input, Generator, Output, Validator, and Repairer. The seven variables are input sufficiency, context availability, grounding complexity, template fit, vocabulary coverage, validation strength, and error observability. Practitioners construct the difficulty profile through qualitative judgment over available evidence. This experience-informed, non-exhaustive difficulty profile is intended to support workflow diagnosis and guide redesign or human-in-the-loop intervention.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.29483

VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data

Di Zhu, Yu Yvonne Wu, Hong Jia, Aaqib Saeed, Vassilis Kostakos, Ting Dang

原文摘要

Wearable devices provide continuous access to physiological signals such as ECG and PPG, offering a path to answering users' questions about their own physiological state and to early detection of cardiac and physiological abnormalities. Yet existing mobile health (mHealth) systems are largely limited to task-specific prediction pipelines or reactive question answering over static summaries. They lack the temporal reasoning, persistent physiological context, and proactive monitoring required for long-term signal streams. To advance this setting, we introduce VitalBench, a longitudinal physiological monitoring benchmark comprising 1,862 QA pairs for reactive question answering and 90.2 hours of continuous ECG/PPG recordings for proactive monitoring, covering cardiac, physical activity, and stress-related tasks. Building on this resource, we propose VitalAgent, a tool-augmented agentic framework for ECG/PPG-based mHealth that supports both reactive question answering and proactive monitoring. VitalAgent is built on a longitudinal physiological memory and a tool-augmented reasoning interface that enables dynamic computation over raw signals. Experiments demonstrate that VitalAgent achieves over 25 points absolute improvement over prompt-based and agentic baselines in reactive evaluation and enables proactive alert monitoring over long-term physiological signals, pointing toward mHealth systems that can both answer questions about and continuously monitor a person's physiological state beyond the clinic.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35244

Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks

Ngoc-Duy Mai, Ha-Thanh Nguyen, Hideaki Takeda

原文摘要

Emotion recognition in artworks remains challenging because affective meaning is often subjective, implicit, and shaped by relationships between visual form and semantic associations. While vision-language models provide strong multimodal representations, direct image-to-emotion prediction may overlook explicit relations among formal, semantic, and affective cues that support emotional interpretation. This paper proposes Visual-Semantic Affect Graphs (VSAG), a graph-based framework that represents artworks through interpretable feature nodes, including color, brushstroke, composition, light-shadow, line quality, and extracted visual entities. The graph learns feature-emotion associations for dominant emotion prediction, with valence-arousal structure modeled through an optional hierarchical auxiliary affect module. We evaluate VSAG and VSAG-TopK against direct VLM inference using Qwen3-VL and InternVL3.5 on EmoArt-5k. Results show that direct VLMs provide useful but modest baselines, while graph-based models improve dominant emotion prediction. In particular, the hierarchical valence-arousal variant of VSAG achieves the best overall performance, improving accuracy, macro-F1, and weighted-F1 over both direct VLM inference and the emotion-only VSAG baseline. Per-class results indicate that graph-based models and VLMs capture partly complementary signals, while valence-arousal structure is most useful when integrated as a coarse-to-fine affect hierarchy rather than as a simple post-hoc correction. These findings suggest that explicit visual-semantic structure can support both prediction and interpretation in artwork emotion recognition.

cs.CV · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35240

Reading Beyond OCR Noise: Robust Cross-Lingual RAG for Legislative Archives

Radha Krishna Deshpande, Ajoy Mondal, Akash Manna, C V Jawahar

原文摘要

India's historical public archives present severe computer vision and document image analysis challenges: decades of parliamentary records survive only as degraded, multi-column scanned pages featuring mixed scripts, complex layouts, and dense visual noise where OCR failure is the primary obstacle to information retrieval. We present an end-to-end framework that couples vision-based layout segmentation and multi-script OCR with an agentic retrieval-augmented generation (RAG) pipeline. Our approach specifically addresses how visual degradation and layout fragmentation propagate into text extraction errors, using an iterative agentic loop to navigate around OCR noise and layout ambiguities before generating answers. Evaluated on the 200,000-page Punjab Vidhan Sabha archive, our system demonstrates robust handling of historical document degradation, outperforming standard text-only baselines.

cs.CV · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28467

Beyond Trajectory Statistics: Community-Consistent Human Mobility Generation via Evolving User-Location Graphs

Bo Liu, Tong Li, Jiapeng Zhang, Zhu Xiao, Zhuo Tang, Kenli Li

原文摘要

Human mobility data are fundamental to Web-based location services and broader urban applications, and mobility generation provides synthetic trajectories when real data are costly or inaccessible. Although recent mobility generators have incorporated collective mobility patterns, they primarily focus on individual trajectories and aggregate population dynamics, leaving evolving community structures formed by user-location interactions insufficiently modeled. In this paper, we study community-consistent human mobility generation. To this end, we formulate mobility generation as the generation of dynamic user-location graphs to model community structures and propose MOTION, a Multi-agent framework for cOmmuniTy-consIstent human mObility geNeration. MOTION consists of user agents, location agents, and a global manager agent. MOTION first detects coherent communities from historical mobility using the Leiden algorithm and extracts community-conditioned interaction priors to guide the generation process. Guided by these priors, the user agents plan mobility, search destination candidates, and infer user movements from the individual view. In parallel, selectively activated location agents infer likely user arrivals from the community view. The manager coordinates both views, diagnoses interactions causing deviations, and attributes targeted reflection signals to revise user decisions, location attraction, and source-user selection. Experiments on two real-world datasets show that MOTION outperforms baselines by at least 4.05% across reported metrics of individual trajectories, population and flow distributions, and community and graph structures. Further analyses confirm its robustness, privacy preservation, and downstream utility. The code is available at https://anonymous.4open.science/r/MOTION-04C4.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35230

Context Is Not Free: Carbon-Aware LLM Routing for Multi-Turn LLM Web Services across Geo-Distributed Data Centers

Xiaoyang Zhang, Yuejun Yan, Qingang Zhang, Yonggang Wen

原文摘要

The sustainability of the Web has drawn growing attention, as large language model (LLM)-based web services leave a substantial carbon footprint. These services typically run in geo-distributed data centers whose grid carbon intensity varies across regions and over time, so routing each query to a cleaner region or a smaller model can reduce emissions. A conversation, however, is a stateful web session: each turn reuses the key--value (KV) cache of its history, which resides only where earlier turns were served. Serving a turn on another deployment requires recomputing this history, whose carbon cost grows with the conversation and can outweigh the saving of the move. Existing carbon-aware LLM routers treat a conversation's queries as independent and ignore this cost. We present CarbonRouter, an online framework that jointly selects the model, GPU type, and region for each query to minimize carbon emissions. CarbonRouter introduces a cache-aware carbon cost model, which charges history recomputation to every candidate deployment using cached-token counts from the serving backends, and uses a lightweight gate that keeps a session on its cached deployment when it would likely move back at the next turn and rebuild its history again. We evaluate CarbonRouter in trace-driven experiments on two real-world conversation datasets with five LLMs, three GPU types, and four regions, where it achieves the lowest carbon of all policies. CarbonRouter reduces CO$_2$ by 16.1\% on average relative to FairCarbon, a state-of-the-art carbon-aware router with the same action space, while also improving predicted answer quality and estimated latency. Moreover, the saving rises further to 23.1\% for sessions longer than 30 turns.

cs.DC · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35226

Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment

YaJie Yin

原文摘要

Reasoning-tuned and reward-trained models are often assumed to verify more reliably because they reason longer or receive correctness signals. We test this in evidence-sufficiency judgment: deciding whether available information actually supports a causal claim, a domain with no decidable correctness reward. Using a pre-registered, same-base, controlled knock-in design, we compare a boundary-keeping recipe (SFT then GRPO) with its own baseline, a scrambled-pairing placebo, and a general-purpose reasoning model under an action-pressure protocol with no evaluation invitation. All load-bearing outcomes are rated by two separate model-rating sessions masked to arm labels; automatic judges only trigger. The trained arm raises spontaneous correct refusal from 25% to 100% (40 per arm; Wilson 95% CI lower bound 91.2%, non-overlapping with the baseline interval [14.2%, 40.2%]), while the scrambled placebo collapses (5% spontaneous / 7.5% invited correct; 91.1% false refusal). The effect is boundary-specific rather than blanket refusal: automatic false refusal on 281 well-formed claims is 1.1% (Wilson upper bound 3.09%), and a targeted 18-item arm-(c) recheck (3 flagged plus 15 accepted) yields 0/18 and 1/18 false refusals in two sessions. The dissociation is the main result: final boundary-keeping is trainable without an inference-time verifier, while observed active numeric/calculation checking in the H3 assay remains near zero; SFT saturation makes the GRPO increment not separately identifiable. A pre-registered mechanism adjudication favors reward internalization of final-action status (H2, best-supported, not proven). The scope is a controlled 14B same-family study: we do not claim proof, cross-family generality, or independent human-expert validation; the rating sessions are model sessions, not human reviewers.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.01478

Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX

Martin Schuck, Marcel P. Rath, Yufei Hua, Abhishek Goudar, SiQi Zhou, Angela P. Schoellig

原文摘要

High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing robots' capabilities. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that synthesizes data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the frontier of aerial robotics algorithm development, supporting model-based and data-driven methods, gradient-based and sampling-based approaches, single- and multi-agent systems, and state- and vision-based policy learning. Crazyflow combines high-fidelity dynamics with JAX for speed and differentiability, scaling to millions of environments or thousands of swarms with thousands of drones on single CPUs and GPUs, and beyond on clusters. Real-world experiments show Crazyflow supports both analytical-gradient-based policy learning, achieving high-accuracy tracking without domain randomization, and sampling-based obstacle avoidance at speeds exceeding half a billion steps per second. Breaking the traditional train-then-deploy paradigm, Crazyflow's performance enables in-flight reinforcement learning; we demonstrate this by throwing a physical drone into the air and training a recovery policy from scratch in 0.37 seconds, catching it before it hits the ground. By pushing accuracy, speed, and differentiability simultaneously, Crazyflow serves as an open-source resource for synthetic data generation, with emerging capabilities for large-scale parallelization for online, in-execution learning and optimization, opening the door to novel algorithm development.

cs.RO · cs.AI · cs.MA · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.24042

Hidden-State Privacy Has an Empty Middle

Alexander Okezue Bell

原文摘要

Of $1{,}536$ Gaussian release covariances we tested for single-layer hidden-state privacy, zero achieve both moderate utility and moderate privacy against an adaptive retrieval attacker. We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width, ruling out uniform Gaussian safety in the class and matching the empirical empty middle. The diagonal inverse-Fisher release $Σ^\star_{\mathrm{diag}}(\mathcal{K}) = (2\mathcal{K}/d)\,\mathrm{diag}(1/F_{ii})$ is the unique minimax-optimal diagonal mechanism at first-order KL budget $\mathcal{K}$ and the only release with worst-attacker top-1 $\le 0.001$ at every point of a 32 model-layer grid, but it sits on a privacy/utility edge rather than filling the middle. A generalized-eigen mechanism reaching $13\times$ Pareto reduction under Euclidean retrieval collapses to $100\%$ top-1 under the adaptive Mahalanobis attacker, and a full-trajectory sequence inverter recovers $94\%$ of clean GPT-2 prefixes but $0\%$ under $Σ_{\mathrm{diag}}$. A split-memory transformer trained from scratch reaches $G_{\mathrm{Mah}} \in [20, 33]$ at 90M and maintains a $6$--$24\times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language-modeling loss penalty; pretrained models top out at 9.3. These results reframe hidden-state release from mechanism-design within the Gaussian class to architecture or release co-design.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35218

MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs

Fengshi Zhang, Xiyan Ding, Shuxiao Xie, Wei Zhang

原文摘要

Generative recommendation with semantic IDs (SIDs) represents each item as a sequence of discrete tokens and autoregressively predicts the next item's SID. Despite strong recommendation performance, repeated decoding over multiple SID positions incurs substantial inference cost. Knowledge distillation transfers knowledge from a powerful generative teacher to a lightweight student, yet conventional objectives do not fully account for multi-token SID generation. We identify two limitations: item-level distribution alignment may not adequately preserve the teacher's ranking of candidate groups sharing SID prefixes, while uniform alignment across SID positions may affect final item ranking differently. We propose MuSID-KD, which combines Hierarchical Candidate Distribution Alignment (HCDA) and Ranking Impact Guided Levelwise Distillation (RIGD). HCDA aggregates item probabilities according to shared SID prefixes and aligns candidate distributions at successive levels, from candidate groups to individual items. RIGD evaluates the reduction in pairwise ranking surrogate loss when one student score contribution is replaced with the teacher's contribution, and allocates supervision accordingly. Experiments on real-world recommendation datasets using three lightweight student architectures demonstrate improved recommendation accuracy and better alignment of prefix marginal distributions and pairwise item rankings, without modifying the student's online inference architecture. Code is available at https://anonymous.4open.science/r/m7k2-review-83f9/.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.01104

CausalMix: Data Mixture as Causal Inference for Language Model Training

Zinan Tang, Yukun Zhang, Shaomian Zheng, Zhuoshi Pan, Qizhi Pei, Dingnan Jin, Qing Cui, Jun Zhou 等 10 位作者

原文摘要

In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely on the assumption of static data distributions. As a result, when the underlying data pool shifts, these methods require costly retraining from scratch. This limitation restricts their ability to scale seamlessly from small settings to larger data pools and model sizes. In this paper, we propose CausalMix to address this limitation by casting data mixture optimization as a causal inference problem. We formulate the statistical features of the data pool as covariates and the domain mixture as the treatment. After fitting a causal model on 512 runs of Qwen2.5-0.5B to estimate the Conditional Average Treatment Effect (CATE), we extrapolate the optimal mixture for an 800K data pool and apply it to train a 7B model. Furthermore, we successfully generalize the framework to long chain-of-thought data on Qwen3-4B-Base. By leveraging causal modeling to isolate confounding biases, CausalMix infers state-dependent data mixtures offline, with the selected mixture fixed during each training run. Extensive experiments show that the mixture guided by CausalMix achieves competitive performance across downstream tasks compared with other baselines. The CATE Interpreter visualizes the learned mixing strategy. Overall, CausalMix offers a causal and interpretable framework for optimizing LLM data mixtures.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35215

SkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills

Chenxu Zhang, Zhou Liu, Wu Xin, Wentao Zhang

原文摘要

Web agents reuse skills whose stored code, selected version, and loaded implementation can diverge across tasks and updates. SkillLifeBench links these states to task outcomes in 388 paired scenarios spanning implementation, interface, runtime, composition, and version changes. We evaluate 14 models on two paired decision tracks: 89 runtime tasks and 60 autonomous lifecycle tasks spanning 12 templates derived from introduced cases. Lifecycle tasks allow agents to inspect, select, and reconfigure skills while completing verifiable user requests. Joint success requires task completion without the registered attack goal. GPT-5.6-Sol and Sonnet 4.6 both achieve 82.0% on runtime tasks, but reach 96.7% and 56.7% on lifecycle tasks. Across lifecycle evaluations, challenged task success is 77.5%, while joint success is 65.2%; 103 runs complete the task and the attack goal. Adding execution provenance in a matched recovery study raises utility joint success from 49.35% with logs and metadata to 65.58%. A deterministic execution-consistency rule reaches 64.94% with higher benign utility, while full restoration reaches 69.48%. Lifecycle tasks distinguish models with similar runtime scores, and execution evidence improves recovery.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35982

Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering

Elizaveta Zinovyeva, Aiham Taleb, Nikita Kozodoi, Daniel Schleicher, Amir Mahdi Namazi, Martin Kraus, Levent Kent, Brian Jensen

原文摘要

Research on coding agents mainly focuses on generation quality. Yet, safety-critical automotive software makes two additional demands. It prioritizes verification, since every change is reviewed, traced to a requirement, and checked against industry standards such as MISRA and AUTOSAR before it can be committed. It is also a narrow domain, written against layered architectures, embedded resource constraints, and organization-specific interface conventions that are scarce in the data general-purpose LLMs are trained on. We present a coding assistant for automotive C/C++ that addresses both demands. First, it exposes three tools to the user over the Model Context Protocol (generate, edit, and verify), allowing developers to run verify on any code on demand rather than relying on the agent to check its own output. Second, rather than using a general-purpose model, we customize the underlying LLM for the automotive domain through prompt engineering and fine-tuning. We construct a dataset from automotive production code of AUMOVIO, where each function is paired with the requirement texts and Unified Modeling Language (UML) behavior it must satisfy. In a two-week pilot on active production projects, developers report verify as the most-used tool and confirm using it on their own code and not only on generated output. Comparing model customization strategies, 75% prefer the faster prompt-engineered configuration. MISRA- and AUTOSAR-inspired pattern checkers indicate that prompt engineering achieves a lower number of violations on C, while fine-tuning shows better conformance with architecture patterns for C++.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35212

One-Shot Federated Model Editing for Device Dynamics at the Edge

Youming Tao, Weijun Yin, Huanyi Xie, Yanqing Yao, Dongxiao Yu, Xiuzhen Cheng, Di Wang, Falko Dressler

原文摘要

Standard federated learning (FL) requires persistent device connectivity across multiple communication rounds, making it unsuitable for dynamic environments such as vehicular networks, where devices frequently join and leave. One-shot FL offers a promising alternative by completing training in a single communication round. However, one-shot FL suffers from model solidification and cannot readily adapt to subsequent client dynamics, including new client contributions and the withdrawal of previous contributions. We therefore consider exact model editing, which removes withdrawn contributions through unlearning or incorporates newly contributed ones through incremental learning without retraining from scratch. We identify that efficient editing fundamentally hinges on learning stability. To this end, we propose F-SOSA, the first stable one-shot FL algorithm that enables rapid and exact model editing. F-SOSA leverages sub-sampling of local models with carefully tuned rate for stable aggregation and performs curvature-aware model fusion to preserve utility. We prove that F-SOSA achieves vanishing training error and reasonably small generalization error bounds. Building on this stability, we further develop two single-round editing algorithms: F-SOSA-U for unlearning and F-SOSA-I for incremental learning. They ensure that the edited model, along with all intermediate algorithmic states, is statistically indistinguishable from retraining while incurring only an expected $O(ρ)$ fraction of its cost, where $ρ$ quantifies stability. Experiments demonstrate that our approach matches retraining performance while reducing cumulative time and communication overhead by at least 36% and 22%, respectively, under realistic urban mobility simulations.

cs.LG · cs.AI · cs.DC · cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35211

Efficient Exact Unlearning for Federated Zeroth-Order Optimization

Weijun Yin, Yanqing Yao, Falko Dressler, Di Wang, Youming Tao

原文摘要

Federated zeroth-order optimization (FedZOO) reduces the memory and communication costs of collaborative training for edge intelligence by avoiding backpropagation while communicating only random seeds and scalar coefficients. However, existing methods lack efficient mechanisms for exact unlearning to fully remove the influence of training data when users request deletion. A key insight is that total variation stability of the learning algorithm creates overlap between model distributions before and after data deletion, allowing exact unlearning to reuse computation through coupling. Based on this observation, we jointly design two stable zeroth-order learning algorithms and their corresponding exact-unlearning procedures: \textsc{FedZOO-S} obtains stability through client and mini-batch subsampling, enabling \textsc{FedZOUL-S} to perform efficient unlearning by preserving earlier updates and restarting from the first affected step. \textsc{FedZOO-NS} further combines subsampling with Gaussian noise to increase overlap between update distributions; \textsc{FedZOUL-NS} exploits this overlap through rejection--reflection coupling to reuse affected updates when the coupling is accepted. We prove exact unlearning for both algorithms: the model and saved state have the same joint distribution as retraining with the corresponding learner on retained data. We further establish stability and convergence guarantees for the learning algorithms and derive upper bounds on expected unlearning cost. Experiments demonstrate effective unlearning with competitive model utility and up to $56.1\%$ less cumulative unlearning time than re-optimization. Compared with first-order baselines, our methods reduce communication overhead by up to approximately four orders of magnitude.

cs.LG · cs.AI · cs.DC · cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35208

Same Story, Different Lens: A Multi-Agent System for Cross-Outlet News Framing Analysis

Affan Yasin, Yueqi Lyu, Rubia Fatima, Weinchen Zhong, Keyi Li

原文摘要

News outlets covering the same event differ in what they emphasize and omit. \textit{Same Story, Different Lens} is an experimental research prototype for comparing these choices. It collects world and politics coverage from 17 outlets, groups reports about the same event, and produces structured analyses of sentiment, political lean, framing, loaded language, possible omissions, and model-estimated proportions of factual claims and opinion. Loaded-language entries include quotations and neutral rewordings. Three model roles (agents) handle article analysis, assessment of source support, and cross-outlet briefing generation. Analyses are stored in a JSONL archive. The evaluation compares outlet-level lean estimates with approximate, predefined reference ratings and summarizes the Critic's model-assigned grounding scores. These measures provide preliminary diagnostics. A grounding score reflects the model's assessment of support in the supplied text and does not establish factual accuracy or constitute independent verification.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35203

OrthoRF: Exploring Orthogonality in Object-Centric Representations

Despoina Touska, Bastiaan Onne Fagginger Auer, Alexandru Onose, Tejaswi Kasarla, Luis Armando Pérez Rey, Maximilian Lipp, Lyubov Amitonova, Martin R. Oswald 等 9 位作者

原文摘要

Neural synchrony is hypothesized to help the brain organize visual scenes into structured multi-object representations. In machine learning, synchrony-based models analogously learn object-centric representations by storing binding in the phase of complex-valued features. Rotating Features (RF) instantiate this idea with vector-valued activations, encoding object presence in magnitudes and affiliation in orientations. We propose Orthogonal Rotating Features (OrthoRF), which enforces orthogonality in RF's orientation space via an inner-product loss and architectural modifications. This yields sharper phase alignment and more reliable grouping. In evaluations of unsupervised object discovery, including settings with overlapping objects, noise, and out-of-distribution tests, OrthoRF matches or outperforms current models while producing more interpretable representations, and it eliminates the post-hoc clustering required by many synchrony-based approaches. Unlike current models, OrthoRF also recovers occluded object parts, indicating stronger grouping under occlusion. Overall, orthogonality emerges as a simple, effective inductive bias for synchrony-based object-centric learning.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35193

Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

Jiayue Pu, Ang Gao, Jinyi Bai, Qipeng Wang, Tongyu Wen, Jiahao Zhao, Keyu Qu, Junhao Zhang 等 12 位作者

原文摘要

AI systems built around large models increasingly use experience and feedback to make persistent changes to models, prompts, memories, tools, and workflows. Recursive self-improvement (RSI) extends this process to inductive biases and to the mechanisms that govern future updates, which can themselves be revised and reused across improvement cycles. Yet self-modification alone does not guarantee trustworthy improvement. Reported gains may reflect flawed evaluations, previously acquired capabilities may deteriorate, and compliance with behavioral constraints may weaken. Compromised artifacts or sensitive information may also persist in successor systems. Changes to improvement mechanisms may invalidate earlier verification results and make human oversight less effective. This survey presents an operational definition and process framework for RSI and organizes the requirements for trustworthy RSI into four interconnected themes: genuine and sustained improvement; behavioral constraints, alignment, and fairness; system security and privacy; and transparency and controllability. We examine these themes from three perspectives: Improvement Validity, Constraint Preservation, and Effective Oversight. This analysis covers improvement diagnosis, proposal generation, proposal evaluation, and update implementation (S1--S4), including the recursive application of these stages to improvement mechanisms (RI). We review risks, safeguards, and evaluation evidence for individual updates, effects inherited by successor systems, and revisions to improvement mechanisms, while distinguishing direct RSI findings from evidence in related systems. Finally, we examine evaluation settings, identify requirements for independent and longitudinal assessment, and discuss applications and open research problems.

cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35188

V$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents

Weitao Feng, Hengheng Xiong, Zihao Zeng, Jun Chen, Jiyang Guan, Xiaofeng Wang, Jialing Tao, Hui Xue 等 9 位作者

原文摘要

Large language models increasingly act through code, modifying repositories, executing programs, and interacting with services in agent form. Their actions introduce risks that cannot be assessed from generated responses alone. Safety evaluation must verify actual consequences, distinguish harm avoidance from task incapability, and cover realistic workflows. We introduce V$^3$AST-Bench, a benchmark for Verifiable results, Valid interpretation, and Versatile risk coverage of Agent Safety. It comprises 212 risk tasks spanning 18 categories. Dedicated runtime environments verify harm and task outcomes through executable checks over states, records, and artifact behavior, while paired capability twin tasks verify workflow competence. Our experiments span 51 combinations of 11 models and five harnesses, spanning 86,496 trials and over 9 billion tokens of model interaction. Results show that V$^3$AST-Bench remains challenging even for frontier coding agents, as Claude Opus 4.8 with Claude Code still causes verified harm on 20.9% of tasks. Across model-harness combinations, agents with comparable competence exhibit markedly different safety outcomes, showing that task capability alone does not guarantee safe execution. More importantly, even explicit recognition of risks does not reliably prevent harmful actions, revealing a critical gap between risk awareness and safe execution. These findings highlight the need to move beyond risk recognition toward enforcing safety throughout execution.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2607.11183

Amplitude-Only FFN Intervention for Tool-Structured LLM Inference: Method, Gated Evaluation Protocol, and Cross-Model Empirical Results

Sheng Xu, Zhen Chen, Junhua Wang, Boyuan Huang, Ke Jia, Jiadun Zhu, Yiming Xu

原文摘要

We study amplitude-only rescaling of feed-forward network (FFN) activations to repair tool calls and other structured outputs, using multiplicative coordinate masks rather than additive steering vectors. Amplitude Gating (AG) keeps pretrained weights fixed and applies magnitude/entropy-based masks at six SwiGLU sites, with a Newton-Schulz windowed ranking variant. Across three Qwen checkpoints and six text/tool endpoints, effects are task dependent. Under frozen local scorers, Qwen3.5-9B non-NS configurations improve two function-call endpoints by +2.61/+2.67 percentage points (pp) and static ToolBench in/out-domain by +1.64/+2.82 pp; JSON gains are small. These gains survive comparing the weaker of two observed AG runs with the stronger baseline, supporting observed-run robustness rather than population significance. Scores measure lexical or answer/action-name agreement, not executed-tool success. Under the current experimental conditions, the six-task random-forest refit improves native score by +0.46 pp with a positive conditional paired interval; transfer to other settings requires further evaluation. The results support task-specific interventions; causal mechanisms, equal-budget advantages, repeated-run uncertainty, and serving cost require further evaluation. Code and experimental data: https://doi.org/10.5281/zenodo.23654706.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35169

Formal Explanations for Linear Temporal Logic over Finite Traces

Valeria Fionda, Antonio Ielo, Francesco Ricca

原文摘要

Linear Temporal Logic over Finite Traces (LTLf) is widely used in Artificial Intelligence to specify desired temporal behavior and determine whether finite traces satisfy or violate it. Explaining these outcomes is essential for debugging and trust. However, existing approaches typically capture either sufficient reasons or counterfactual causes, without clarifying their relationship. We introduce a native characterization of abductive (AXps) and contrastive (CXps) explanations directly over finite traces, based on locking and unlocking time-indexed events. We prove its equivalence to the classifier-based formulation, and show that CXps coincide with a recently proposed temporal causality semantics for LTLf. This characterization enables an efficient implementation based on the enumeration of minimal unsatisfiable cores and minimal correction sets of ASP programs. Experiments on real-world event logs demonstrate the effectiveness of the approach.

cs.LO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35980

UnityBench-Mini3D: Evaluating LLM Agents for 3D Game Development in Unity

Yijun Zhou, Minghao Shao, Ke Zhang, Renkai Yuan, Hongbo Yuan, Bin Hu, Bozhao Qian, Hongxia Shen 等 23 位作者

原文摘要

Game development stresses coding agents in ways general software engineering does not: correctness depends on how engine APIs, serialized scene state, and runtime behavior interact, not on source code alone. Existing benchmarks mainly target platforms such as Godot and heavily rely on LLM judges or coarse task-level outcomes. We present UnityBench-Mini3D, a benchmark of 77 project-level Unity tasks organized around seven expert-defined skill categories rather than tutorials or genres, with three difficulty tiers. Each task pairs a complete Unity project with natural-language requirements and is evaluated using 1,178 held-out, human-authored milestone tests covering scene structure, component configuration, and runtime behavior. This in-engine evaluation provides deterministic partial credit, localizes failures, and distinguishes partial implementations from complete solutions without relying on subjective judges. Across 21 models and 9 coding harnesses, the average pass rate reaches 80.9% on easy tasks but falls to 35.2% on hard tasks, with just 57.7% overall. UnityBench-Mini3D provides a reproducible, diagnostic testbed distinguishing systems across difficulty levels.

cs.SE · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35151

SoK: Timestamps Are Not a Time Model: Rethinking Temporal Reasoning in Host-Based Intrusion Detection

Rene Heinzl, Markus Nissl

原文摘要

Host-based intrusion detectors order events, window audit streams and sequence attack stages by their timestamps. Every conclusion they draw therefore rests on assumptions about clocks, delivery, entity identity and the integrity of the evidence, and most of these assumptions go unstated. This Systematization of Knowledge (SoK) makes them explicit. Drawing on temporal databases, stream processing and runtime verification, we distill five components of a time model, together with a checklist of evidence assumptions and four levels of guarantee, and walk through a running campaign with them. A documented search yields fifteen families of detection and investigation. For papers selected by screening role and period, plus named systems and landmarks, we check the stated assumptions in the full texts, and we assess eleven temporal knowledge representation and reasoning (KRR) formalisms and a learned baseline on nine attack patterns. Some early alert correlators stated clock and delivery assumptions, and forensics measures clock error. Current provenance-based detectors state no clock bound. Four audited papers describe input-ordering conditions or conventions, but none specifies conditions for conclusion validity across a stated class of delivery failures. In the selected provenance-based systems, campaign composition uses system-specific procedures or objectives, learned state, causal graph queries or language models, and beyond CEP-based query systems, we found no temporal rule language or stream reasoner from KRR applied to host audit data. In 28 of 38 audited provenance-era detector papers, capture or stored evidence is trusted or its manipulation is placed out of scope, and none says which conclusions survive deleted, delayed or forged records. Five open challenges follow from these gaps.

cs.CR · cs.AI · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35150

LongSearchEval: Evaluating Long-Horizon Web Search Capabilities of Large Language Models via a Trajectory-Aware Agent Framework with Failure-Node Localization

Jialiang Liu, Shusheng Li, Wenjun Tan

原文摘要

Long-horizon web search requires LLM-based agents to integrate information across web pages through extended interactions under task-specific constraints. Evaluating this capability is important not only for measuring final answer quality, but also for assessing whether an agent acquires, verifies, and uses evidence reliably over extended interactions. Existing evaluations, however, mainly rely on simulated trajectories or on post-hoc trajectories reconstructed from final answers, rather than on retained real interaction traces, which limits the fidelity of behavioral assessment and weakens support for fine-grained error localization. To address this gap, we introduce LONGSEARCHEVAL, a trajectory-aware agent evaluation framework that combines a unified agent execution protocol with source constrained outcome verification and retrospective failure-node localization. Stage 1 verifies answer groups against agent-cited webpages without human-authored gold answers; Stage 2 audits normalized rounds and links flagged failure nodes to incorrect answer groups. We evaluate 16 models from eight families on 100 tasks, yielding 1,600 retained runs and 6,545 automatically flagged failure nodes. Trajectory collection and evaluation required 1,037 and 318 hours of cumulative runtime, respectively. Human validation yields 94.50% agreement on supplied answer-group labels and 98.11% feature-correspondence precision for audited round-group links. Together, outcome scores and linked trajectory evidence support controlled model comparison and retrospective inspection of answer-related content.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35147

Locked In: Multi-Objective RL for the AI Data Center Build-Out

Satyapragnya Kar, Rajarshi Das, PR Panigrahi

原文摘要

AI data center build-out is a multi-trillion-dollar, multi-decade infrastructure program. Yet siting, power procurement, and cooling decisions are still made with static, single-point scoring tools. These tools are evaluated once, on day-zero numbers. This is a poor fit. A site's water, power, and carbon profile drifts substantially over the 10 to 20 year asset life. The governing decisions are also irreversible, and they bind capital and physical plant for years. We formalize long-horizon build-out as a tiered multi-objective Markov decision process. Strategic commitments are gated to discrete windows, incur switching costs, and energize only after source-dependent lead times. Operational dispatch is restricted to capacity that physically exists. We solve the problem with a preference-conditioned multi-objective agent that has a semi-Markov manager and worker hierarchy. The agent recovers a family of policies that a planner can steer across cost, carbon, water, and reliability at inference time. We validate long-horizon dynamics with a lightweight counterfactual rollout model. Across three commitment regimes (irreversible, reversible, and commit-once) on real site data, preference conditioning yields a confirmed, steerable trade-off on both objective pairs in every regime. Imposing lock-in produces a more evenly covered frontier and a far more consistent rate of anticipatory retrofit ahead of a binding water-stress constraint than a freely reversible formulation. Finally, a compact counterfactual dynamics model tracks slow-moving state well. It is measurably outperformed by simple persistence on the water-stress axis. We report this limitation rather than obscure it. We release the environment, agents, baselines, and evaluation harness. All of them are grounded in real interconnection-queue, water-stress, and grid-emissions data.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35138HF 社区推荐

Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models

Xilin Wei, Shengyuan Ding, Xinyu Fang, Tiancheng Gu, Yuchi Wang, Zhixun Li, Ziyu Liu, Yuhang Zang 等 16 位作者

原文摘要

Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding sessions. Its two tracks, Multimodal Editing (ME) and Repository Editing (RE), cover localized edits with optional image, audio, video, or document inputs and coordinated repository revisions. Tasks span three capability dimensions: Grounded Understanding, UI Transformation, and Functional Implementation. The tasks pair normalized requests and runnable pre-edit applications with 2,331 hidden expert-authored acceptance criteria. Our judge-then-refute protocol grades criteria using source and browser evidence, challenges positive verdicts with a separate LLM verifier, and audits visual and interaction claims without gold code or target screenshots. Under a shared agentic harness, the strongest of ten model endpoints passes an average of 69.9% of criteria per task but fully satisfies only 26.4% of tasks. All ten endpoints achieve lower criterion completion on repository edits spanning three or four change types than on those spanning one or two. Co-Design Bench provides a testbed for studying the gap between partial requirement satisfaction and complete task success under agentic execution for real-user application revisions.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35125

When Fusion Order Matters: Insights on Progressive Multimodal Representation Learning for Cross-modal Retrieval

Haoxiang Zhao, Bin Wang, Yaofei Wang, Xiao Lan, Yunfeng Diao, Xu Wang

原文摘要

Multimodal video retrieval combines visual, acoustic, and speech information, yet how their fusion order should depend on the data and the retrieval query remains unclear. We introduce Unified Progressive Representation Learning for Order Analysis, or UniPRO, to investigate this question through configurable fusion schedules with matched model components and training settings. Starting from text-to-video retrieval, we find that the tested one-by-one schedules outperform stacked fusion, while changing the order within one-by-one fusion also changes performance. To guide order selection, we examine two complementary considerations: learning difficulty under unequal modality availability and preservation of information relevant to the query. Complete-modality controls show that missing inputs alone cannot explain order sensitivity. At R@1, text and audio retrieval favor schedules that introduce the modality matching the query last. Controlled speech missingness during training and testing reverses the preferred order in both R@1 and SumR, with different crossover points. These findings motivate balancing the two considerations when selecting a fusion path. We then use them to predict a visual-last schedule for image queries, which achieves 97.9 R@1, the highest among the evaluated orders on MSR-VTT-9k. Main experiments on four text-to-video benchmarks establish the effectiveness of UniPRO, with component ablations assessing its supporting design. Together, the results identify fusion order as a task-dependent choice that should account jointly for modality availability and the retrieval query.

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35123

Generative AI in Turbulence: Foundations, Applications, Validations and Benchmarks

Luca Biferale, Michele Buzzicotti

原文摘要

Generative AI offers new approaches to turbulence problems in which incomplete observations or unresolved d.o.f. admit multiple physically plausible solutions. Potential applications include stochastic closures, super-resolution, data assimilation, uncertainty quantification, and the generation of Eulerian and Lagrangian flow ensembles. However, turbulence is not a conventional image-generation problem. Its multiscale dynamics, intermittency, extreme events, rough velocity fields and intrinsically stochastic transport make visual realism, pointwise error, and low-order spectral agreement insufficient measures of physical fidelity. We examine where generative AI provide novel capabilities with emphasis on diffusion models, score-based methods, and related probability-transport formulations. We discuss their use in unconditional generation, probabilistic reconstruction, reduced-order modeling, temporal evolution, and mesh-free representations. We argue that validation must address turbulence properties: energy transfer, structure functions, anomalous scaling, pdf tails, coherent structures, conservation laws, temporal consistency, ensemble diversity and generalization. Finally, we discuss potential limitations in validation, baseline, data availability and reproducibility, and the need for a benchmark ecosystem combining open data, standardized challenges, hidden tests, physics-aware metrics, and documented failures. This paper serves as a bridge between two communities. For AI practitioners, we provide a fair and accessible introduction to turbulence, essential for appreciating the challenges posed by the field and for assessing the physical relevance of generative models. For turbulent practitioners, we provide an introduction to the key technological aspects of Generative AI, clarifying what these tools actually do, and where their potential and current limitations lie.

cs.AI · cs.LG · nlin.CD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35113

UTA: Universal Training Adaptive Learning Rate Decay

Anda Tang, Junjie Wang, Xuanlin Yang, Cong Fang, Zhouchen Lin

原文摘要

Learning rate decay (LRD) is critical for training high-performance models, yet most designs remain empirically driven. Although the Universal Budget Aware (UBA) LRD offers a theoretical framework, its reliance on SGD dynamics limits its applicability to modern Adam-type optimizers and leaves its key `optimization difficulty parameter' opaque. To bridge this gap, we propose the Universal Training Adaptive (UTA) LRD. Unlike UBA's fixed offline trajectory anchored solely to iterations, UTA treats LRD as a closed-loop shape-and-scale problem. By continuous-time formulation, UTA is training-state adaptive with segment-wise optimal shape. This adaptivity links external iterations with internal training states, enabling a near-optimal path in both progression shape and learning rate (LR) scale, a property unattainable by other LRDs, including UBA. Empirically, we demonstrate consistent improvements across language models (LLaMA 60M to 1B) and vision models (ResNet50, ViT-B) on ImageNet with plug-and-play ease and negligible overhead. Extensive ablation studies further confirm UTA's robustness across dimensions, including peak LR, final decay ratio, its parameter $\varphi_0$, component efficacy and generalization to fine-tuning scenarios, underscoring its practical implementability.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗