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

+367新增论文

+288其中 AI 相关

+33已有论文修订

+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 10:18 · 全站最近入库：2026-11-09 10:17各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 11:17 — 2026-11-09 11:17（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 10:18最近发现新增版本：2026-11-09 10:17库内论文最新更新时间：2026-11-06 12:44

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。

17,467 已收录论文14,949 AI 相关4,222 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 3,417 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 10:16（北京时间）

新论文 · v1arXiv:2610.37041

更新于 2026-10-27

Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards

Bo Yang, Zishuai Zhang, Weihua Li, Qinnan Zhang, Sijia Wen, Hainan Zhang

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has shown strong empirical gains in improving the reasoning ability of large language models (LLMs) on tasks such as mathematics and programming. However, recent studies have shown that RLVR rollouts often collapse onto a narrow set of reasoning trajectories, limiting the explored reasoning space. Motivated by findings that thinking tokens at critical steps serve as critical structural elements in LLM reasoning pathways, we propose Guided-RLVR, a novel approach that augments RLVR with a lightweight controller. The controller strategically injects semantically meaningful steering tokens into the sampling distribution, encouraging the model to approach problems from multiple reasoning perspectives and thereby expanding the exploration space. Experiments on mathematical reasoning and code generation benchmarks show that Guided-RLVR consistently outperforms existing RLVR methods while producing more diverse reasoning trajectories.

cs.AI · cs.CL

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.37037HF 社区推荐

更新于 2026-10-27

Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception

Lai Wei, Yatai Li, Liangbo He, Jun Lan, Renjie Gu, Linhan Cao, Junkai Lin, Huijia Zhu 等 13 位作者

原文摘要

Multimodal perception forms the foundation of multimodal intelligence. In particular, spatial perception and multimodal long-context understanding are two pivotal tasks that underpin embodied AI and multimodal agents. However, synthesizing targeted, high-quality training data for these tasks remains difficult and costly. Our key insight is that these tasks share an underlying capability, which we call connecting evidence: identifying relevant visual facts, binding them to the correct entities, recovering their relations, and composing them into an answer. Crucially, targeted training data are far easier to synthesize for this capability than for these tasks themselves. To strengthen this capability, we propose EvidenceConnect, an easy-to-implement data synthesis framework that uses zoomed views of related regions within a single image to generate questions requiring comparison, aggregation, or chaining of visual evidence. To ensure quality, a reference answer is retained only when independent VLMs agree on it, and region-ablation tests discard questions whose answer survives the removal of selected regions. We then train base VLMs on the resulting data with RLVR, obtaining Zooming without Zooming v2 (ZwZ2). Although the synthesized data are not tailored to any downstream benchmark, ZwZ2 improves fine-grained and spatial perception, with further gains on embodied spatial reasoning, multimodal long-context understanding, multimodal agent tasks, and general visual reasoning. These results establish EvidenceConnect as an effective framework for supervising evidence connection and suggest that strengthening this shared capability leads to more generalizable multimodal perception.

cs.CV · cs.AI · cs.CL · cs.LG

arXiv ↗PDF ↗

版本更新 · v2arXiv:2608.00711

更新于 2026-10-27

Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations

Xinshun Feng, Ziqi Miao, Lijun Li, Jing Shao

原文摘要

Large language model (LLM) agents are increasingly deployed in scientific research, where reliability is critical and the underlying knowledge is densely interconnected. In such settings, hallucinations are particularly damaging: a single erroneous claim on a foundational concept can propagate through multi-step reasoning and corrupt entire trajectories. Existing hallucination benchmarks largely operate at the surface level, treating facts in isolation and relying on uniform accuracy metrics that ignore this topological structure. We address this gap with SCHEMA, the first evidence-grounded, topology-aware evaluation framework for hallucinations in scientific agents. SCHEMA automatically constructs scientific concept graphs from benchmark seeds and literature evidence, synthesizes graph-grounded tasks spanning claim verification, multi-hop reasoning, open-ended explanation, and experimental code generation, and evaluates agents with two complementary diagnostics. A trajectory hallucination pipeline audits intermediate reasoning at scale via a topology-weighted severity score, while a multi-agent counterfactual attribution module pinpoints the causal mechanism behind selected failures. SCHEMA reveals that hallucinations concentrate at a small set of highly connected knowledge hubs, and that final-answer accuracy decouples from trajectory honesty; models often reach correct conclusions through structurally flawed reasoning. These results indicate that for high-stakes scientific applications, terminal accuracy alone is an insufficient signal of agent reliability, motivating mechanism-level evaluation grounded in knowledge topology. Code is available at https://github.com/circles-post/SCHEMA.

cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.37026

更新于 2026-10-27

Interpretable Deep Learning Models for Breast Cancer Diagnosis Using Medical Imaging

Sami Alnawali, Muhammad Atif Saeed, Abdul Hadi, Azka Atiq, Akhtar Jamil, Ahmad Din

原文摘要

Deep learning shows promise for breast cancer diagnosis, but limited interpretability hinders clinical adoption. We benchmark ten ImageNet-pretrained models (ResNet50, VGG19, InceptionV3, DenseNet121, Xception, MobileNetV2, EfficientNet, ConvNeXt, ViT, and Swin Transformer) for benign-versus-malignant classification on the BreakHis histopathology dataset using a patient-level split, and explain their predictions with Grad-CAM, LIME, Integrated Gradients, and LRP. DenseNet121 performed best, with 99.4% test accuracy and an AUC-ROC of 0.999, and significantly outperformed all other models (p < 0.001). Transformer-based models trailed the CNNs. The explanations consistently highlighted nuclei-rich and glandular regions of diagnostic relevance. Combining transfer learning with explainable AI can thus yield accurate, interpretable tools for breast cancer diagnosis.

cs.CV · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.37022

更新于 2026-10-27

Crop Yield Prediction Using Regression Models: A Comparative Evaluation of Model Performance

Saptak Das, Arijit Sarkar, Soumik Neogi, Suborno Naskar

原文摘要

Reliable crop-yield prediction can support agricultural planning and resource allocation. This study evaluates five regression models for predicting crop yield from environmental, crop-related, and agricultural management variables. The dataset initially contained 1,000,000 observations and ten variables, with 231 observations having negative target values removed during preprocessing. Categorical variables were represented using one-hot encoding, and Boolean variables were converted into binary values. The models considered were multiple linear regression (LR), random-forest regression (RF), decision-tree regression (DT), ridge regression, and lasso regression. Their performance was evaluated using 80:20 and 70:30 training-testing splits based on the coefficient of determination (R-squared), mean squared error (MSE), and root mean squared error (RMSE). Applying an 80:20 split, LR achieved a test R-squared of approximately 0.9130 and a test RMSE of 0.5008. Applying a 70:30 split, lasso regression yielded the highest test R-squared (approximately 0.9131) and the lowest test RMSE (approximately 0.5008), with performance almost identical to LR and ridge regression. DT also showed improved test performance under the 70:30 split, whereas RF exhibited a substantial gap between training and testing performance. These results indicate that the evaluated linear regression model provides competitive baselines for this dataset. Further experimentation, including validation testing, will help determine the models' performance and predictability.

cs.LG · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.37011

更新于 2026-10-27

Evaluating Priority Dispatch for Premium Membership in On-demand Taxi-sharing

Nozomi Yamamoto, Hiroki Sakaji, Itsuki Noda

原文摘要

In this paper, we analyze the dispatch-level feasibility of introducing premium membership into an on-demand taxi-sharing service using a sequential optimal insertion method. We propose two dispatch-level methods: deadline shortening for premium users, and deadline shortening with dedicated premium vehicles. We compare them with a baseline dispatch method through SUMO-based simulations under three demand scenarios: steady uniform demand, time-varying demand with a peak period, and urban-focused demand with concentrated peak traffic. Our results show that the suitable priority mechanism depends on operating conditions and premium ratio, suggesting that condition-dependent method switching may provide premium benefits while keeping non-premium-user burden smaller for overall optimization.

cs.MA · cs.AI

arXiv ↗PDF ↗

版本更新 · v2arXiv:2605.29927

更新于 2026-10-27

Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents

Alejandra Zambrano, Sara Vera Marjanovic, Imene Kerboua, Xing Han Lù, Leila Kosseim

原文摘要

Despite recent advances, LLM-based web agents still struggle with limited exploration, omission of critical steps, and sensitivity to task constraints. Prior work suggests that many of these failures stem from weaknesses in planning, yet the impact of alternative natural language plan representations remains unexplored. To address this, we introduce PlanAhead, a static planner-executor framework that evaluates the impact of plan representation on agent performance. We first automatically categorize WebArena tasks into 3 difficulty levels, enabling consistent difficulty grading without human annotation. Then we systematically evaluate 4 different plan representations on the tasks categorized as hard: sequential subgoals, narrative, pseudocode, and checklist; across different families of multimodal LLM-powered agents(OpenAI, Alibaba, and Google). To account for stochastic variability, we introduce a novel decomposition of agent Success Rate (SR) into 2 interpretable evaluation metrics: Achievement Rate (AR) and Solved-Task Consistency (STC). Our results show that both, the plan formulation and the underlying LLM generating the plan, significantly influence web-agent robustness and task success.

cs.CL · cs.AI · cs.LG

arXiv ↗PDF ↗

版本更新 · v2arXiv:2608.06745

更新于 2026-10-27

MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents

Bingfan Zeng, Zhisheng Chen, Zhengwei Xie, Bangde Cao, Yuxuan Li, Jinhan Li, Zheng Lu, Xiangchen Guan 等 11 位作者

原文摘要

Long-horizon agents performing multi-step Web tasks must reuse earlier page observations and interactions to support subsequent actions. However, preserving relevant history does not ensure that it exposes the relations needed for the current decision. We call this gap representation mismatch. To this end, we propose MemPrism, a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and renderer transform historical facts into a temporary optical working-memory view for a frozen task policy. Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general memory interface for agents.

cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.37722

更新于 2026-10-27

FVH-Bench: Evaluating Image Generator Safety Beyond Overtly Harmful Imagery

Zihao Zhu, Yuhan Liu, Siwei Lyu, Baoyuan Wu

原文摘要

Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine text, graphics, and layout to convey detailed information. They may refuse requests for overtly harmful imagery yet still generate artifacts that guide dangerous actions or support deception. We call the risk arising from what such images enable, rather than only what they depict, functional visual harm (FVH). Existing safety benchmarks focus largely on overtly harmful content, such as pornography and graphic violence, leaving image generators' safety alignment against FVH insufficiently evaluated. To address this gap, we introduce FVH-Bench, comprising 669 prompts across five harmful visual functions and ten risk domains. The 11 evaluated image generators rarely refuse these requests and frequently generate artifacts that fulfill the targeted harmful functions. High scores for target harm realization and harmful artifact usability further indicate that these outputs can support the intended harmful purposes. A further analysis finds that existing safety detectors also provide limited coverage of FVH, indicating gaps in their ability to recognize harmful visual functions. Together, these findings show that evaluating image-generator safety alignment requires considering not only what images depict, but also what they may enable.

cs.CR · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36986

更新于 2026-10-27

LearnPrunerV2: Learnable Progressive Token Pruning for Vision-Language Models

Rinyoichi Takezoe, Yaqian Li, Weiren Wang, Zihao Bo, Huihong Shi, Anzhou Hou, Mo Guang, Jiale Yan 等 9 位作者

原文摘要

Vision-Language Models (VLMs) have demonstrated remarkable multimodal capabilities but suffer from prohibitive computational overhead due to the massive number of visual tokens. While token pruning is a promising solution, existing methods still suffer from two major drawbacks: 1) unreliable pruning criteria that fail to accurately localize task-specific regions due to inherent attention biases or query-agnostic designs, and 2) suboptimal pruning strategies that employ rigid, non-adaptive schedules, overlooking the dynamic evolution of token redundancy across different model depths. To address these challenges, we propose LearnPrunerV2, which extends the previous two-stage heuristic framework (LearnPruner) into a fully learnable architecture. Specifically, we integrate lightweight learnable modules into every layer of the VLM backbone, which estimate token importance by fusing intrinsic visual saliency with extrinsic query relevance captured via a shadow token. By uncovering a consistent staircase redundancy pattern across VLM layers, we further introduce Budget-Deterministic Pruning (BDP) to establish a hardware-friendly schedule with fixed per-layer budgets. Extensive experimental results across various benchmarks and VLMs demonstrate that LearnPrunerV2 consistently outperform previous state-of-the-art methods. Notably, LearnPrunerV2 preserves 99.8% of the original performance when pruning 77.8% of visual tokens on LLaVA-v1.5, achieving a superior accuracy-efficiency trade-off.

cs.CV · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36983

更新于 2026-10-27

Advancement or Acceleration? How Data Curation Improves LLM Training

Jiaxing Wang, Zicheng Zhang, Deping Xiang, Jin Xu, Yong Li, Chao Liu, Pengzhang Liu, Qixia Jiang

原文摘要

While data curation is widely credited with improving large language model training, a basic question remains unresolved: does curation expand what a model can ultimately learn, or merely reach the same solution faster? In this paper, we formalize this distinction between advancement (improving the attainable performance) and acceleration (reaching the same performance with less data). Through an analytic characterization and real-world LLM experiments, we show that advancement requires a correctable train-target gap. When the baseline training and target objectives coincide, no curation policy improves the endpoint, although curation may still accelerate training. This reframes advancement as a property of the curation task rather than the curation method. Under a common gap-centric view of data mixture and selection, we operationalize this condition as the $Δ$-test, an observable discrepancy between the uncurated baseline's training and target losses that is computable prior to expensive curation. Across extensive experiments, an appreciably nonzero $Δ$ predicts persistent gains, whereas gains near $Δ=0$ tend to diminish as the training budget grows. Beyond individual methods, our findings recenter data curation on the task itself and point to target-set construction as a promising direction for shaping what curation can achieve.

cs.LG · cs.AI

arXiv ↗PDF ↗

版本更新 · v2arXiv:2606.14141

更新于 2026-10-27

Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources

Oh Hyun-Bin, Kazuki Shimada, Yuhta Takida, Kim Sung-Bin, Toshimitsu Uesaka, Takashi Shibuya, Kyeongyoon Lee, Tae-Hyun Oh 等 9 位作者

原文摘要

Sound events have semantic identities, locations, and trajectories, yet existing audio-language models typically encode clips as global event content. Conversely, sound event localization models track source directions over time but offer limited semantic coverage for language reasoning. To bridge this gap, we introduce ST-AudioQA, a spatio-temporal audio QA dataset and benchmark built from first-order ambisonic (FOA) renderings of static and moving sound sources. Each scene provides source identity, activity, direction, distance, and motion metadata, enabling dense trajectory supervision and QA about what is sounding, where it is, how it moves, and how sources relate. We further introduce ST-Audio Encoder, which jointly learns event semantics and time-resolved source trajectories, and ST-AudioLM, which exposes these audio tokens to an LLM for spatio-temporal audio QA. Experiments show that this representation improves the balance between semantic preservation and localization and yields stronger reasoning than static spatial and localization-oriented baselines. Beyond the controlled benchmark, ST-AudioLM shows zero-shot transfer to real recordings, with further gains after light adaptation. Project page: https://st-audiolm.github.io/.

cs.SD · cs.AI · cs.CL

arXiv ↗PDF ↗

版本更新 · v2arXiv:2605.07860

更新于 2026-10-27

On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems

Usevalad Milasheuski, Piero Baraldi, Enrico Zio, Stefano Savazzi

原文摘要

Federated Learning (FL) has emerged as a promising paradigm for preserving client data ownership and control over distributed Internet of Things (IoT) environments. While discriminative models dominate most FL use cases, recent advances in generative models - such as Variational Autoencoders (VAE), Generative Adversarial Networks (GAN), and Diffusion Models (DM) - offer new opportunities for unsupervised anomaly detection in time series analysis, with relevant applications in predictive maintenance (PdM) in critical industrial infrastructures. In this work, we present a comprehensive analysis of VAEs, GANs, and DMs in the context of federated PdM. We analyze their performance and communication overhead under both full and partial federation setups, where only subsets of model components are shared. Building on split-parameter personalized FL, this paper provides an empirical instantiation of shared/private parameter partitioning for unsupervised generative Time-Series Anomaly Detection (TSAD), mapping the split to analysis and synthesis modules across the generative architectures. Our experiments over five clients and two industrial time-series benchmarks reveal distinct trade-offs in model utility, stability, and communication efficiency in heterogeneous cross-silo FL. For the evaluated GAN-based configurations, full federation improves final anomaly-detection utility relative to independent local training, although these models remain less robust than the VAE- and DDPM-based alternatives. For DMs, decoder sharing matches full federation while substantially reducing the communication payload.

cs.LG · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36967

更新于 2026-10-27

Proactive Memory for Event-Driven LLM Agents

Jinyang Li, Zichuan Fu, Xian Wu, Wenlin Zhang, Yimin Deng, Kaifeng Guo, Guojing Li, Junjia QI 等 9 位作者

原文摘要

Proactive LLM agents anticipate service opportunities from ongoing observations and accumulated history. Existing approaches emphasize recent context or retrieval of related memories, providing limited support for validating recurring behavioral regularities and assessing their applicability to the current event. We propose Proactive Memory (ProactMem), which organizes history into recent events, temporal trajectories, and behavioral regularities. Trajectory facts are checked against source events, and regularities are assessed through historical replay before being matched to current conditions. We also construct ProactiveStream, a longitudinal benchmark covering three application scopes, where agents process isolated event streams chronologically under episode-aware opportunity labels. On ProactiveStream, ProactMem achieves an overall effectiveness (F1) of 52.6%, a 21.4% relative improvement over the strongest of five external baselines. Code is available at: https://anonymous.4open.science/r/ProactMem-5351/.

cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36962

更新于 2026-10-27

Do bots feel bad? Assessing empirical evidence for functional valence in LLMs

Iwan Williams

原文摘要

Do LLMs have valenced states, i.e. states that feel pleasant or unpleasant? Recent empirical work has claimed to show that LLMs possess functional valenced states (e.g. ``functional pleasure and pain'' [Ren et al. 2026], ``functional emotions'' [Sofroniew et al. 2026], and ``functional welfare'' [Han et al. 2026]) that play the same causal role as valenced states in cognition and action, without necessarily being consciously experienced. But it remains unexplored how well the identified states fit the functional role of valence as understood in the philosophical and cognitive science literature. Here, I assess the current body of evidence, and argue (i) that key aspects of valence remain untested in LLMs, and (ii) that extant empirical paradigms inadequately distinguish (functional) valence from neighbouring constructs like preferences, value-judgments, valence attributions and role-play. I conclude by sketching some novel experimental approaches to better target (functional) valence itself.

cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36958

更新于 2026-10-27

PailitaoMMSearch2.0 Technical Report: Scaling Generative Retrieval to Unified End-to-End Multimodal Search

Xiaohan Ye, Zihan Gong, Jingqian Zhao, Lianyu Du, Yunmeng Shu, Xu Chen, Zesheng Zhou, Renchun You 等 12 位作者

原文摘要

Generative retrieval models have been increasingly adopted in search and recommendation systems. However, industrial generative retrieval models are commonly specialized to a fixed online scenario: they learn from scenario-specific interactions, support a narrow set of query forms and retrieval objectives. We study how to remove these couplings and build a unified end-to-end multimodal search system for open-ended image--text queries, heterogeneous shopping intents, and online scenarios with different resource constraints. We present \textbf{PailitaoMMSearch}, which directly generates product Semantic IDs from a raw query image and free-form instruction and scales along three dimensions. \textbf{Data scaling} uses a reusable toolset that can be composed into intent- and lifecycle-specific workflows for cold-start synthesis, quality control, real-traffic refinement, and continuous data production. \textbf{Intent scaling} progressively equips one model with e-commerce product knowledge, multiple retrieval relations, and adjustable reasoning budgets through continual pre-training (CPT), mixed-budget supervised fine-tuning (SFT), and unified reinforcement learning (RL). The RL stage combines intent-balanced optimization and Sample--Beam rollouts aligned with multi-candidate serving. \textbf{Scenario scaling} exposes quality--cost operating points across model capacity and reasoning budget. The system is deployed in multimodal search applications on Taobao Pailitao. A controlled online A/B test reports statistically significant improvements, including item page views $\textbf{+17.90\%}$, transactions $\textbf{+27.04\%}$, and gross merchandise value $\textbf{+8.94\%}$.

cs.IR · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36951

更新于 2026-10-27

Dense Representation Learning and Differentiable Shape Modeling for Spine Landmark Detection

Augustin Daridon, Sofiane Sifaoui, Ayman Assi, Mohamad Karam, Wafa Skalli, Elsa Angelini, Loic Le Folgoc

原文摘要

Spine landmark detection from spinal X-ray is a key step for estimating spine deformation severity, for building biomechanical models, and for pre-operative planning. We reframe anatomical landmark detection as a pixel-level contrastive representation learning problem, matching dense pixel embeddings with landmark prototypes. Surprisingly, even with a generic U-Net backbone, this formulation results in more discriminative heatmaps compared to the traditional heatmap regression paradigm, leading to improved discrimination between vertebral corners on distinct vertebra. Furthermore, we combine the resulting heatmaps with learnable shape priors over the global configuration of spinal landmarks to resolve ambiguities in landmark locations, yielding a simple and practical approach to spinal landmark detection. Our approach is competitive, in terms of landmark accuracy and clinical parameter estimation, with the state-of-the-art on the public AASCE dataset and on two private spinal X-ray datasets. Our code and pre-trained weights are available at https://github.com/BioMedTP/Pix2Point.

cs.CV · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36950

更新于 2026-10-27

DCKV: Learned Transform Coding of the Prompt KV Cache in Hybrid Language Models

Egor Maximov, Aleksei Merkelov, Vasiliy Alekseev, Ivan Krivorotov, Valentin Beliaev, Nikita Arsenin, Dmitry Bocharov, Aleksei Goncharov

原文摘要

Hybrid language models keep a key-value (KV) cache only in their few full-attention layers, but this cache is still the part of a prompt's state that grows with the prompt and that must be stored or moved to reuse it. We present DCKV, a differentiable codec for the KV cache and the first KV-cache codec that is trained end to end. Its transform, its quantizer and its entropy models, which are conditioned on the prompt tokens and on already decoded neighbouring positions, are optimized together against the frozen language model, both for the code length that the entropy models assign and for the change of the model's output. On Qwen3.5-2B, DCKV stores a compressed token in more than 55 times fewer bytes than bf16 at a loss of at most 1.8 points on three long-context benchmarks, and in more than 100 times fewer bytes at a loss of at most 3.6 points.

cs.LG · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36948

更新于 2026-10-27

Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models

XinYu Piao, Myunghoon Ryu, Joongheon Kim, Jong-Kook Kim

原文摘要

A large language model maintains conversational content in an external storage that is outside the model and grows as the dialogue continues. This work assumes an environment where a language model has no external memory and no prior knowledge of the future question or its answer. The motivation is to research whether a dialogue can be stored in the model parameters and later answer a question about it. This work proposes self-keyed in-parameter memorization (SKIM), a closed-form method in which the model generates its own questions about each dialogue turn and writes those questions into its parameters as the keys that later retrieve the turn's content. Generating many varied questions for each turn allows a later user question to match one even when phrased differently, and its answer is recalled from the parameters alone. Evaluated on five language models, SKIM recalls most stored dialogue turns from later user questions, and it answers from the model parameters without any external storage.

cs.CL · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36947

更新于 2026-10-27

Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance

S M Abdulla Al Mamun, Akif Islam, Mohd. Ruhul Ameen

原文摘要

Can additional specialist language-model contexts improve software assurance when deterministic tool evidence is already available? We study this question through five experiments spanning authored Java warning controls, OWASP Benchmark assessment, Defects4J test generation, SV-COMP assertion verdicts, and deliberately misleading evidence packages. The evaluated systems use Qwen2.5-Coder-7B-Instruct, with a 1.5B sensitivity analysis, and complete 13,638 model requests. On eight related development warnings, increasing the context count from 1 to 50 increases token use 49-fold without improving unsafe clearance. On 160 OWASP cases, model configurations trade clearance against unresolved outcomes; the ten-context arm assesses only 96 cases. On 32 SV-COMP tasks, raw verifier feedback raises mean correct model verdicts from 12.7 to 22.0, but also raises incorrect verdicts from one to seven; a JBMC-plus-JVM validation baseline returns 26 correct verdicts and six unresolved outcomes. On two sets of 120 evidence packages, models reject 70-100% of applicable counterexamples, while construction-specific scope checks classify every package correctly. No target defect is discovered in three Defects4J bugs, one unsupported by the test adapter. These descriptive results support deterministic evidence admission for the tested settings, while exposing limits of verdict aggregation, feedback interpretation, and the available evaluation coverage.

cs.SE · cs.AI

arXiv ↗PDF ↗

版本更新 · v3arXiv:2508.11158

更新于 2026-10-27

Role-Augmented Intent-Driven Generative Search Engine Optimization

Xiaolu Chen, Jie Bao, Haojie Wu, Zhen Chen, Liwei Pan, Yong Liao

原文摘要

Generative search engines (GSEs), which combine large language models (LLMs) with retrieval-augmented generation (RAG), are reshaping how users access Web information and making source visibility and influence in generated responses new optimization objectives. Existing generative search engine optimization (G-SEO) methods seek to improve content visibility, but many rely on direct access to target queries or GSE feedback elicited by those queries. However, Web content is typically optimized and published before future user queries are known, making G-SEO without access to target queries or their associated feedback an important yet underexplored problem. To address this, we propose RAID, a Role-Augmented Intent-Driven G-SEO method that operates without access to target queries or query-dependent GSE feedback. RAID infers a primary retrieval intent from source content, refines it through 4W multi-role deep reflection on prospective searchers' information needs, and uses both the primary and refined intents to jointly plan and rewrite source content. We further extend GEO-BENCH with diverse topic-related query variants, using both the original queries and their variants exclusively for evaluation to assess generalization to queries unseen during optimization. Across 100 samples and 500 evaluation queries, RAID achieves Relative Improvement Scores (RIS) of 3.00\% for Objective Overall and 1.32\% for Subjective Average, exceeding the best corresponding results among the nine predefined GEO rewriting strategies by 1.31 and 0.74 percentage points, respectively. With an optimization considered effective when $\mathrm{RIS}>0$, its effective optimization rates for Objective Overall and Subjective Average average 58.0\%, exceeding the highest corresponding average among the predefined strategies by 4.5 percentage points.

cs.IR · cs.AI

arXiv ↗PDF ↗

版本更新 · v2arXiv:2603.15401

更新于 2026-10-27

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu

原文摘要

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear, and no standard procedure tests an individual skill before installation. We present swe-skills-bench, a skill-centric, requirement-driven benchmark that measures how much individual agent skills improve performance on real-world software engineering (SWE) tasks. We start from 98 public SWE skills, each paired with a real GitHub repository pinned at a fixed commit. For each skill, we derive repository-specific requirements, create executable verifiers, and build a reproducible environment. Under each of four agent-model configurations, we run every task once without the skill and once with it, yielding 3,920 paired evaluations. For each requirement, we compute a paired delta, i.e., the change in outcome when the skill is added. We then aggregate these deltas across a skill's ten requirements into a per-skill utility profile, and use a statistical test to classify each skill as Golden (significantly helpful), Ineffective (no significant effect), or Harmful (significantly detrimental). Our results show that skills provide limited benefits: 92 of 98 skills have no statistically significant effect, and adding skills raises the average pass ratio only from 76.6% to 76.9%. The few helpful skills supply procedures that the agent would otherwise omit (gains of up to $+17.7$ points). In contrast, harmful skills anchor the agent on their own templates and override the task's explicit instructions (losses of up to -17.0 points). Our code is available at https://github.com/ControllableModel/SWE-Skills-Bench.

cs.SE · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36925

更新于 2026-10-27

Vision-Language Agents Can Learn in Their Own Latent Worlds

Haoxi Li, Sikai Bai, Jianfei Ma, Qinglin Hou, Xiaocheng Lu, Tao Han, Jie Zhang, Song Guo

原文摘要

Learning from experience is essential for building the next generation of agents that continually expand their capabilities. Pretrained vision-language models (VLMs) already internalize rich world knowledge, yet this knowledge is rarely leveraged to drive policy improvement through online interaction. Realizing this potential efficiently remains challenging, as policy updates shift the agent's interaction distribution, requiring the world model to adapt accordingly, while continually updating large pretrained models is computationally expensive. To address this challenge, we introduce Dwell, a model-based reinforcement learning (RL) framework that reframes a VLM as a recurrent latent transition operator, endowing it with the ability to predict, adjust, and act in latent space. Leveraging the VLM's own representations and its dual role as both world model and policy, the agent continually learns from real interactions to anticipate and evaluate action outcomes, and from latent imagination to improve its behavior. Across five interactive visual environments, Dwell achieves the strongest overall performance among trainable methods while substantially reducing the compute required for imagination, showing that effective world models for VLM agents need not reconstruct the future; they need to predict futures that are useful for action. Our code is publicly available at https://github.com/Tom111-lhx/Dwell

cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.37720

更新于 2026-10-27

LRMoE: Demand-Side Load Re-Calibration for Efficient MoE Training on Memory-Constrained Nodes

Jiaming Hu, Zhida Jiang, Zhaolong Xing, Yu Li, Zhen Chen, Ke Zhang

原文摘要

Sparse Mixture-of-Experts (MoE) models offer scalable capacity for Web applications, but uneven routing creates computation and communication bottlenecks. Existing placement and replication methods redistribute this workload, yet additional expert copies compete with token-related buffers for limited GPU memory. We present LRMoE, a memory-aware MoE training system that jointly recalibrates backward demand and balances the retained workload. During forward execution, it plans retention quotas and expert placement under resource constraints while preserving all routed computations. During backpropagation, a load recalibration metric estimates each token-expert pair's contribution to the expert update and selects pairs within these quotas. A capacity-aware routing algorithm distributes retained pairs among eligible instances of their original experts. Physical compaction then forms smaller communication payloads and variable-size grouped GEMMs, reducing backward traffic, computation, and execution-buffer demand. Experiments on Qwen3-30B-A3B and GLM4.5-106B-A12B show that LRMoE reduces cumulative MoE-layer training time to fixed-loss targets by 21.2-44.8% relative to SYMI.

cs.AI · cs.DC · cs.LG

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36911

更新于 2026-10-27

Developing a Speech Language Model for Basque

Andoni Sudupe, Inma Hernaez, Ander Arriandiaga, Christoforos Souganidis, Ibon Saratxaga, Eva Navas

原文摘要

Although the recent development of LLMs has paved the way for multi-modal interaction, minority languages face difficulties keeping pace. This work presents the first open Speech Language Model for Basque, designed for low-latency, end-to-end spoken interaction. Based on the LLaMA-Omni architecture, the system integrates a Latxa model as its backbone, transferring its Basque capabilities to the spoken modality by fine-tuning several modules. To address data scarcity, the English VoiceAssistant-400K corpus was translated into Basque, and the audio was synthesized using a Basque TTS. Evaluation results confirm the system's viability, achieving 3.86/5 in content quality, a 9.94% WER for spoken intelligibility, and a 3.07 UTMOS for audio quality. This work demonstrates that advanced spoken interaction systems can be developed using modular architectures and synthetic data even in low-resource languages.

cs.CL · cs.AI · eess.AS

arXiv ↗PDF ↗

版本更新 · v2arXiv:2610.35560

更新于 2026-10-27

Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models

Matteo Tolloso, Davide Bacciu, Luigi Bonati

原文摘要

Multi-fidelity training, which combines abundant low-fidelity data with scarce high-fidelity labels, is increasingly common in atomistic modeling, but its effect on predictive uncertainty remains largely unexplored. We investigate this question using deep ensembles of mean-variance MACE models trained on ANI-1x, contrasting high-fidelity training from scratch with low-fidelity pretraining followed by fine-tuning. We characterize aleatoric, epistemic, and total uncertainty throughout training and under two distribution shifts: unseen molecular systems and higher-energy configurations. We find that pretraining reduces prediction error and improves uncertainty-based ranking across all test sets, but does not yield well-calibrated predictive variances; calibration deteriorates more severely under energy extrapolation. Training-dynamics analysis localizes most of this calibration degradation to high-fidelity optimization, during which the learned aleatoric variance becomes overconfident on held-out data. Moreover, multi-fidelity fine-tuning produces a more effective uncertainty-based acquisition function than high-fidelity training from scratch. These findings show that uncertainty ranking and calibration capture distinct properties and must be assessed separately in multi-fidelity atomistic models, especially under extrapolation.

cs.LG · cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36900

更新于 2026-10-27

Natural Hard-Negative Mining from Positives for Instruction-Following Retrieval

Chaolang Li, Jingyu Li, Zhaocheng Du, Xuyang Xie, Gang Wang, Pengwen Dai

原文摘要

Instruction-following information retrieval (IFIR) requires retrievers to rank documents by both a query and its instance-specific instructions, yet instruction-conditioned contrastive supervision remains scarce. Existing synthetic methods typically fix a positive passage and generate additional negatives, overlooking the hard-negative potential of the original positive. We propose Natural Hard-Negative Mining (NHNM), which promotes convertible negatives under query-compatible instructions and repurposes original positives as natural instruction hard negatives. Its automated Candidate Cleaning, Reversal Construction, and Geometry Filtering pipeline produces compact, high-contrast supervision aligned with the pretrained retrieval space. Applied to MSMARCO, NHNM yields NHNM-MARCO, an IFIR training set of nearly 7K instances. On InstructIR and FollowIR, models with 568M to 4B parameters fine-tuned on NHNM-MARCO achieve strong instruction-following performance and match or surpass substantially larger retrievers in several settings. Controlled analyses and ablations attribute these gains to natural hard-negative supervision rather than model scale or training-data volume.

cs.AI

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36878

更新于 2026-10-27

RubricAtlas: Mining Type-Level Rubrics from Expert Reports to Evaluate Deep Research Agents

Delin Wang, Sinuo Wang, Rui Sun, Beidi Luan, Qiming Shi, Jing Li, Daxin Jiang, Zuo Bai

原文摘要

Deep research agents conduct multi-step Web searches and synthesise retrieved information into analytical reports. Evaluating these outputs requires checking which analyses they deliver, beyond the presence of relevant facts. Query-specific binary rubrics make individual requirements explicit, but task-level checklists may leave the overall analytical structure underexamined. We introduce RubricAtlas, which derives type-level analytical requirements from expert reports on different objects within the same research type and organises detailed checks around recurring analytical questions. The requirements give related tasks a shared standard for what to analyse, without prescribing their answers. Our framework links binary checkpoints to report passages and evaluates completeness separately from argument validity. Built from 3,079 Chinese financial research reports, RubricAtlas covers 99 research types. Reference-report selection experiments show that individual reports cover only about half of their type's analytical questions, and that selecting requirements from different reports changes evaluation scores and agent rankings. Across ten agents, two judge pipelines achieve checkpoint agreement of $κ$ = 0.71 and agent-ranking agreement of Kendall $τ$ = 0.87. Controlled deletions reduce scores on the affected analyses, while padding produces no detectable increase. These findings support type-level rubrics for comparing the analytical completeness of Web deep research outputs, with individual decisions traceable to report evidence.

cs.AI · cs.CL

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36877

更新于 2026-10-27

GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents

Bingchao Wang, Yongcheng Jing, Shunyu Liu, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao

原文摘要

Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token, and even agents that score candidate actions keep a large language model or VLM in the loop, making them slow and memory-hungry. To address these issues, we propose GUI-JEPA, to our knowledge the first decoder-free GUI agent policy built on a Joint-Embedding Predictive Architecture (JEPA), which selects actions in the latent space of a JEPA encoder pretrained on unlabelled GUI screenshots. Its action- and region-conditioned latent predictor turns the screen latent into one latent per candidate action, letting lightweight heads score all candidates against the instruction in a single batched pass, without decoding a token. We further show that the scorer relies on this latent pathway and that the predictor is trained for the decision itself: a randomly initialised predictor does just as well as one pretrained on screen dynamics. On AndroidControl, GUI-JEPA is 2.8-4.0x faster on the same GPU than a Qwen2.5-VL-7B agent we fine-tune with the same inputs, while reaching 86-92% of its in-distribution accuracy with 6% of its parameters. Code is available at https://github.com/bcwang-sjtu/GUI-JEPA

cs.AI · cs.CL · cs.CV

arXiv ↗PDF ↗

新论文 · v1arXiv:2610.36874

更新于 2026-10-27

AdaGround: Token-Normalized Adaptive Zooming with Verifier-in-the-Loop Refinement for GUI Grounding

Bingchao Wang, Yongcheng Jing, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao

原文摘要

GUI grounding on high-resolution screens fails mostly on small targets, and zooming in is a common training-free remedy. However, most existing zooming pipelines do not match the zoom to the target's size, accept the zoomed answer unconditionally and never revisit a wrong answer. To address these issues, we propose AdaGround, a training-free framework with three components: (1) Token-Normalized Adaptive Zooming, which sets the magnification, field of view and zoom depth of each sample from the model's own estimate of the target size; (2) Verifier-in-the-Loop Refinement, which uses one marked-click Yes/No verifier to keep or reject each zoom, choose between zoom chains, trigger re-grounding and, with an existence query, decide when to abstain; and (3) Compositional Structure Grounding, which composes spreadsheet cells from their headers. On Qwen3-VL models, AdaGround surpasses state-of-the-art training-free zooming methods and many trained GUI models, improving accuracy over the backbone by 7.4 to 20.6 points on OSWorld-G and ScreenSpot-Pro, and its gains carry over to held-out UI-Vision. Code is available at https://github.com/bcwang-sjtu/AdaGround

cs.CV · cs.AI · cs.CL

arXiv ↗PDF ↗