跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+729新增论文
+575其中 AI 相关
+82已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 15:16 — 2026-11-21 15:16(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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 6,976 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.22515

Right Labels, Wrong Reasons: Signed Feature Attribution for Multi-Label Explainability

Kenton White

原文摘要

When a multi-label classifier assigns the right labels, it may do so for the wrong reasons. Diffuse feature combinations may vary across classifier families and lack a dominant feature. This paper proposes FLEX (Fisher LDA Explainer), a global surrogate that fits a single direct multi-label Fisher LDA over the full binary label matrix, producing signed feature attribution lists for each label in a single coherent coordinate system. Across the evaluated benchmarks and classifier families, FLEX reproduces the black box's predictions with consistently high fidelity. Pooling covariance across labels outperforms a per-label alternative on most datasets, with the advantage growing largest where labels are numerous and positive examples are scarce. FLEX's fidelity-complexity Pareto curve is monotonically increasing, giving practitioners a predictable path to higher-fidelity explanations as more features are used, and its in-sample fidelity matches or leads Binary Relevance alternatives once a modest feature budget is allowed. The magnitude of each discriminant weight vector bounds its label's separability, flagging labels that may be predicted correctly for the wrong reasons. The evaluated classifiers largely agree on which predictions to make, but reach those decisions through different feature subsets when no single feature dominates.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22511

LMLineage: Content Lineage and Context Governance for LLM Agents

Wei Hou, Jingxin Geng, Xin Chen, Zheqing Jiang

原文摘要

Interpretability for AI agents should not be confined to understanding the model's internal weights. It must also cover the agent's reasoning and decision-making process over multi-source context. We present LMLineage, an out-of-band system that attributes every output sentence of an agent session to its supporting input spans with calibrated confidences, without requiring white-box access to the model or any additional inference passes. On top of the lineage metadata, we build concept-drift micro compaction: instead of waiting for the context-length limit and summarizing everything, the system detects when previously used input documents have stopped being referenced ("drifted") and surgically compacts only those, preserving user instructions verbatim. We evaluate on a multi-tier corpus: 71 gold annotated sentences from 10 Chinese web-QA cases, plus 90 turns of independently collected multi-turn sessions across three generator models (gpt-4o-mini, qwen3.8-27b, deepseek-v4-flash). Results show that (i) window-level embedding similarity is far better aligned with LLM paraphrasing than whole document or lexical matching; (ii) the greedy-window fast path is both faster and more accurate on average than exhaustive line-matching (a multiple-comparisons bias in the latter inflates web recall at the cost of overall accuracy); (iii) per-turn attribution completes in 1s on a single GPU, remaining stable as context accumulates to 40 turns; and (iv) concept-drift detection is conservative (0% false compaction) with recall bounded by attribution accuracy. We further describe the concept-drift micro compaction design and an interactive incident-tracing/memory-cleaning case study. A companion patent application covers the lineage construction method.

cs.AI · cs.CL

版本更新 · v4arXiv:2507.20230

Building verifiable databases at scale from the chemical literature via a multi-agent system

Yufan Chen, Ching Ting Leung, Bowen Yu, Haifan Zhou, Jianwei Sun, Yong Huang, Linyan Li, Hao Chen 等 9 位作者

原文摘要

Accelerating chemical research with artificial intelligence requires high-quality databases. However, many reactions exist only as graphics drawn for human readers, which machines must read exactly. Specialist software is precise but rigid, whereas multimodal language models are flexible yet often write incorrect structures; neither flags errors. We present ChemEAGLE, a multi-agent system where tools supply structures and a language model extends their reach through judgments that programs apply. On 424 published graphics, its F1 score for exactly correct reactions was 82.2%, against 47.7% for a tool-equipped generalist agent, and calibrated confidence limited review to 35% of reactions at 96.6% accuracy. Without review, it built a 60,103-reaction photochemistry database whose records trained models to rank conditions and predict products. Verifiable databases can thus be built at scale.

cs.AI · cs.CV · cs.MA

版本更新 · v2arXiv:2609.23808

FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model

Jingxuan Xu, Gang Wu, Yanan Wu, Yutao Mou, Songwei Yu, Tianzhuang He, Zhengshuo Gong, Zhao Liu 等 17 位作者

原文摘要

While test-time scaling enhances Large Language Model (LLM) agents in long-horizon software engineering (SWE), sparse binary rewards (Pass/Fail) create a severe credit assignment crisis and waste failed exploratory trajectories. Current trajectory optimization and scaling methods are costly and structurally limited, relying on heuristic state reuse without causal diagnosis or delayed scalar scoring without actionable online guidance. We propose FLARE (Full-Lifecycle Alignment and Reward Engine), a novel dense supervision paradigm driven by a lightweight Generative Reward Model (GRM). First, RADAR, an offline causal-aware diagnostic framework, extracts high-fidelity, hindsight-free supervision through causal-chain backtracking to distill a GRM providing real-time, step-level risk feedback. Second, FLARE uses this GRM to continuously optimize the agent across its entire lifecycle. During inference, FLARE acts as an Active Scaffold, autonomously intercepting high-risk generation steps for localized breakpoint re-execution, drastically reducing compute overhead. During post-training, the GRM's structured signals serve as process-supervised reranking scores for Supervised Fine-Tuning (SFT) and step-level dense rewards for Reinforcement Learning (RL), mitigating policy collapse in sparse environments. Extensive evaluations show that FLARE establishes a new Pareto frontier across the agent lifecycle: FLARE (N=1) outperforms Global Rollout (N=5) with a 5x reduction in token consumption. Extending FLARE to training overcomes the sparse reward problem in long-horizon interactive tasks, delivering relative performance gains of 19.13% in SFT through process-aware data curation and a consistent 9.19% improvement in RL.

cs.CL · cs.AI

版本更新 · v2arXiv:2610.31276

RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding

Jingxuan Xu, Zihang Xu, Yuechen Luo, Ziqi Miao, Wenqiang Zhu, Weihao Li, Junhao Fan, Xinshun Feng 等 12 位作者

原文摘要

Long-horizon coding agents can observe a failure and generate a plausible critique yet continue along the same incorrect trajectory. We call this the Critique-to-Action Handoff Gap. We introduce RIPPLE, a recovery-oriented training framework that internalizes process-level guidance into a single self-recovering policy. A prefix-only teacher provides evidence-grounded recovery supervision without access to future actions or terminal outcomes. After lightweight distillation, reinforcement learning assigns stage-specific credit to reflection triggering, diagnosis, and corrective action. Local validity signals gate trajectory advantages so that intermediate recovery decisions do not indiscriminately inherit terminal outcomes. Across four repository-level software-engineering benchmarks, RIPPLE improves the base policy by an arithmetic mean of 4.8 score points, with no auxiliary critic at deployment. Controlled ablations isolate the benefits of local, stage-aligned credit, and matched-prefix interventions show that critique semantics affect subsequent correction. Recovery gains concentrate where the prefix contains sufficient diagnostic evidence and the repository state remains reversible within the remaining budget.

cs.AI

新论文 · v1arXiv:2611.22497

Towards Data-Efficient, Real-Time World Models

Raluca Stevenson, David Bignell, Jennifer C. White, Tabish Rashid, Emanuele Aiello, Mariya Hendriksen, Junha Hyung, Sadegh Aliakbarian 等 12 位作者

原文摘要

State-of-the-art world models have been used to produce sequences of gameplay that accord with provided user-input actions. However, high quality, consistent gameplay generation often comes at the cost of inference speed, making real-time interactive play and ideation challenging. The substantial quantities of data used to train state-of-the-art models have also made custom training of these models appear impractical, limiting many of their potential uses in creative fields. In this work we demonstrate a major step towards efficient world models: achieving both fast high-quality inference, and improved data efficiency. This is done by replacing the next-token prediction paradigm with a two-stage discrete diffusion-based approach, introducing a lightweight refinement transformer which carries out iterative masked predictions. Building on an autoregressive world model capable of generating highly consistent and complex sequences over minutes (Kanervisto et al., 2025), we achieve substantial model speed-up (79x) with a modest quality trade-off. Additionally, we demonstrate that this model can be trained to reproduce high-quality, consistent gameplay using a dataset containing approximately one day (28 hours) of gameplay data. Our results demonstrate progress towards removing barriers to the use of world models in settings where real-time inference and data efficiency are essential.

cs.AI

新论文 · v1arXiv:2611.22496

DARWIN: a Geospatial Foundation Model for Marine Intelligence

Coen van den Elsen, Laurens Geffert

原文摘要

We present DARWIN, a geospatial foundation model for marine intelligence. Recent Earth-observation foundation models have concentrated on terrestrial domains. The marine realm poses distinct challenges: missingness, multi-modal physical and biogeochemical variables, sparse labels, and dynamics that are transient, multi-scale, and non stationary over time. DARWIN adapts a masked-autoencoder backbone to these properties through missingness-aware encoding, expanded spatial and temporal masking, and Fourier-style positional embeddings, and is pretrained on 26 years of global Copernicus reanalysis together with GEBCO bathymetry. On predicting chlorophyll-a, the pretrained backbone attains the lowest monthly relative error in every month of 2022, outperforming both no-encoder baselines and an identically architected random-init encoder. At 10% of the supervised training data, DARWIN already surpasses the random-init model trained on 100% of the data. Embedding analysis and qualitative reconstructions show that DARWIN captures coherent oceanographic structure rather than memorising input statistics, providing a scalable backbone for downstream marine applications such as anomaly detection, species distribution modelling, and environmental monitoring.

cs.AI · physics.ao-ph

新论文 · v1arXiv:2611.22495

Motion-Aware Reward Modeling for Instruction-Guided Video Editing

Li Li, Xiangbo Gao, Bo Ni, Samyadeep Basu, Viet Dac Lai, Jing Shi, Seunghyun Yoon, Gang Wu 等 14 位作者

原文摘要

Reward models for instruction-guided video editing can favor temporal consistency at the expense of motion. We study this failure, termed \emph{motion collapse}, using controlled motion-suppression variants of real edits. On VE-Bench, the evaluated composite reward prefers a motion-suppressed candidate in $97\%$ of cases. Learned video rewards and a VLM judge also struggle with mild suppression, while latent optimization and reward-guided fine-tuning exploit this weakness to increase reward as motion declines. A linear probe of our base reward backbone performs near chance on mild suppression, motivating an explicit inter-frame dynamics input. We propose a motion-aware reward model that combines an RGB frame-difference stream with preference training against motion-suppressed and fabricated-motion negatives. A distillation anchor preserves alignment with human quality judgments. On the VE-Bench motion ladder, our model reduces the rate of selecting motion-suppressed candidates to $0\%$ while achieving a Spearman correlation of $0.57$ with human quality ratings. It also detects unseen suppression variants and preserves motion during reward-guided fine-tuning on two editing pipelines. These results support explicitly modeling motion in rewards for video editing.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.19292

Zero-Shot Weight-Space Programming for Prediction and Classification of Target Variables in Structured Datasets

Eduardo C. Garrido-Merchán

原文摘要

Weight-space programming fixes every parameter of a feed-forward network by hand, with no gradient descent anywhere in the construction. Every demonstration so far starts from a target function handed to the model as a rule system, making it a compilation problem. A supervised dataset withholds that specification, so the procedure must do the statistical inference itself and then express the result in the parameterisation it was given. We ask whether a large language model can do both. It is shown a small dataset in full, with the architecture of a feed-forward network, and writes out every weight and bias as a literal number, with no optimizer, no gradient, no code execution, and no chance to evaluate it first. Each construction is sealed and pre-registers its expected score. The graded suite runs from two toy problems, through nine synthetic problems disguised by a hidden rotation, to the classical benchmarks and one real engineering regression. The frozen network matches the closed-form optimum wherever that optimum is linear, reaches the irreducible error of the generating process on three rungs where it is not, and beats every fitted baseline on two of those, including the same architecture trained by gradient descent. It fails on two rungs, both times because the structure to be found is oblique to the coordinates it analysed. Three further constructors separate two failure modes a single score conflates: one returns no parameter vector at all on the hardest rungs, another delivers everywhere while writing networks worse than predicting the mean. One of those failures proves avoidable: another constructor solves the oblique-hinge rung by a margin that survives multiple-comparison correction. What predicts whether the hidden layer earns its keep is the training error of a linear separator, which the composite complexity index misses.

cs.AI

版本更新 · v3arXiv:2611.09271

Zero-Shot Weight-Space Programming Across a Difficulty-Graded Ladder of Two-Player Games

Eduardo C. Garrido-Merchán

原文摘要

Weight-space programming sets every weight of a feed-forward network by hand, from an explicit specification of the desired computation, with no gradient descent and no training data anywhere in the construction. We ask how far a large language model can carry this practice, zero-shot, across games of deliberately increasing difficulty. We design a four-rung ladder (Nim, tic-tac-toe, two sizes of Connect Four, and a chess endgame) spanning four axes of difficulty, and build a second, independent network at each rung, using a structurally unrelated game at matched difficulty, to separate what a rung's finding says about the difficulty level from what it says about the one game used to measure it. Ten networks are built and independently verified. Six admit a complete, non-statistical proof of correctness against an independent oracle. The chess-endgame rung is exact where correctness is cheap, move legality and, in one network, an exact one-ply mate detector, and collapses where it is expensive, composing a multi-move mating plan, from 84.1-100% success at the one-ply tactics it was built to get right down to 0.57-9.13% in full adversarial play; its replicate shows this collapse is an order of magnitude less severe under a shorter required plan and exact rather than heuristic safety checks. The standard-sized rung confirms, by holding hand-set evaluation weights fixed and adding only shallow search, that the remaining gap is an architectural ceiling rather than a matter of engineering effort, and this exact collapse reproduces across two structurally unrelated games. We release all ten networks, their independent oracles, construction-cost measurements, and a cold-prompt protocol for a future cross-model comparison

cs.AI

新论文 · v1arXiv:2611.22490

SciWorkBench: A Benchmark for Real Scientific Workflows

Yuchen Zhang, Taolin Han, Jinghang Wang, Jinxin Wang, Yun Wu, Wai Yuet Chiu, Xiaogang Li, Yuting Fu 等 22 位作者

原文摘要

Language models are increasingly being used as agents capable of planning and executing projects, as well as refining their actions through feedback. This shift raises a question: can current agents complete projects like real scientists? To examine this question, we introduce SciWorkBench, a benchmark for evaluating agents' abilities on real science tasks across biology, chemistry, materials science, and physics. SciWorkBench is built from peer-reviewed literature or expert-contributed research scenarios. We also propose a unified scientific analysis framework validated by domain experts, which can categorize most tasks in SciWorkBench. Each task covers one or more stages of this framework. We evaluate up-to-date models within the Claude Code and Codex agent frameworks under a unified execution and grading protocol. The best-performing agent achieves a mean score of 57.38, indicating that current agents still struggle with realistic scientific workflows. Our failure analysis identifies three recurring weaknesses at the workflow level: difficulty translating scientific knowledge into task-specific procedures, weak integration of evidence across different modalities, and limited capacity for scientific self-correction. These findings highlight the importance of workflow-based evaluation for measuring progress toward reliable AI systems for scientific research.

cs.AI

新论文 · v1arXiv:2611.22483

Manufacturing Differential Sparsity: Planner-Hardware Co-Design for Efficient World Model Planning

Wenbo Zhu, Paul Yi-Chia Chen, Yuanhan Li, Zishen Wan, Christopher Torng

原文摘要

JEPA-style latent world models let embodied agents plan toward new goals with model predictive control, but they are still too slow for real-life embodied control: sampling-based MPC repeats predictor inference tens of thousands of times per plan, and even on high-end GPUs one planning step can take tens of seconds. We observe substantial latent locality in this repeated-inference workload: the predictor maps close actions to close latents, and inside a quantized predictor this closeness takes a form that hardware can exploit, differential bit-level sparsity. Unlike an input stream, whose temporal similarity is given, a planner itself decides which candidates it evaluates together, so the planner can choose its own references and, with reference forest sampling, manufacture more sparsity: it couples the sampled action sequences of each group to a shared root, with competitive planning quality. We build the accelerator on the insights of the rich line of bit-level sparsity accelerators and design it and the planner tightly coupled as a single co-design: the planner increases sparsity and exposes structure for hardware scheduling, and the bit-exact hardware effectively uses the sparsity that the planner creates. On three JEPA world models, our co-design is 1.28-1.80x faster than a dense accelerator and uses 38-52% less energy, and it is 1.22-1.58x faster than prior bit-sparse design and uses 16-36% less energy, with the same area. To our knowledge, our planner is the first planner that manufactures differential bit-level sparsity across its candidates and exposes its structure for hardware scheduling, and our co-design is the first algorithm-hardware co-design for JEPA-style world-model planning.

cs.AR · cs.AI · cs.LG · cs.RO · eess.SY

新论文 · v1arXiv:2611.22482

LeViT-UNet++: Towards Balanced Fine-Grained Details and Context for Efficient Medical Image Segmentation

Guoping Xu, Jinling Zhu, Liuyue Li

原文摘要

Efficient medical image segmentation is essential for clinical applications requiring fast and accurate delineation, such as surgical navigation, radiation therapy, and real-time image-guided intervention. Despite substantial advances in convolutional neural networks and Transformers, attaining high accuracy under limited computational resources remains difficult, because reducing model complexity often sacrifices fine-grained structural details and global context modeling, yielding an unfavorable accuracy-efficiency trade-off. To address this, we propose LeViT-UNet++, an efficient encoder-decoder architecture that better balances local detail preservation and global context modeling. Specifically, we introduce a Haar Wavelet Multi-Scale Downsampling (HWMD) module that decomposes feature representations into low- and high-frequency components to extract multi-scale structural information, thereby mitigating detail loss during downsampling. We further develop a depthwise convolution-based decoder that integrates multi-scale global representations from Transformer blocks with local spatial features, enabling progressive feature refinement while reducing computational overhead. Evaluated on four benchmarks (Synapse, ACDC, LA2018, and MSD Heart) under both 2D and 3D settings, LeViT-UNet++ achieves competitive accuracy with a compact parameter footprint and fast inference. On Synapse, for instance, it attains a DSC of 76.57% with only 8.025M parameters and 241.72 FPS, confirming a favorable accuracy-efficiency balance. These results demonstrate the effectiveness of combining wavelet-based multi-scale feature extraction with lightweight local-global feature fusion for efficient medical segmentation. The source code is available at https://github.com/apple1986/levit_unet_pp.

cs.CV · cs.AI · cs.MM

新论文 · v1arXiv:2611.22480

RehearsalBench: Can AI Predict What Happens When You Change a Company?

Mika Siddiqui, Tharaka Perera

原文摘要

Organizations increasingly ask AI systems what will happen if they change how they operate: which work to automate, which team to resize, what a voice agent will do to waiting times. We introduce RehearsalBench, a benchmark that measures whether AI models can diagnose an operation, choose an intervention, and forecast its consequences. Each model is placed in a simulated bank contact center fitted to real call-level records, sees only what a manager would see, and submits a plan and forecasts that are then played out across 200 seeded futures and three plausible versions of the organization. Decisions are scored in dollars at the stakeholders' stated valuations; forecasts are scored on the effect of each change relative to doing nothing. Ten models made 280 attempts across 14 organizations. The best model, GPT-6 Astra, improved on doing nothing by 6.8% of the no-change cost and made 77% less forecast error than a forecaster who always predicts no effect. On average, every model forecast the direction of every specified effect correctly, but models erred on the size of the same effects in the same direction, overstating a voice agent's effect on repeat contacts about five-fold. No model ever recommended holding off when doing nothing was the right choice. To test external validity, twelve models forecast 33 real organizational changes with known outcomes. Under verdict rules fixed in advance, the benchmark's forecast ranking agreed with the real-world ranking (Spearman $ρ= 0.92$, 95% lower bound 0.50). We report the result alongside an inconclusive first test, the analysis choices made after outcomes were seen, and evidence that part of the agreement reflects how well models size their uncertainty.

cs.AI

版本更新 · v3arXiv:2609.16612

Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal corpora using frozen audio encoders

Mudit Sinha, Sanika Chavan

原文摘要

Comparing acoustic structure across very different vocal corpora is difficult because the recordings use different native event units, contain different amounts of sequence, and were collected under different conditions. We use the high-dimensional representations of frozen, pretrained audio encoders to measure acoustic diversity and temporal organization. Matched sampling gives each corpus the same opportunities to observe new acoustic forms and relationships between events, without changing its native event definition. We compare sperm-whale codas, human speech phones, Bengalese-finch syllables, and common-marmoset calls using 1,952 events and 1,700 adjacent pairs per comparison. Whale shows the fastest accumulation of encoder-defined acoustic groups, while Finch has the strongest repeated-sequence recurrence against ordinary within-block shuffles. Their neighboring-event dependence is closely matched under a source-and-position control. A second preceding event changes held-out prediction more favorably for Whale than for the other corpora, although Whale's standalone improvement remains uncertain. Waveform measurements recover several differences, but duration and acquisition-sensitive properties also contribute. Together, the findings show how pretrained representations can measure distinct forms of vocal organization, while waveform and source controls define the scope of the comparison.

cs.SD · cs.AI

版本更新 · v3arXiv:2610.25170

Forecasting Retail Sales at Every Grain: Trees, Foundation Models, Transformers and World Models Compared on Four Public Data Sets

Karthik Iyer, Madan Dabbeeru

原文摘要

A retailer makes decisions from the same demand at different grains: store orders by item and day, promotions by item and week, category reviews and supplier terms. This paper asks whether one forecast, built at the finest grain and summed to every coarser grain, can serve them all, and which model does that best. It compares LightGBM, pretrained foundation models (TimesFM, Chronos-Bolt, Timestral), the Temporal Fusion Transformer and a world model that carries each item's state forward under the price and promotion plan, on M5, six Dominick's categories, Breakfast at the Frat and Corporacion Favorita, with the world model and LightGBM tuned by a common search. When to use the average: the average of the tuned world model and LightGBM, summed to every grain, has the lowest error in 22 of 27 grain and data set cases and is never the least accurate on the final held-out periods. When to use the world model: on existing items kept out of training it loses at most 0.040 in scaled error, against up to 0.311 for LightGBM, and on lines with short history it is clearly more accurate on six of nine data sets. When to use LightGBM: on heavily promoted lines, fast sellers and lines with long history (six of nine data sets each) and in price-cut weeks. Inconclusive: lines never promoted and slow lines are close to even, and 52 weeks ahead the average is the most accurate on five of seven data sets, with the world model ahead of LightGBM on two of seven. The findings hold for these data sets and the price and promotion levers; anyone adopting them should rerun every comparison on their own data.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.39278

WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining

Yuhao Lu, Jiongxu Chen, Hexiang Wei, Jiajin Wu, Juelin Li, Mingjian Liang, Fan Yang, Zhuowei Liang 等 12 位作者

原文摘要

Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulations remain tied to specific robot configurations, and 3D motion prediction models use flow-only supervision, providing a limited learning signal for physical dynamics. To circumvent these limitations, we introduce \method{}, a generative world model that jointly predicts future video and query-based 3D trajectories. By parameterizing 3D motion as continuous displacement tokens aligned with the video grid, a unified Mixture-of-Transformers (MoT) backbone jointly denoises both modalities under a rectified-flow objective. This formulation couples explicit geometric dynamics with visual evolution, effectively unlocking the physical commonsense embedded within pretrained video models. To empirically scale and validate this unified architecture, we train \method{} on a heterogeneous mixture of 1.44 million object-level samples spanning simulated and real-world domains. We further introduce WorldFlowBench, comprising 1,678 evaluation samples from 11 data sources across simulated and real-world interactions, including spatial reasoning tasks. Across all three evaluation sets, WorldFlow achieves the lowest average displacement error (ADE) and final displacement error (FDE) among the evaluated learning-based methods. Notably, on the challenging SpatialCog set, WorldFlow achieves an ADE of 0.060 m, a 54.2\% reduction compared with the strongest external baseline. It also reduces ADE and FDE by 55.9\% and 68.5\%, respectively, compared with its flow-only variant. Project page: https://worldflow-rbs.github.io/.

cs.CV · cs.AI · cs.RO

版本更新 · v2arXiv:2605.07830

CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios

Taein Lim, Seongyong Ju, Munhyeok Kim, Hyunjun Kim, Hoki Kim

原文摘要

Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, agents exhibit distinct attack-selection biases, differing in both the families they explore and the concentration of their efforts. These patterns remain relatively stable across prompt variations. To systematically quantify this behavior, we introduce CyBiasBench, a comprehensive 630-session benchmark that evaluates five agents on three targets and four prompt conditions with ten attack families. We identify explicit bias across agents, with different dominant attack families and varying entropy levels in their attack-family allocation distributions. Such bias characterizes agent behavior within the evaluated environments and provides information beyond aggregate attack success rates. Furthermore, our experiments reveal a bias momentum effect, where agents resist explicit steering toward attack families that conflict with their bias. This forced distribution shift does not yield measurable improvements in attack performance. To ensure reproducibility and facilitate future research, we release an interactive result dashboard at https://trustworthyai.co.kr/CyBiasBench/ and a reproducibility artifact with aggregated session-level statistics and full evaluation scripts at https://github.com/Harry24k/CyBiasBench.

cs.CR · cs.AI

新论文 · v1arXiv:2611.22457

From Ideal to Real: Integrating Language Models into Smart Home for Human-Centric IoT Safety and Security Fuzzing

Lin Li, Xinbo Ban, Chao Chen, Lei Pan, Ming Ding, Kok-Leong Ong, Jun Zhang

原文摘要

Integrating IoT devices into household systems offers enhanced control over living environments. However, as these devices become pervasive in critical sectors such as healthcare, transportation, and home automation, they expose inter-rule vulnerabilities that may lead to privacy breaches, data theft, and physical harm. Traditional fuzz testing methods, which often operate in simulated environments assuming ideal human decisions, fail to account for the complexities of human interactions that can influence device operations in smart homes, potentially leading to unforeseen consequences. To reveal the impact of real human decisions and discover unexpected inter-rule vulnerabilities, we introduce an enhanced version of IoT Fuzz for smart homes by integrating large language models to emulate human decision-making processes. Our novel approach adds a layer of realism and unpredictability to the testing environment, more accurately capturing the diverse and dynamic nature of human interactions in smart home settings.

cs.AI

新论文 · v1arXiv:2611.22456

PACD: Provenance-Aware Consensus Decoding for Mitigating Cross-Modal Hallucinations in Omnimodal Large Language Models

Chang Sun, Yijun Tian, Zhenwei Tang, Yuchen Deng, Yifan Simon Liu, Chenxu Wang, Wei Wang

原文摘要

Omnimodal large language models (Omni-LLMs) integrate audio, video, and text for multimodal reasoning, yet remain vulnerable to cross-modal hallucinations, where one modality improperly influences predictions about another. Existing training-free decoding methods mitigate these errors through modality perturbation or relevance-based weighting. However, due to interference from irrelevant modality cues during fusion and difficulty detecting shared errors, these methods may suppress correct unimodal predictions and allow erroneous consensus to persist. To address these limitations, we propose Provenance-Aware Consensus Decoding (PACD), a training-free framework for mitigating cross-modal hallucinations. PACD comprises two complementary paths based on whether the branches reach consensus. For non-consensus cases, Relevance-Guided Candidate Arbitration identifies task-relevant unimodal evidence and selectively arbitrates between predictions using alternative candidates. For consensus cases, Provenance-Based Consensus Recovery leverages the outranking principle to evaluate the consistency and strength of layer-wise modality evidence for alternative answers, selectively resolving erroneous consensus under confidence constraints. Extensive experiments on four Omni-LLMs and five benchmarks across two tasks demonstrate the superiority of PACD. Compared to existing methods, PACD achieves up to 27.6% relative improvement over standard decoding across CMM, AVHBench, and SVHalluc for cross-modal hallucination mitigation, and an average relative improvement of 7.7% over best baseline across OmniVideoBench and FutureOmni for general audio-visual reasoning.

cs.AI · cs.LG

新论文 · v1arXiv:2611.22446

As Student Rollouts Continue, Visual Backdoors Keep Growing

Zane Fu, Yanzhao Zheng, Jinze Liu, Ziting Qin, Qianshan Wei, Jihuai Zhu, Yipeng Yu, Baohua Dong 等 10 位作者

原文摘要

Conventional knowledge distillation can facilitate the propagation of backdoors from teacher models to student models. However, how this risk manifests in On-Policy Distillation (OPD) remains insufficiently studied. OPD has recently emerged as an important post-training paradigm for Vision-Language Models (VLMs). Unlike traditional offline distillation, OPD does not require teacher-generated responses. Instead, it uses the teacher's probability distributions to supervise response trajectories generated online by the student. Since the initial student model typically generates benign responses and receives no explicit supervision from malicious target responses, OPD appears to offer some inherent resistance to backdoor propagation. In this paper, we challenge this intuition and reveal a more subtle risk of visual backdoor propagation in OPD. Through experiments across multiple model families and datasets, together with theoretical analysis, we identify three main findings. First, unlike the relatively gradual propagation observed in traditional offline distillation, backdoors rarely emerge in OPD at low poisoning ratios. However, the attack success rate rapidly approaches 100% once a critical threshold is exceeded. Second, backdoor propagation does not depend on explicit malicious responses. Instead, it is driven by the continuous accumulation of anomalous probability mass assigned by the teacher. Finally, based on these findings, we propose a novel trigger design that enables visual backdoor propagation with zero explicit trigger injection. These findings further reveal an overlooked mechanism of backdoor propagation in OPD and highlight its potential security risks.

cs.CV · cs.AI

新论文 · v1arXiv:2611.22438

Eyes in the Update? Learning Where Rewards Land in Multimodal Reasoning

Lixuan He, Tianzhe Chu, Shulin Tian, Shikang Zheng, Feng Chen, Yi Ma

原文摘要

Multimodal post-training has moved from broad instruction tuning toward reinforcement learning for image and video reasoning, where outcome rewards can improve final-answer accuracy. Yet these rewards are assigned to complete generated trajectories, while visual evidence is used only at sparse and uneven positions inside the response. Recent work has begun to make multimodal RL more token-sensitive through grounding signals or external token-level weighting. We ask a more specific question: can the allocation of the same trajectory-level reward be inferred from the model's own multimodal computation, rather than from an auxiliary annotator, perception module, or process label? We propose Gaze-RL, a representation-driven policy optimization method that redistributes completion-level advantage through a latent reward landing field. The field is computed from internal cross-modal geometry and local predictive uncertainty, assigning larger update weight to positions that are both visually anchored and decision-bearing while remaining mean-one, so the total credit of each rollout is preserved and only its positionwise allocation changes. Gaze-RL requires no process supervision, auxiliary perception module, or architectural modification, and improves both Qwen2.5-VL and InternVL3.5 across a broad range of image and video benchmarks.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22434

Encoding, Decodability, and Use: A Five-Layer Framework for Benchmark Measurement Audits with Evidence from UAV Intent Recognition

Zhirong Su, Tian Zhang

原文摘要

Benchmark accuracy is routinely read as evidence that a model understands the construct the benchmark measures. We propose and instantiate on AeroIntent a five-layer framework that decomposes that reading into observation, representation, decoding, use, and behaviour. The framework separates encoding, decodability, and use as distinct levels. In the instantiation, the observation layer is unreliable on 7 of the 20 Drone programs and floors the direct visual correlate of radial velocity at a 0.26\% scale change. The representation layer exposes two task-designed RGB features with nominal signals. RAFT flow radial bias reaches $r=+0.257$ ($p=0.030$), and bounding-box optical-flow divergence reaches $r=+0.203$ ($p=0.029$). No multi-feature readout gives a fold-mean test correlation above the cluster minimum detectable effect (MDE), and the largest positive global out-of-sample correlation is $r=+0.080$. The decoding layer sets the MDE at $|r|=0.599$ at the multi-feature Bonferroni threshold ($α=0.00714$, power 0.80), and the observed $r=+0.080$ has power 0.00. Two injection experiments establish the MDE's condition from both sides: aligned injections are detected at or above the simulated power, and orthogonal injections are not detected. The use layer finds accuracy consistent with program memory (program-identity 0.937/0.597/0.210) and multi-region static cues. The behaviour layer is consistent with accuracy not requiring a radial-velocity readout (appearance 0.6552 vs bounding-box trajectory 0.4080, cluster-level paired $Δ=+0.2471$, $p=0.0132$).

cs.LG · cs.AI

版本更新 · v2arXiv:2610.25963

ABACUS: Program-Guided Multistep Reasoning over Frozen Judgment Models

Yuhao Wang, Zelin Zang

原文摘要

Judgment models answer semantic questions by scoring a finite set of candidate outcomes. Can reusable programs turn these local decisions into powerful multistep reasoning? We introduce \method, a framework that jointly constructs judgment schemas and composition programs for frozen judgment models. A generative teacher designs the procedure offline; the judgment model resolves local semantic questions online, and the saved program composes its decisions into an answer. We study three allocations of design effort between humans and the teacher, focusing on construction through a shared interface. We instantiate the framework with Kev. On three selected BIG-Bench Hard tasks, nine independently constructed programs solve all 450 executions of 150 development inputs. A separate deployment study freezes three programs after development-set reference-agreement refinement and evaluates them on 600 held-out questions. These programs achieve near-perfect 99.67\% macro accuracy, versus 64.00\% for direct Kev and 68.80\% for final-answer-only Qwen3.5-4B. They attain comparable observed accuracy to Qwen's unrestricted response policy (99.07\%) with an \textbf{8.43-fold online speedup}: 0.255 versus 2.150 seconds per question. These results show how reusable programs can substantially expand the reasoning capability of a compact judgment model while keeping its parameters fixed.

cs.AI

版本更新 · v5arXiv:2606.16084

Rhythm of the Deep: Two-tier acoustic organization of sperm-whale codas from click waveforms to coda sequences

Mudit Sinha, Sanika Chavan

原文摘要

Sperm-whale codas are usually described by the number and timing of their clicks. These measures reveal patterns in whale communication, but do not describe how individual clicks sound. We ask what click waveforms add beyond timing and how acoustic information is organized within codas and across sequences of codas. We analyze 1,952 codas, using frozen audio encoders to identify recurring forms of clicks and whole codas independently. Direct spectral and envelope measurements then test whether the click forms differ in recorded sound. Within codas, click-form composition improves the measured prediction of whole-coda form beyond timing alone. Click spacing also remains related to whole-coda sound when the same click forms are present. Neighboring click forms help predict the next click in the annotated sample, although their order does not improve the tested classification of whole codas. Across recorded sequences, the second preceding whole-coda form improves prediction beyond the immediately preceding form. The gain exceeds two broad first-order references, but stricter controls do not establish a general higher-order rule. Together, these findings show different organizing relationships at the two scales. Within codas, click sound and rhythmic spacing help distinguish complete vocalizations. Across codas, earlier whole-coda forms help predict what follows.

cs.AI · cs.CL

版本更新 · v2arXiv:2610.16957

SarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection

Niyazi Ahmet Metin, Dilara Keküllüoğlu

原文摘要

Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearly hateful wording. Sarcasm is one such form of indirect expression, as it can convey harmful intent through mock praise, exaggeration, humor, or apparent politeness. In this paper, we introduce SarcasTraps, a targeted external test set for analyzing the effect of sarcasm on Turkish hate speech detection. SarcasTraps contains 479 entries annotated along two dimensions: hate speech and sarcasm. We train classifiers using BERTurk and XLM-RoBERTa on two existing Turkish hate speech datasets and evaluate them on SarcasTraps, using it strictly as an external test set. We also evaluate GPT-4.1 and Llama-3.3-70B in a zero-shot setting on SarcasTraps. Results show that sarcasm substantially affects hate speech detection. Fine-tuned encoder models lose recall on sarcastic hate, while zero-shot LLMs maintain higher recall but suffer substantial precision drops on sarcastic examples. These findings show that both fine-tuned hate speech detectors and zero-shot LLMs struggle when sarcasm is involved, and SarcasTraps provides quantitative evidence of this challenge through a targeted Turkish test set. Due to the presence of sensitive and hateful language, SarcasTraps will be shared upon request for academic research purposes. Warning: This paper has examples from the dataset which contains offensive and hateful content towards groups of people.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.22420

Proceedings of the 2026 XCSP3 Competition

Gilles Audemard, Christophe Lecoutre, Emmanuel Lonca

原文摘要

This document constitutes the proceedings of the 2026 XCSP3 Competition. The results of this competition of constraint solvers were presented at FLOC (Federated Logic Conference) 2026 Olympic Games, held in Lisbon, Portugal from 20th to 29th July, 2026.

cs.AI

新论文 · v1arXiv:2611.22407

ROSMonitoring in Action: Runtime Monitoring and Enforcement for ROS 2 Actions

Giacomo Paltrinieri, Angelo Ferrando

原文摘要

Robotic applications often rely on long-running operations, such as navigation, manipulation, and inspection, which in ROS~2 are commonly implemented as actions. Unlike topics and services, actions involve a structured lifecycle comprising goal submission and acceptance, feedback, status updates, result retrieval, and cancellation. Existing versions of ROSMonitoring support topics and services, but do not reconstruct this lifecycle or expose action-level events to a runtime-verification oracle. In this paper, we extend ROSMonitoring with runtime monitoring and enforcement for ROS~2 actions. Actions are declared directly in the monitoring configuration and automatically instrumented through the underlying ROS~2 communication endpoints. The generated monitor reconstructs action-level events, correlates them through goal identifiers, maintains the state of active goals, and translates violations into protocol-aware enforcement operations. These include goal rejection, cancellation, message suppression, and protocol-compliant responses generated directly by the monitor when the original communication cannot be forwarded. We evaluate the implementation through controlled stress tests that vary the number of action invocations, workload size, and client–server topology. The results show approximately linear growth in monitoring cost with repeated action invocations under a fixed workload, while larger action workloads and a greater number of configured client–server pairs introduce additional overhead. These results characterise the scaling behaviour of the current implementation under the tested sequential workloads while highlighting the main performance limitations of the current synchronous implementation.

cs.AI · cs.LO · cs.RO

新论文 · v1arXiv:2611.22404

Symbolic Abstraction Refinement

Daniel Bryce, Robert P. Goldman, David J. Musliner, Jeremy Gottlieb, John Skovbekk

原文摘要

Autonomous systems choose actions whose outcomes are uncertain and are subject to time constraints. Probabilistic timed automata (PTAs) model exactly this, and verifying one answers a question about the system's decision-making: the maximum probability of reaching a goal, or the minimum probability of reaching a hazard, that a controller can guarantee. Verification normally works over symbolic states, each pairing a discrete location with a region of clock values, and its difficulty is that the best behavior generally varies within such a region. The PRISM verifier's most capable PTA method responds by splitting regions until each is uniform, rebuilding the transitions that reach them and propagating the split backward through the state graph of a stochastic game, a cascade of graph reconstruction that partitions regions the property never depends on. We present SYMAR, which instead makes the value function symbolic: each symbolic state carries a function from sub-regions of its clock region to probability bounds, so refinement is the appearance of new sub-regions in that function, and previously generated states are never split nor their incoming transitions reconstructed. Both sources of PTA nondeterminism, the timing and the choice of actions, are captured implicitly by the preimage computation that produces those sub-regions. Heuristic forward search then bounds how much refinement is done at all, expanding an And-Or graph from the initial state along the most promising behaviors so that effort is confined to the property-relevant fragment, guided by bounds and preferred actions from a single unrefined run of the existing method; a partial-refinement backup keeps the otherwise combinatorial sub-region count lean, and every stored interval provably contains the true probability. On the PRISM PTA benchmarks, whose subproblems recur in autonomous systems (distributed agreement under contention, leader election, and self-configuration without central coordination), SYMAR is up to 108x faster, solves an instance on which the existing method exhausts the time limit, and is markedly less sensitive to the deadline constant, resolving one instance in a 37-node search graph, unchanged as the deadline triples, where the existing method needs 86,380 abstract states and 73 refinement rounds.

cs.AI

新论文 · v1arXiv:2611.22392

Deal With It: On Better Schedules for Listwise Reranking

Benjamin Clavié, Herumb Shandilya, Hanna Lichtenberg, Aamir Shakir, Makoto P. Kato

原文摘要

Listwise LLM rerankers cannot reliably rank hundreds of documents in a single call, and rely on schedules to orchestrate their calls. Parallel schedules split candidates into groups and advance a fixed quota from each. When a group holds more of the top passages than its quota, some are cut, and expensive repair calls become required. We show that the way candidates are split matters where such a quota can bind, and that, in expected cuts, the best split there deals them round-robin by retriever rank, like cards. Although not conceptually new, dealing has remained unanalyzed. We prove that, under a simple retriever model, no split with equal quotas cuts fewer of the true top ten on average, and that contiguous chunks cut more as the retriever improves. DealRank, the simplest schedule our analysis allows, is on average within 0.1 nDCG@10 points of the best schedules over six LLMs, in two rounds. It is consistently 1.1 to 1.4 times faster than BlitzRank with concurrent first calls up to a thousand candidates. There, it needs three rounds and is eleven times faster than the sliding window. In existing schedules such as BlitzRank, dealing reduces repair calls from 59% of queries to 14%, improving latency with no significant change in quality. Random partitioning appears equivalent at a quota of four, as predicted, but ties results to the seed and trails by 1.3 nDCG@10 points at a quota of one over a dense retriever.

cs.IR · cs.AI