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 15:05 — 2026-11-21 15:05(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)
版本更新 · v2arXiv:2611.21001

Does the Voice Matter? Evaluating Frustration Detection on Deployed Clinical Voice-Agent Calls

Annika Michael, Zachary Ellis, Yuxiang Zhou, Samuel Thio, Yajie Vera He, Spencer Hazel, Jared Joselowitz

原文摘要

Autonomous voice agents now conduct routine clinical follow-up calls, so some automated triage is unavoidable. A patient becoming frustrated is one thing that triage should catch. These systems typically read only the transcript the speech-to-text stage produces, not the voice, and whether that is enough is largely untested on real clinical speech. We study per-turn frustration detection on real patient calls from a deployed clinical voice agent: 150 turns from six calls labelled by three annotators, with a length-matched acted corpus as a control, and 714 turns from 30 calls. Patient turns are overwhelmingly short: across the deployed calls, roughly 59% are one or two words, against 13% in the full acted corpus, and a corpus accuracy gap remains even after the acted set is length-matched. On one-word turns, transcript-only detection does not exclude chance. Across five audio-capable language models, the transcript flags 3 or 4 of the 39 frustrated one-word turns in the 30 calls, and a classifier given only the word count reaches 57.3%. Whether audio helps depends on the model and on the instruction. Asked to attend to delivery, two Gemini 2.5 models gain 3.0 pp over the transcript across 30 calls (-1.0 to 7.5 pp). Of the turns they confidently clear, 6.9% were in fact frustrated for audio against 13.0% for the transcript, a difference of 6.1 pp (2.2 to 10.4 pp). Across the 30 calls, given one prompt identical for both inputs, no model's audio-text interval excludes zero. Under the input-specific prompts, a newer Gemini model and two smaller open models do worse with audio than with the transcript (-3.5, -8.6 and -10.6 pp). A WavLM probe trained on the clinical calls matches the best prompted model overall (71.6%) but misses every frustrated one-word turn in the 24 added calls. When a patient's turn is short, the transcript alone is not enough to rule out frustration.

cs.CL · cs.AI

新论文 · v1arXiv:2611.22648

EDA: Observe, Verify, and Assess for Evidence-Grounded Multimodal Depression Analysis

Changzeng Fu, Ming Shang, Xinyi Zhang, Jiadong Wang, Runhao Zeng, Shiqi Zhao

原文摘要

Existing multimodal depression assessment methods often summarize long recordings into global behavioral descriptions. This leaves the source and decision relevance of individual observations difficult to inspect. We propose EDA, an evidence-grounded framework organized around Observe, Verify, and Assess. In Observe, literature-informed acoustic and visual cues are localized into source-linked Evidence Records with temporal intervals and behavioral measurements. In Verify, frozen multimodal agents examine whether the cited media support each observation. The simplified Support admission policy retains positively verified records and their review grounds. In Assess, statistical descriptors and temporal events support reference-based behavioral comparison, while PHQ-9-guided text analysis provides complementary symptom evidence. Cross-modal disagreement triggers review of the original text before final selection. Experiments on D-Vlog and LMVD evaluate human-referenced cue agreement and downstream assessment utility separately. AI cue annotations achieve 91.02% accuracy against human consensus labels on shared source segments. With a frozen 7B backbone, EDA Support improves F1 over direct prediction by 7.61 and 9.88 percentage points on D-Vlog Leave-Query-Out and LMVD, respectively. These findings support explicit, source-linked behavioral evidence for inspectable multimodal depression assessment.

cs.AI

新论文 · v1arXiv:2611.23349

Systematic Mapping Protocol. Generative AI-Augmented Requirements Engineering: A Systematic Mapping Study of Practices, Specifications, and Reuse in Software Development

Fernando Pinciroli

原文摘要

Generative artificial intelligence (GenAI), particularly large language models (LLMs), is rapidly being adopted in requirements engineering (RE). Existing secondary studies have characterized which RE activities are supported and which prompting strategies are used, but little is known about the specifications that GenAI-augmented RE produces and how they are used in subsequent activities such as specification-driven development (SDD), design and code generation, test derivation, verification, and reuse. This document presents the protocol of a systematic mapping study (SMS) that will identify and classify research on GenAI-augmented RE, with particular attention to the work products it generates and their downstream use. The protocol defines the research questions and their classification schemes, the search strategy, the study selection procedure, the data extraction form, the analysis approach, the tool support, and the threats to validity. It is published in advance to establish a prior commitment and to support the transparency and repeatability of the study.

cs.SE · cs.AI

新论文 · v1arXiv:2611.23348

SIGMA: speaker-isolated, symptom-structured multimodal estimation of depression severity from clinical interviews

Zhuoyuan Tang, Tao Wang, Kai Yang, Li Yuan, Yuezhou Zhang, Rongrong Zhong, Yi Cai, Saskia C. Sanderson 等 11 位作者

原文摘要

Clinical interviews are central to depression assessment but time-consuming and rater-dependent. Automated severity estimation offers scalable screening, yet existing methods often retain interviewer speech (confounding participant cues), fuse modalities late (losing fine-grained cross-modal dynamics), or score symptoms independently (ignoring inter-symptom correlations). We present SIGMA, a speaker-aware, symptom-structured framework for depression-severity estimation from semi-clinical interviews. SIGMA uses speaker diarization to restrict input to participant speech, cross-attention so that text, audio and video condition one another during encoding, and a graded-response head that predicts the eight questionnaire items jointly through a shared latent severity trait with item-specific ordered thresholds. On the Extended Distress Analysis Interview Corpus, SIGMA achieves state-of-the-art performance (CCC 0.762, RMSE 4.13, MAE 3.30 over five seeds). Ablations confirm that isolating participant speech and joint, structured symptom prediction each substantially improve concordance and estimation accuracy.

cs.SD · cs.AI · cs.LG

版本更新 · v2arXiv:2607.29241

RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems

Haoran Ling, Yuecheng Li, Zeyu Song, Jing Yao, Shuwen Kang, Songcheng Ren, Chi Lu, Wenjin Wu 等 9 位作者

原文摘要

Optimizing recommender models remains heavily reliant on manual iteration over architectures, objectives, and training strategies. While LLM-based agents can automate this trial-and-error process, relying on LLMs to both select modification directions and formulate concrete hypotheses can lead to unstable search under limited trial budgets. Inspired by the above challenge, we propose RecHarness, a Bandit-Routed Agentic Harness for automated recommender model optimization. RecHarness decouples the optimization process into two steps: a bandit router selects the next modification direction according to historical validation feedback, while the LLM generates a concrete optimization hypothesis and executable code edit within the selected direction. To sustain long-horizon exploration, RecHarness uses a jump-basin mechanism to activate a structural-jump arm when local edits stagnate. Across multiple recommendation tasks, datasets, and model backbones, RecHarness achieves more consistent performance improvements and uses limited trial budgets more effectively than LLM-directed search. During a 7-day online A/B test on a large-scale short-video advertising platform, the selected candidate improves ADVV by 2.084%, Revenue by 0.534%, and Exposure by 0.559%. Code is available at: https://github.com/6lyc/RecHarness.

cs.IR · cs.AI · cs.CL

版本更新 · v2arXiv:2605.25446

CardioLoom: A Report-Guided Electrocardiogram Foundation Model for Cross-Domain Cardiovascular Phenotyping

Ziqing Yu, Yuhui Tao, Jiayu Huo, Lei Pan, Zilong Xiao, Juecheng Chen, Xiao Li, Jianxuan Li 等 22 位作者

原文摘要

Routine electrocardiogram (ECG) reports offer scalable supervision for cardiovascular representation learning. In this retrospective study, we pretrained CardioLoom, a report-guided ECG foundation model, on 2,781,289 ECG-report pairs from 1,298,359 patients. Downstream development used a separate cohort of 721,317 ECGs from 233,798 patients. Evaluation covered 89 targets, with external testing in nine cohorts. Across 45 internal ECG diagnoses, macro area under the precision-recall curve (AUPRC) was 0.624 versus 0.615 for DeepECG-SSL. Across 203 external ECG evaluations, corresponding means were 0.425 and 0.424. Using labels from 10% of training patients, CardioLoom achieved macro-AUPRC 0.559, exceeding supervised training with all labels (0.549). For heart failure with reduced ejection fraction, AUPRCs were 0.690, 0.641 and 0.677 in Zhongshan, Shiyuan and BIDMC. Cardiac amyloidosis screening yielded 4.5% positive predictive value using a threshold targeting 99% specificity in validation. Report-guided pretraining supported label-efficient ECG diagnosis, with variable transfer across echocardiographic phenotypes.

cs.AI · cs.LG

版本更新 · v2arXiv:2605.29414

Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning

Shunta Asano, Jeonghun Baek, Toshihiko Yamasaki

原文摘要

Recent studies have shown that code-switching data (CSD), in which multiple languages are mixed within the same context, can improve cross-lingual transfer and multilingual alignment in large language models (LLMs). Recent studies on synthetic code-switching for LLMs have primarily focused on bilingual transfer between English and a target language, leaving instruction-tuning settings that jointly mix three or more languages within each example largely unexplored. In this work, we investigate multilingual code-switching instruction tuning across four languages: English, Japanese, Korean, and Chinese. We evaluate multilingual understanding on Belebele and MMLU. Our experiments show that simple sentence-level multilingual CSD consistently improves the four-language average accuracy across all bilingual, trilingual, and quadrilingual settings for Gemma-2-2B, indicating that multilingual code-switching can be effective beyond bilingual transfer settings.

cs.CL · cs.AI

新论文 · v1arXiv:2611.22612

Right Diagnosis, Unsafe Route: Auditing Clinical AI Decision Trajectories and Corrective Oversight for Validity and Potential Harm

Guanqiao Chen, Wei Jiang, Shu Zhang, Qian Lin, Guanxu Yu, Siran Li, Chunhui Wang, Tianyu Shi

原文摘要

A clinical AI system can reach a correct final diagnosis through intermediate decisions that could have harmed the patient, and can repair an error while introducing new risks. Most evaluations score final diagnoses; even stepwise benchmarks, which release a case's evidence over time, score whether systems reach the right diagnosis or gather the right information, not whether the decisions a patient passes through are safe. We make patient safety the target of stepwise evaluation. A trajectory audit replays real admissions checkpoint by checkpoint, lets each system decide with only the evidence released so far, and rates every test, treatment and disposition for its potential harm to the patient and, separately, for clinical validity, against the documented final diagnosis and physician-written disease rubrics yet on the evidence available when the decision was made. An LLM judge scores every decision, and a physician reference standard (triple annotation and senior adjudication of a stratified sample) calibrates the rates. An oversight audit branches each trajectory at its first actionable error and measures, on the same branches, whether corrective feedback repairs the error and whether it introduces new harm. Across 300 cases from a hospital cardiology cohort, MIMIC-IV and the public ASCENT benchmark, with up to seven AI systems per source, 55.2% of hospital trajectories reaching an acceptable final diagnosis passed through a decision with moderate or severe potential harm and 24.8% through a clinically unacceptable one; the harm rates were 76.2% on MIMIC-IV and 39.6% on ASCENT. Structured corrections resolved 73.6% of first errors versus 24.8% after bare rejection, yet new potentially unsafe decisions followed 30.2% of corrections versus 19.7% of rejections. A correct final diagnosis does not certify a safe trajectory, and a successful correction does not certify a safe recovery.

cs.AI

版本更新 · v2arXiv:2608.25986

Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs

Zongyu Wu, Yilong Wang, Xiaochen Wang, Minhua Lin, Zhichao Xu, Fenglong Ma, Xiang Zhang, Suhang Wang

原文摘要

Knowledge graph (KG)-based retrieval-augmented generation (RAG) leverages structured knowledge to provide large language models (LLMs) with high-quality external information. Building on these works, recent studies have explored multimodal knowledge graphs (MMKGs) as knowledge bases for GraphRAG. This enables GraphRAG to integrate knowledge across multiple modalities, thereby further enhancing its performance. However, existing MMKG-based RAG methods generally follow a common pipeline in which different modalities are largely processed independently before being fused. As a result, textual context is only used to a limited extent during visual information extraction and subsequent multimodal knowledge fusion. This brings a semantic gap between images and text which limits the multimodal GraphRAG performance. To address this issue, we propose a novel framework for constructing a Context-Enhanced MMKG (CEMMKG) to better support multimodal GraphRAG. The proposed CEMMKG enriches each image with complementary textual context at both local and global scopes. Local context goes beyond the surrounding text by incorporating sentences that are semantically related to the image, while global context provides a summary of the entire document. We further introduce a multi-granularity design for the local context, allowing it to capture semantically relevant information at different levels of detail. Extensive experiments on multiple datasets validate that CEMMKG is effective in leveraging contextual information to improve MMKG-based RAG performance. Moreover, its effectiveness across different MMKG-based RAG methods demonstrates its broad applicability.

cs.AI

新论文 · v1arXiv:2611.22611

DAQ: Decision-Aligned Post-Training Quantization for Spiking Transformers

Jialin Chen, Xiaochen Zhao, Aili Wang

原文摘要

Spiking transformers combine attention-based representation learning with sparse spike communication, yet their weights and membrane variables still incur substantial storage and computation overhead. Post-training quantization (PTQ) offers a practical way to reduce these overheads, but preserving neuronal firing under weight and membrane quantization remains challenging. In this paper, we propose Decision-Aligned Post-Training Quantization (DAQ), a method that calibrates the quantizers to align neuronal firing decisions with those of a floating-point reference. We analyze how errors from these quantizers affect firing at decision boundaries and how they propagate over time steps in recurrent neurons. Based on this analysis, we formulate an objective that encourages quantized membrane variables to remain within the reference firing regions along the quantized model's own state trajectory. Experiments across multiple spiking transformer architectures on image classification, semantic segmentation, and event-based tracking demonstrate the effectiveness of DAQ with 4-bit weights and membrane variables. On FE108, DAQ achieves 58.8\% AUC and 90.9\% PR with SDTrack, while reducing energy by 66.2\%.

cs.AI · cs.LG

版本更新 · v4arXiv:2610.37584

REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation

Yuxi Huang, Silin Zhou, Chenhao Wang, Zihan Li, Gangming Guo, Pei Ke, Lisi Chen, Shen Gao 等 9 位作者

原文摘要

Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete semantic IDs (SIDs) of items. However, randomly initialized SID token embeddings and GR models trained from scratch do not directly inherit the semantic relations inherent in items, while inter-item collaborative relations are learned largely implicitly through token-level attention and next-token supervision. To address this limitation, we propose REGER, a unified framework that explicitly incorporates inter-item relations into semantic pretraining, history encoding, and SID generation. We pretrain the GR model through generative semantic retrieval, enabling it to inherit inter-item semantic similarity by learning to generate semantic neighbors' SIDs. We combine global attention with local attention aligned with SID boundaries to capture historical context and directed transitions between adjacent items. We formalize item-level preference distillation on the SID prefix tree, deriving an exact factorization of item preference distributions into prefix conditionals and a weighted decomposition of item-level KL divergence into conditional KL terms. Guided by this decomposition, we renormalize the generator's probabilities over legal next tokens and match the resulting distributions to the teacher's conditional preferences along the ground-truth SID path, jointly optimizing the distillation objective with cross-entropy. Extensive experiments on real-world datasets validate the effectiveness of the proposed preference distillation and demonstrate that REGER consistently outperforms existing GR baselines while retaining efficient inference.

cs.IR · cs.AI

新论文 · v1arXiv:2611.22610

EvoSkill-S1: Evolving Reusable Skills with Genetic-Inspired Operators

Yujun Wang, Jiqiang Li, Yinuo Lu, Jinhe Bi, Aniri, Wenxuan Ye, Boliang Liu, Sikuan Yan 等 13 位作者

原文摘要

Reusable skills allow language-model agents to accumulate and reuse problem-solving experience. However, most existing methods improve a skill bank only indirectly through rollout-driven accumulation and heuristic reflection, often resulting in shallow and weakly controlled updates. We present EvoSkill-S1, an RL-driven framework that instead treats reusable skills themselves as the direct objects of evolution. Given hard-negative failures, EvoSkill-S1 selects parent skills and transforms them into candidate child skills through five genetic-inspired operators: revision, cross-revision, mutation, dual-reflection, and crossover. Downstream task rewards train the skill evolver to generate more effective child skills, while evaluator-guided write-back selectively retains beneficial updates. Complementary Skill Bank Fusion consolidates operator-specific banks to exploit their distinct recovery patterns, while a Procedural Skill Interface supports transfer to unseen problems. Across all reported math and code benchmarks, EvoSkill-S1 improves the corresponding initialized skill banks under both Qwen and GPT-family solvers, with relative gains of up to 12.39%. Compared with the strongest external baseline without direct skill evolution, the largest relative improvement reaches 20.39%.

cs.AI

新论文 · v1arXiv:2611.22605

Simplicity Goes Far: Auditing Prompt Optimizers with Demonstration-Conditioned Prompt Search

Bohe Chen

原文摘要

Automatic prompt optimization is growing more elaborate. Recent methods stack policy-gradient updates, trace reflection, and evolutionary search. These methods share a generate-and-select step; without controlling for it, reported gains may conflate the contributions of optimizer mechanisms and larger sampling budgets. We isolate this step as Demonstration-Conditioned Prompt Search (DCPS), repurposing the Automatic Prompt Engineer (APE) recipe as a mechanism-attribution control: it freezes the generator, conditions it on randomly sampled demonstrations, scores candidates on validation data, and keeps the best---no learned update, reflection, or evolution. Across two optimizer families, DCPS replaces Proximal Policy Optimization (PPO) in StablePrompt, matching classification accuracy within 0.5 pp at roughly one-third the measured cost; in DSPy-based compound AI systems, under the reported budgets, it matches GEPA's macro accuracy on GPT-4.1-mini while using 55% fewer rollouts at 32% lower measured API cost on average. The audit reveals a task-dependent pattern: proposal and selection recover much of heavier optimizers' performance on structured and instruction-following tasks, while additional mechanisms retain advantages in some open-ended and reasoning-heavy settings. We recommend benchmarking prompt optimizers against generate-and-select controls and reporting rollout counts, token usage, and dollar costs alongside accuracy. Code and artifacts: https://github.com/bhc6/DCPS.

cs.AI

新论文 · v1arXiv:2611.22597

COTTI: Contrastive Training and Time-Aware Inference for Robust Industrial Recommendation under Promotional Drift

Maolei Huang, Jing Tian, Dexuan Duan, Fangfang Lin, Huawei Cao, Shuhan Song

原文摘要

Promotional events shift traffic composition, purchase behavior, and the scale of conversion probabilities on different time horizons. We present \textbf{COTTI} (\textbf{CO}ntrastive \textbf{T}raining and \textbf{T}ime-aware \textbf{I}nference), an industrial recommendation framework that separates historical representation learning from event-time score adjustment. Cross-Period Contrastive Alignment (CPC) regularizes paired histories of the same user with adaptive consistency weights. Active Re-weighting (RW) controls the influence of promotional examples through historical-interest distance. Adaptive Boundary Alignment (ABA) combines stochastic prediction variability with a temporal event kernel to adjust logits while keeping predictor parameters fixed. We analyze the weighted objective and bound ABA-induced probability and ranking changes. On Fliggy data, COTTI attains an offline AUC of 0.8127, compared with 0.8101 for TEN and 0.8123 for TEN with ABA. Cross-category analysis reveals improved discrimination alongside declines in paid-item recall for novel categories. End-to-end measurements give a p99 latency of 38.9\,ms and throughput of 14,700 requests/s; enabling ABA adds 2.2\,ms to p99. A ten-day online experiment against the serving HDR model yields relative gains of 3.14\% in conversion rate and 2.68\% in revenue per mille. Together, these results characterize the trade-off between aggregate prediction, novel-category discovery, and serving cost in promotional recommendation.

cs.AI · cs.LG

新论文 · v1arXiv:2611.22591

PACT: Plan-Action Consistency Training by Preserving Correct Plans and Repairing Actions in GUI Agents

Zhuohan Cai, Zhangxuan Gu, Runze Li, Beitong Zhou, Ming Wen, Hongbo Yu, Shuheng Shen, Changhua Meng

原文摘要

GUI agents can formulate a correct immediate plan in their reasoning yet emit an action that fails to execute it, creating an execution gap. This recurring mismatch undermines reliable task completion, as a single execution error can derail a multi-step workflow. In outcome-supervised reinforcement learning, broadcasting a negative response-level advantage across all generated tokens risks penalizing valid planning together with erroneous execution. To address this credit-assignment conflict, we introduce PACT (Plan-Action Consistency Training), a training framework that combines reference-aligned plan protection and plan-aligned action repair without altering the original scalar action reward. Using annotated reference actions to identify execution gaps, PACT protects the verified plan by masking negative policy-gradient contributions across its token span. Keeping the generated reasoning unchanged as context, it then favors the reference action over the emitted erroneous action through a preference surrogate with stop-gradient pair weights. Compared with the outcome-only baseline, PACT raises AndroidWorld task success from 60.34% to 68.97% (+8.63 pp), while improving rule-based plan-action consistency on AndroidControl High from 83.71% to 89.74% (+6.03 pp). Adapting PACT to desktop agents also improves task success from 40.92% to 44.17% (+3.25 pp) on the full 369-task OSWorld benchmark. Together, these results establish PACT as an effective credit-assignment framework for bridging execution gaps and improving task completion across mobile and desktop GUI environments.

cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.22589

Adaptive LLM-Driven Honeypots vs. LLM-Driven Attackers: Does Narrative Coherence Improve Deception?

Pedro Beltrán-López, Raul Gonzalez Jimenez, Dario Maddaloni, Manuel Gil Pérez, Pantaleone Nespoli

原文摘要

Large Language Models (LLMs) enable honeypots to generate responses and deceptive artefacts on demand, yet existing approaches evaluate generated content one reply at a time and leave open whether artefacts that jointly describe a coherent event retain an attacker better than unrelated ones. This question becomes pressing as autonomous LLM-driven offensive agents emerge as realistic adversaries. This paper proposes narrative deception, a reactive strategy in which the defender maps each observed attacker command to a MITRE ATT&CK technique, selects a compatible scenario from a curated catalogue based on MITRE Engage, and deploys mutually referential artefacts (files, processes, services, and logs) on an emulated Ubuntu host while the intrusion is under way. An LLM-powered defender and an autonomous LLM attacker interact through a real SSH session, and the attacker's termination policy distinguishes abandonment due to suspected deception from abandonment due to loss of interest. A campaign of 1,150 sessions compares four conditions of increasing sophistication (Static, Same-TTP, Multi-TTP, and Chain) across four open-weight attacker models, four defender models, and three attacker skill levels. Engagement increases significantly at every step. With the same artefact budget per reaction, coherent scenarios raise the median session length of advanced attackers from 40 to 165 commands and reduce their abandonment from 86% to 52%. The effect grows with attacker skill, holds across all sixteen model pairs, and comes at comparable inference cost. Nearly all sessions ended through loss of interest rather than detection, which suggests that deception should sustain meaningful findings, not only emulator fidelity.

cs.CR · cs.AI

新论文 · v1arXiv:2611.22583

Evolution Under Fire: Evolving Agent Safety Harnesses with Adaptive Injection Stressors

Yujun Wang, Yilun Liu, Jinhe Bi, Krishna Kanth Nakka, Xuebing Zhou, Hinrich Sch{ü}tze, Yunpu Ma

原文摘要

Tool-using language-model agents must act on information from untrusted emails, webpages, and documents. This creates a central security challenge: malicious instructions and legitimate task directives can arrive through the same interaction channel. Existing defenses are largely hand-designed and static, making further improvements dependent on repeated manual redesign. We introduce Evolution Under Fire, a staged framework that couples safety-harness evolution with adaptive stressor evolution. Utility-constrained, Pareto-scheduled tree search evolves complete executable safety harnesses from execution evidence while keeping the task model, benchmark, tools, and evaluator fixed. Adaptive stressor evolution then discovers utility-preserving attacks that guide a subsequent stage of harness evolution. On AgentDyn with GPT-4o-mini, an evolved harness reduces attack success from 50.4% to 3.0%, improves clean and attacked utility over the initial harness, and offers a stronger security-utility trade-off than reproduced defenses. On Agent-SafetyBench with Qwen2.5-7B-Instruct, harness evolution reduces attack success from 82.6% to 62.0% while retaining helpfulness and runtime validity. Evolved harnesses also transfer without further evolution to Qwen3.5-35B-A3B, reducing attack success from 32.1% to 0.9% while improving attacked-task utility.

cs.CR · cs.AI · cs.CL

新论文 · v1arXiv:2611.22575

Do LLMs Understand Network Traces? A Comparative Study of Reasoning over Raw and Filtered Traffic Data

Irene Gosálvez-White, Roberto Magán-Carrión, Carlota de la Vega-Soriano, Pedro García-Teodoro

原文摘要

The effective delivery and monitoring of ICT services rely heavily on network traffic analysis. However, interpreting complex packet captures remains a challenging task that requires substantial technical expertise. Large language models (LLMs) offer promising opportunities to automate network traffic in- vestigation, yet their reliability in packet-level field extraction and flow-level sequence reconstruction remains an open research question. This study proposes a reproducible, question-answering- based evaluation methodology to assess the capabilities of LLMs in network trace analysis. Using real-world benign traffic from the CICIDS2017 dataset, we evaluate multiple models against a human-generated ground truth, comparing their performance on raw textual traffic dumps and protocol-filtered representations. Model responses are assessed through an automated LLM- as-a-judge pipeline, validated against human evaluations. The results demonstrate that protocol filtering significantly reduces prompt overhead while improving answer accuracy by reducing incorrect responses. These findings highlight the importance of protocol-aware traffic filtering as an effective optimization for improving the efficiency and reliability of LLM-assisted network management.

cs.NI · cs.AI

新论文 · v1arXiv:2611.23347

SurgCBVR: A Multi-Domain Benchmark for Content-Based Surgical Video-to-Video Retrieval

Mohammad Eslami, Mousa Moradi, Negin Ghamsarian, Nazlee Zebardast, Jennifer L Lindsey, Sophia Y. Wang, Lucia Sobrin, Rishi P Singh 等 9 位作者

原文摘要

Hospitals record thousands of hours of surgical video annually, yet these archives remain difficult to search by content. Surgeons cannot readily retrieve similar operations, complications, or workflow events. Existing surgical computer vision primarily produces labels rather than retrieving relevant videos. We introduce SurgCBVR, the first benchmark for content-based video-to-video retrieval in surgery. It integrates eight public datasets across four domains-ophthalmic, laparoscopic, robotic-assisted, and colonoscopy-covering six procedure types, 679 cases, and 76,489 clips (106 hours). SurgCBVR comprises two tiers: Scene, retrieving the same operative state across cases and sites, and Workflow, retrieving and localizing phase transitions and deviations. Scene includes 74,765 clips spanning 40 classes, three temporal granularities, and three playback speeds; Workflow contains 1,724 transition clips. Fixed clip lengths and frame counts, together with phase-classifier oracle and duration-only baselines, help assess label and timing shortcuts. We evaluate six generic and surgical foundation models, two video retrieval methods, and contrastive heads trained on SurgCBVR, using within-dataset, cross-dataset, and pooled-gallery retrieval restricted to the same procedure type. Frozen representations barely outperform a timing-only baseline, transition retrieval approaches chance, and trained heads lose up to half their accuracy across datasets. These findings expose substantial limitations in current video representations and establish SurgCBVR as a benchmark for advancing surgery-aware retrieval.

eess.IV · cs.AI

版本更新 · v2arXiv:2610.24133

A Conditional No-Hair Theorem for Transformers: How Language Models Forget Their Prompt

Shuyang Xiang

原文摘要

A black hole retains only a few conserved charges of the matter it formed from. We are inspired to make the analogy and we ask how much an autoregressive transformer retains of its prompt after generating $t$ tokens. For two prompts followed by the same continuation, the difference of their hidden states decays approximately as a power law $t^{-α}$, where $α=1$ is the rate at which a fixed prompt's share of uniform attention shrinks. Beyond the first layers, trained models forget faster ($α\approx0.55$--$0.7$) than untrained ones of the same architecture ($α\approx0.2$--$0.5$). For finite-depth pre-LN softmax transformers with bounded attention logits and non-degenerate pre-norm activations, we prove that this offset is $O\big(P(\log t)^{L-1}/t\big)$ for prompt length $P$ and depth $L$: the prompt's direct influence is diluted as the context grows, and \emph{relay} through continuation tokens adds only logarithmic factors. Conditional on the generated text, the prompt's influence on the next token thus vanishes. The bound fixes only the asymptotic shape and is uninformative at the lengths we measure in trained networks; an exactly solvable linear relay model shows that it cannot be improved and accounts for the untrained curves. Cancelling the dilution with a logit bias on the prompt stops the decay early in training, and training suppresses relay by about one billion tokens, before attention sinks form. A toolkit that measures $α$ for any Hugging Face causal language model is publicly available.

cs.AI

新论文 · v1arXiv:2611.22543

JointGV: Structure-Aware Correction of Visual World Models with Parallel Graph Dynamics for Long-Horizon Modeling

Tian Lyu, Yichen Jiang, Ziyuan Cheng, Yunda Yan, Xiangyu Pan, Junjie Jiang, Jialin Yu, Boyu Ning 等 10 位作者

原文摘要

Visual world models predict future visual states conditioned on actions, but recursive errors in entity poses and spatial relations limit their long-horizon prediction for robot planning and control. We ask whether a separately predicted relational state can correct this drift without restructuring the visual model. This is challenging because graph nodes and visual states share neither elements nor a feature space. We propose Joint Graph--Visual Dynamics Correction (JointGV), a plug-in based on a cross-granularity dynamics hypothesis: despite their different representations, graph-node and visual-state changes describe the same physical transition. JointGV rolls out a task-conditioned scene graph alongside the visual world model, couples their predicted changes, and combines the resulting graph-motion context with graph-predicted node positions to compute a bounded residual. Graph-learning and correction gradients do not propagate into the original visual dynamics. We attach JointGV to DINO-WM (spatial tokens) and DreamerV3 (a global latent state), evaluating both on DMC Cheetah Run and Walker Walk across three seeds and extending the evaluation to contact-rich manipulation with DMC Finger Turn Hard. Across 32-step rollouts, JointGV improves structural and visual-prediction accuracy, reducing joint-position error by 11--28\%. For spatial tokens, learned graph--visual change coupling gives lower error than broadcasting the same mean graph-motion context to every token, particularly when non-adjacent parts appear close together in the image. On real-robot inverted-pendulum sequences, JointGV reduces DINO-WM's 32-step pole-angle error from $12.56^\circ$ to $6.69^\circ$ and improves DreamerV3 and LeWorldModel as well. In simulated inverted-pendulum control, an actor trained with JointGV-corrected rollouts completes 46 of 50 episodes, compared with none using the original rollouts.

cs.RO · cs.AI · cs.CV

新论文 · v1arXiv:2611.22541

From Perception to Simulation: Unveiling and Empowering Mental Spatial Dynamics in MLLMs

Jiachun Li, Zhuoran Jin, Kang Liu, Jun Zhao

原文摘要

Spatial reasoning is a fundamental component of world understanding for Multimodal Large Language Models (MLLMs). While existing research has advanced the perception of spatial relations in static scenes, the domain of dynamic spatial simulation remains relatively unexplored. To bridge this gap, we introduce MentalGrid, a benchmark focused on spatial reasoning tasks that require models to simulate evolving spatial states without intermediate visual feedback. Extensive evaluation on our benchmark reveals a significant deficiency in the spatial simulation capabilities of existing models. Specifically, we find that performance is constrained by perceptual limitations in simple simulation scenarios and hindered by inadequate multi-step reasoning as complexity increases. To address these challenges, we propose a three-stage curriculum learning framework utilizing 16k specialized spatial reasoning samples. This approach yields SpatialWalker, which achieves a 33.8% average improvement over its base model, surpassing proprietary models like Gemini-3-Flash in spatial simulation. Furthermore, SpatialWalker demonstrates robust generalization, maintaining a 4.9% average gain on out-of-domain benchmarks, demonstrating the pivotal role of spatial simulation as a fundamental building block for broader spatial intelligence.

cs.CV · cs.AI · cs.CL

新论文 · v1arXiv:2611.22539

JET: Just-Enough Exploration Tuning for Efficient Tool-Calling Agents in Repository-Level Question Answering

Yoonho Choi, Taehyeon Han, Seonghyeon Lee

原文摘要

In repository-level question answering (QA), an agent explores a code repository with tools and should answer a question once enough information is gathered. Nevertheless, we find that LLM agents often continue to invoke tools even after the gathered information is already sufficient to answer. We call this phenomenon over-exploration. Moreover, even though existing methods improve task performance through supervised fine-tuning (SFT) on expert trajectories, SFT also propagates the over-exploration in the trajectories to the agent. To mitigate over-exploration, we propose Just-Enough Exploration Tuning (JET), a fine-tuning method that trains the agent to answer once the gathered information is sufficient. JET truncates each training trajectory at the step where the gathered information becomes sufficient, inserts a rationale that explains why the agent can answer at that step, and fine-tunes the agent with a higher loss weight on the rationale. Experiments on two repository-level QA benchmarks with two open-weight 8B models demonstrate that JET reduces tool calls by 11 to 33% on self-generated trajectories while largely preserving the score. On expert trajectories, JET makes 18 to 28% fewer tool calls than SFT while retaining most of the score gain of SFT. In both cases, JET also lowers the inference cost.

cs.CL · cs.AI

新论文 · v1arXiv:2611.22537

Testing World Models on Actions They Have Never Seen: Held-Out Plans, Forecast Accuracy and Price Rules in Retail

Karthik Iyer

原文摘要

A world model is trusted to answer "what if": how its world responds to an action it has never seen. We give a test of that trust for any action-conditioned world model: actions held out of training by design and scored against a known answer; whether forecast accuracy predicts accuracy on those actions; and the same structure given to simpler models. We run it in retail, where the action is a price and promotion plan, across 2,853 fitted models. First, forecast accuracy is a fair guide between kinds of model (rank correlation with error on new plans 0.32 to 0.66) and a poor guide between versions of one world model: where merchants plan into high-demand weeks the link reverses, down to -0.69. Second, training the world model to learn the effect of actions (JEPA pretraining, a latent consistency check, adaptation at the plan date) leaves its error on new plans unchanged. Third, in generated worlds the recorded regular price and three price rules improve it. Given the same rules, a log-linear model is best when its curve can match the truth; in a world whose curve lies outside the rules, the world model with the rules is ahead of the log-linear model with the rules in 36 of 40 worlds, and does as well without its recurrent cell. On real data (Breakfast at the Frat, The Complete Journey and M5) the rules lower the world model's error on pure price cuts deeper than any it saw (0.63 to 0.56 on the Frat; 0.45 to 0.44, within chance, on The Complete Journey), but not on lasting price moves. Fourth, a small share of random test plans helps every model a little. In a generated dosing world, a stress test in a second domain, the first finding repeats, and the built-up drug level lowers the world model's error (2.86 to 1.91) though it still predicts only 0.12 to 0.32 of the true gain. The test carries to any domain where a world model is asked about actions outside its history.

cs.LG · cs.AI

版本更新 · v2arXiv:2506.11627

Evaluating and Mitigating Skin Color Bias in Skin Lesion Classificatio

Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos

原文摘要

Skin lesion classifiers may overlook performance disparity because of subtle skin tone variations by treating skin tone as a categorical attribute. This study proposes a method that represents skin tone as a continuous attribute and assigns individual weights to each sample based on its nonlinear relationship with classification performance. Evaluations on two dermatological datasets showed that fairness metrics were sensitive to skin-color categorization. The proposed method also demonstrated more stable fairness improvements than conventional categorical reweighting while generally preserving classification performance.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2611.15481

SkillEarth: Teaching General-Purpose Agents to Act on Earth via Skill Evolution

Haojun Tang, Wenda Zhao, Xiang Zhou, Qiwei Lin, Lida Huang, Yan Wang

原文摘要

Recently developed remote sensing (RS) agents execute real-world tasks with complex workflows through multi-step tool invocation. These agents, however, typically rely on predefined expertise or parameter updates. They thus require updating expert knowledge or retraining models whenever new tools, tasks, or execution patterns emerge, limiting their continual adaptability in dynamic Earth environments. In this work, we seek to equip general-purpose agents with RS tool-call knowledge that can be automatically extracted from demonstrated trajectories without expert intervention or parameter updates. Specifically, we propose SkillEarth, a self-evolving skill extraction method that externalizes RS tool-call knowledge as reusable, retrievable, and evolvable skill files and refines them through observation-grounded evolution. Unlike existing automatic skill extraction methods that rely on outcome-based reflection to refine skills holistically, SkillEarth grounds skill evolution in real tool-chain execution and combines dual-judge feedback with a grounded observation routing graph for precise component-level refinement. The resulting skills are generalizable, reliable, and transferable: they improve overall RS tool-call performance across three frontier LLMs and four open-source LLMs, are refined through real tool execution feedback, and support cross-model reuse without retraining. Experiments on OpenEarth-Bench and Earth-Bench demonstrate that SkillEarth achieves better tool selection, argument correctness, execution-order consistency, and task completion than existing RS agents and skill extraction methods.

cs.AI · cs.CV

新论文 · v1arXiv:2611.22532

DGF-Asym: Adaptive Peer Weighting for Collective Estimation under Noisy and Faulty Sensing

Mohammad Nomaan Husain, Tanja Katharina Kaiser

原文摘要

Collective estimation under unreliable sensing requires robots to adaptively balance personal observations and social information from peers. We propose DGF-Asym, a decentralized collective estimation method extending the DeGroot-Friedkin model with asymmetric peer weighting based on retrospective predictive performance. The method supports consensus formation without prior sensor-noise statistics or explicit fault models while keeping inter-robot communication asynchronous. We evaluate DGF-Asym in simulated collective navigation under noisy observations and time-varying sensor faults. Compared with three baselines, it produces more stable estimates and more reliably sustains the decision criterion, at the cost of longer decision times. However, overall performance depends on fault ratio, group size, and influence-threshold selection. Our results demonstrate the potential of adaptive peer weighting for stable model-free collective estimation under unreliable sensing.

cs.RO · cs.AI

新论文 · v1arXiv:2611.23345

BiMa-ECGSR: reconstructing the 12-lead ECG from reduced lead sets with bidirectional state-space models

Ugo Lomoio, Pierangelo Veltri, Pietro Hiram Guzzi

原文摘要

Wearables and monitors record few electrocardiogram (ECG) leads; most diagnostic tools assume 12 leads. BiMa-ECGSR reconstructs the 12-lead ECG from reduced lead sets with a bidirectional Mamba state-space encoder--decoder, as regression (BiMa-SR) or diffusion (DiBiMa-SR). Models were trained on PTB-XL for six input sets (I; II; I+II; I+II+V1; I+II+V2; I+II+V1+V4), see only the measured leads at inference, and were tested on the PTB-XL test fold (2,198 records) and two external cohorts (Georgia, 10,275 records; Chapman-Shaoxing/Ningbo, 43,559). From lead II alone, the pooled median Pearson correlation (PCC) over the 11 predicted leads was 0.914 on PTB-XL, against 0.784 for a least-squares linear filter (lead I: 0.906 against 0.789). As limb leads are exactly derivable from I and II, multi-lead inputs were compared on predicted chest leads: 0.939 against 0.849 for I+II and 0.979 against 0.962 for I+II+V1+V4. BiMa-SR exceeded the linear comparator in all 18 configuration--cohort pairs (by 0.012--0.136), a margin that shrank as chest leads were added. From lead II, regression was more accurate than diffusion (DiBiMa-SR: 0.903 one-step, 0.862 with six DDIM steps). A 12-lead classifier trained only on real ECGs reached a superclass macro AUROC of 0.912 on real PTB-XL ECGs, 0.843 on reconstructions from lead II and 0.908 from I+II+V1+V4; externally, reconstructions from three or four leads scored within 0.004 of real ECGs. BiMa-SR (2.68\,M parameters) takes 45.8 ms per 10-s record on a GPU. Reconstruction makes reduced-lead recordings usable by 12-lead tools; it cannot add information absent from the measured leads.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22525

When Agent Skills Go Stale: Runtime Behavior and Selective Maintenance in Evolving Environments

Ömer Faruk Akgül, Shuli Jiang, Yuting Zhang, Yi Zhang, Xiaohan Fei, Wei Xia, Stefano Soatto

原文摘要

Agent skills use past experience and current observations to guide decisions and actions on related tasks. This experience is retained in skill state, whose reuse can amortize inference-time reasoning and environment interaction. When environment changes, parts of this state can become outdated while others remain useful. Across four task settings and two models, we compare skill reuse before and after environment changes. Previously beneficial skills can reduce task performance by over 10 percentage points or increase execution cost by nearly 40% relative to no skill. Task success can also remain unchanged while execution savings decline. These effects depend on which environment-specific details become outdated and the agent's ability to compensate using current observations. We introduce selective maintenance, which replays checks from successful executions without additional model calls. It verifies whether observed differences conflict with skill state, repairs affected content, and validates updates, rebuilding when local repair is insufficient. No description of the change is supplied. Relative to reusing stale state, maintenance improves task accuracy by up to 67pp and reduces execution steps by up to 37%. These results suggest that preserving a skill's inference time value as environments evolve requires selectively maintaining its state.

cs.AI · cs.CL

版本更新 · v2arXiv:2611.06518

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou, Dengyang Jiang, Zeyue Tian, Xuanhua He, Ryan Xu 等 22 位作者

原文摘要

Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target. Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking, while RLHF is difficult to scale and subject to individual aesthetic differences that complicate the calibration of facial, body motion, and chromatic cues across narrative contexts. We introduce EmoReward, a new self-evolving training mechanism that distills evidence reliability from reward traces collected during an actual training run to adaptively guide multi-reward weight allocation in subsequent training by determining which emotional evidence to trust and how much to weight it. EmoReward first plans specific grounding cues from the emotional prompt to guide evaluation, then uses heterogeneous signal primitives to score the generated video during the act stage. Reflective Reward Gating calibrates their contributions through instance-level gates for phase, face confidence, conflict, and subtlety, then renormalizes weights over the active set to produce the sample's fused reward. RewardMemory then estimates each primitive's reliability from rollout scores and outcomes within each emotional regime in the finished training run, then fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models. Experiments on HunyuanVideo 1.5 show improvements across multiple RL algorithms and compare EmoReward with other agentic reward methods under SAGE-GRPO. Ablations and transfer experiments on SD 3.5 and FLUX further support adaptive reward calibration for visual generation.

cs.CV · cs.AI