跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 14:51 · 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 2026-11-21 16:31 — 2026-11-22 16:31(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:2026-11-22 14:51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 49 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 14:49(北京时间)
新论文 · v1arXiv:2611.26094

Phantom of the Masquerade: Graph Neural Network-Based Detection of Masquerade Attacks in Controller Area Networks

Nehal Ameen, Pablo Moriano, Irfan Ahmed

原文摘要

The lack of built-in security in controller area networks (CANs) exposes modern vehicles and industrial systems to masquerade attacks that can compromise safety and reliability. These attacks inject malicious messages that mimic legitimate communication patterns, making them difficult to detect using existing intrusion detection systems (IDS). Prior graph-based IDS approaches often rely on shallow embeddings that decouple representation learning from classification, which may limit their ability to fully exploit structural and signal-level information. In this paper, we propose PhantoMasq, a graph neural network (GNN)-based framework for detecting masquerade attacks in CAN systems. PhantoMasq models CAN traffic as message sequence graphs enriched with lightweight statistical features derived from signal behavior, enabling joint learning of structural dependencies and temporal characteristics. The detection task is formulated as a graph-level classification problem and solved using graph convolutional networks (GCNs). We evaluate PhantoMasq on the ROAD dataset under a protocol that prevents overlapping windows from spanning training and test data. Across five masquerade attack types, PhantoMasq achieves mean AUC-ROC between 0.831 and 0.999, with performance depending on the transmission rate of the targeted identifier and the magnitude of the induced signal deviation. Against a state-of-the-art graph-embedding baseline evaluated on the same sliding-window configurations, PhantoMasq achieves higher AUC-ROC on all five attack types, by 0.13 to 0.36, and is less sensitive to window configuration. Window-processing latency ranges from 2.33 to 5.94 ms per window on CPU, corresponding to a throughput of 168 to 429 windows per second. We make our implementation and experimental artifacts available to support reproducibility.

cs.CR · cs.LG

版本更新 · v2arXiv:2506.18941

A Quasi-experimental Study of Conversational AI-supported Engagement in Large CS Courses

Neha Rani, Sharan Majumder, Ishan Bhardwaj, Pedro Guillermo Feijoo Garcia

原文摘要

Lucrative career prospects and creative opportunities often attract students to enroll in computer science courses, resulting in large class sizes. A common challenge in large classrooms is the lack of engagement between students and both the instructor and the learning material. Recent advances in Large Language Models (LLMs) present an opportunity to leverage Conversational Artificial Intelligence (CAI) to address this challenge. To examine the potential of CAI to support engagement with learning material, we designed an in class activity in a large Software Engineering course in which students interacted with a CAI tool. Using a quasi-experimental, within-subject study design in a real classroom at a large public United States University. We compared student engagement during an activity that involved the use of CAI for discussion with an activity that did not (peer discussion). For our analysis, we collected data on students interactions with the CAI tool and their self-reported responses on multiple engagement scales. Results show higher student engagement with the learning material in the activity involving CAI discussion as opposed to without (peer discussion). Higher self-reported learning was also observed in the activity with CAI as compared to without. Students also reported significantly more usefulness for learning in the CAI condition. Overall, our results indicate that CAI (ChatGPT) has the potential to support engagement with learning content during in-class activities in large class sizes.

cs.CY · cs.AI · cs.ET · cs.HC

新论文 · v1arXiv:2611.24284

CROMPT: Adapting CLIP via Cross-Modal Prompting for Robust Zero-Shot Generalization under Adverse Weather

Aniruddh Sikdar, Arya Kishor, Snehashis Dhibar, Suresh Sundaram

原文摘要

Domain adaptation for semantic segmentation is challenging when target-domain images are unavailable during training. Zero-shot domain adaptation addresses this by adapting models using only textual descriptions of the target domain. However, existing prompt-learning methods are not well suited for ResNet-based CLIP vision backbones or pixel-level cross-modal feature alignment. We propose CROMPT, a prompt-learning framework for zero-shot domain adaptation in semantic segmentation. CROMPT introduces Cross-Modal Feature Augmentation (CROMA), combining Random Visual Prompting with Hybrid Textual Prompting (HTP) to jointly adapt visual and textual representations. We further propose CROMA-VL, which leverages vision-language models to generate domain-conditioned prompts, and a progressive easy-to-hard adaptation strategy for improved domain invariance. Experiments on two benchmark datasets demonstrate consistent improvements over strong baselines and state-of-the-art methods, achieving 1.63-2.63% mIoU gains while maintaining inference-time complexity. These results establish CROMPT as an effective and efficient framework for zero-shot multi-domain semantic segmentation. OpenReview: https://openreview.net/forum?id=FxqFsIL685

cs.CV

新论文 · v1arXiv:2611.23991

SIRAZ: Sparse Inter-Layer Residual Aggregation for Zero-Shot Visual Neural Decoding

Neha, Mudasir Ganaie

原文摘要

Brain-computer interfaces aim to establish direct communication between neural activity and external systems, making interpretation of brain signals an important problem. In this context, neural visual decoding seeks to infer visual information from neural activity by learning a mapping between brain responses and the corresponding visual stimuli. It investigates how visual information emerges from neural signals and relates to perceptual processing while enabling the reconstruction or retrieval of visual stimuli from neural signals. Our brain primarily follows a hierarchical pathway to process visual information captured by the eye. However, neural representations learned by existing methods differ fundamentally from those produced by the biological visual system. To bridge this gap and mimic the human vision hierarchy, we introduce Sparse Inter-layer Residual Aggregation for Zero-shot (SIRAZ). SIRAZ is a framework that aligns neural visual representations by jointly modeling early visual processes via fovea- and magnocellular-pathway-inspired Difference-of-Gaussians transformations. To align the semantic information with neural information, it extracts multiple intermediate representations of the image at multiple depths and passes them through the Residual Gated Adapter Mechanism. To study the temporal dynamics of neural signals, the Direction-aware Multi-Scale Temporal Attention Encoder is introduced to align the learned neural representation with the final visual representation. The proposed framework achieves 92.5% top-1 and 99.27% top-5 accuracy in the intra-subject setting on the THINGS-EEG dataset, and 50.25% and 75% top-1 and top-5 accuracy in the THINGS-MEG dataset. The results indicate that combining biologically motivated visual representations with the structured modalities of neural dynamics improves cross-modal alignment and zero-shot image retrieval.

cs.CV

版本更新 · v2arXiv:2605.22169

Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning

Vipul Arya, S. H. Shabbeer Basha, Srikrishna U N, Sunainha Vijay, Snehasis Mukherjee

原文摘要

Deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have achieved state-of-the-art performance on various computer vision tasks such as object classification, detection, segmentation, generation, and more. However, these models are data-hungry as they require more training data to learn millions or billions of parameters. Especially for supervised learning tasks, curating a large number of labeled samples for model training is an expensive and time-consuming task. Active Learning (AL) has been used to address this problem for many years. Existing active learning methods aim to choose the samples for annotation from a pool of unlabeled samples that are either diverse or uncertain. Choosing such samples may hinder the model's performance as we pool based on one dimension, i.e., either diverse or uncertain. In this paper, we propose four novel hybrid sampling methods for pooling both easy and hard samples, which are also diverse. To verify the efficacy of the proposed methods, extensive experiments are conducted using high- and low-confidence samples separately. We observe from our experiments that the proposed hybrid sampling method, Least Confident and Diverse (LCD), consistently performs better than state-of-the-art methods. It is observed that selecting uncertain and diverse instances helps the model learn more distinct features. The code related to this study will be available at https://github.com/vipularya135/LCD.

cs.CV

版本更新 · v2arXiv:2606.12563

Arbor: How Search Policy Shapes Agent Behavior in System Optimization

Neha Prakriya, Chaojun Hou, Zheng Gong, Huasha Zhao, Yanyuan Qin, Chris Cai, Xi Zhao, Zhenyu Gu 等 9 位作者

原文摘要

Achieving peak performance on modern accelerators requires coordinated optimization across kernels, operator fusion, KV-cache management, quantization, scheduling, and communication overlap, a process that demands weeks of expert effort per model and hardware platform. We present Arbor, a system that gives autonomous agents an explicit optimization tree to reason over, backtrack through, and deepen with experience, with pluggable search policies, scored bandit traversal, parallel agent swarms, and depth-first sweep, sharing a common harness of containerized isolation, automatic rollback, and end-to-end validation. Arbor generalizes across domains: +40% to +193% on six production inference models across two GPU generations, +42.8% on LLM training, and +41% on recommendation training, where agents autonomously wrote kernel-level and framework-level optimizations spanning thousands of lines of code. In controlled ablations where every search policy receives the same agent, tree, and tools, we find that search structure shapes both the magnitude and the nature of the optimizations. The bandit achieves +30.1% through targeted framework fixes, the sweep +26.4% through deep kernel rewrites, and the swarm +33.4% by compounding independent changes. An agent-driven loop that receives the same harness, tools, and information, but selects its own targets reaches +14%, writing 4x more code per percentage point of improvement than Arbor's structured search policies. We additionally introduce an evaluation framework for autonomous loop-based agents spanning efficiency, grounding, robustness, and depth, designed to characterize agent search behavior across long-running optimization campaigns.

cs.AI

新论文 · v1arXiv:2611.23075

Exploring Students' Insights on Creating Videos to Learn Software Design and Engineering

Pedro G. Feijóo-García, John D. Centner, Lucas G. Zangari, Chase G. Wrenn, Neha Rani, Juan S. Sánchez-Gómez, Olufisayo Omojokun

原文摘要

This research-to-practice study examines the use of student-created instructional videos as an active learning strategy in a large undergraduate Software Design and Engineering (SWE) course. Supporting engagement and understanding in large-scale computer science (CS) courses remains a challenge, as instruction often relies on automated activities and summative assessments that prioritize grading over meaningful learning. This can make the learning experience feel impersonal, leading to frustration, anxiety, and confusion, especially when students face complex topics or new programming tools. To address these issues, we implemented a learner-centered strategy grounded in the principle of ``learning by teaching," where students created instructional videos to explain course concepts in their own words. This approach allowed students to take ownership of their learning, adapting the material to fit their individual perspectives and reinforcing their understanding through explanation. We report on students' reflections from a large introductory SWE course (over 700 students), analyzing their open-ended feedback on the benefits and drawbacks of the strategy. Students highlighted increased engagement and learning, and many appreciated the flexibility of the video-based format compared to traditional multiple-choice exams, which they found more restrictive. However, students also noted that the video creation process was time-consuming. This study contributes to the growing conversation on active learning in computing and engineering education by showcasing the potential of student-created instructional videos to enhance student agency, motivation, and conceptual understanding in large-scale learning environments.

cs.CY

新论文 · v1arXiv:2611.23346

Securing and Auditing Long-Horizon LLM Agents: State-Transfer Auditing and Controls in the Agent Harness

Deep Shah, Nehal Kathrotia

原文摘要

Long-horizon LLM agents across codebases, web browsers, and enterprise infrastructure rely on an execution harness to move state between the working context, session history, persistent memory, and external environment. While conventional execution traces log model prompts and tool calls, critical security and reliability failures occur during state transfers: a transfer can admit unchecked content (indirect prompt injections, unverified memory writes), rewrite state lossily (context compaction dropping user constraints, memory consolidation stripping source authority), or restore state incompletely (workspace rollbacks leaving aborted KV state active on the inference server). Because current traces omit what crosses these boundaries, failure attribution and runtime monitors fail on multi-step trajectories. We present a state-transfer audit architecture for the agent harness. At each transfer boundary, we define an audit point specifying the minimal hash-chained record the harness emits, separating low-overhead deterministic checks from model-based semantic checks and binding internal context, memory, and inference-server cache state to external actions. We show that the same transfer records required for causal failure attribution supply the durable state needed by runtime security controls, including least-privilege capabilities, replay-resistant authorization outside the prompt, information flow control, obligation monitors, and transactional recovery across multi-agent and infrastructure pipelines. Finally, we analyze multimodal GUI adaptations and implement and evaluate a reference harness middleware across 240 multi-step fault-injection trajectories, showing that transfer records localize root causes and catch cross-transfer violations missed by lifecycle and tool-only logs at microsecond deterministic overhead.

cs.CR

新论文 · v1arXiv:2611.22299

Harnesses That Improve Themselves: A Unifying Framework for Self-Improving Agent Harnesses

Deep Shah, Nehal Kathrotia

原文摘要

Whether a foundation model succeeds as an autonomous agent depends as much on its runtime software as on its weights. This runtime, the agent harness, manages context and memory, steers multi-turn control, executes tool actions in sandboxes, and verifies work before stopping. Because models differ in how they use tools and how they fail, a static harness tuned for one model or task often stalls, wastes tokens, or regresses on another. This bottleneck has driven a shift from prompt tuning to self-improving agent harnesses: systems that inspect their own execution traces, separate runtime bugs from model limits, and rewrite their own code. We present a unifying architectural and design framework for self-improving agent harnesses. The framework pairs four editable runtime components (context and state, agent control, action interfaces, and verification and recovery) with a four-stage loop that diagnoses failures, proposes code patches, validates candidates, and deploys updates. Using this framework, we show how optimizers trace errors across long trajectories and discover reusable runtime mechanisms such as pre-stop verifiers, loop breakers, and persistent memory. We further show why full-harness rewrites overfit or break across modules, and how modular updates with validation gates generalize across models while bounding token cost. To keep self-modification safe, we establish practical defenses against recurring failure modes including prompt bloat, benchmark gaming, and evaluator tampering. Finally, experiments on SWE-bench Lite validate this framework, showing that gated modular evolution outperforms prompt reflection and full-harness rewrites across models and repositories at a fraction of the token cost.

cs.AI

版本更新 · v3arXiv:2604.00024

WHBench: Evaluating Frontier LLMs with Expert-in-the-Loop Validation on Women's Health Topics

Sneha Maurya, Spandana Govindgari, Girish Kumar

原文摘要

Large language models are increasingly used for medical guidance, but women's health remains under-evaluated in benchmark design. We present the Women's Health Benchmark (WHBench), a targeted evaluation suite of 47 expert-crafted scenarios across 10 women's health topics, designed to expose clinically meaningful failure modes including outdated guidelines, unsafe omissions, dosing errors, and equity-related blind spots. We evaluate 22 models using a 23-criterion rubric spanning clinical accuracy, completeness, safety, communication quality, instruction following, equity, uncertainty handling, and guideline adherence, with safety-weighted penalties and server-side score recalculation. Across 3,102 attempted responses (3,100 scored), no model mean performance exceeds 75 percent; the best model reaches 72.1 percent. Even top models show low fully correct rates and substantial variation in harm rates. Inter-rater reliability is moderate at the response label level but high for model ranking, supporting WHBench utility for comparative system evaluation while highlighting the need for expert oversight in clinical deployment. WHBench provides a public, failure-mode-aware benchmark to track safer and more equitable progress in womens health AI.

cs.CL · cs.AI · cs.CY

版本更新 · v2arXiv:2602.00092

通过宪法解释与控制模型行为:基于原子概念编辑

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

Neha Kalibhat, Zi Wang, Prasoon Bajpai, Drew Proud, Wenjun Zeng, Been Kim, Mani Malek

AI 速读 基于摘要

提出一种黑盒可解释性框架,通过原子概念编辑学习可验证的自然语言“宪法”,以解释和控制模型在多种任务中的行为。

cs.LG · cs.AI · cs.CL · cs.CV

查看原文摘要

We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior, such as its alignment, correctness, or adherence to constraints. Our method leverages atomic concept edits (ACEs), which are targeted operations that add, remove, or replace an interpretable concept in the input prompt. By systematically applying ACEs and observing the resulting effects on model behavior across various tasks, our framework learns a causal mapping from edits to predictable outcomes. This learned constitution provides deep, generalizable insights into the model. Empirically, we validate our approach across diverse tasks, including mathematical reasoning and text-to-image alignment, for controlling and understanding model behavior. We found that for text-to-image generation, GPT-Image tends to focus on grammatical adherence, while Imagen 4 prioritizes atmospheric coherence. In mathematical reasoning, distractor variables confuse GPT-5 but leave Gemini 2.5 models and o4-mini largely unaffected. Moreover, our results show that the learned constitutions are highly effective for controlling model behavior, achieving an average of 1.86 times boost in success rate over methods that do not use constitutions. Our open-sourced code can be found at https://github.com/google-deepmind/atomic_concept_edits

版本更新 · v4arXiv:2604.05164

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents

Neharika Jali, Anupam Nayak, Gauri Joshi

原文摘要

As LLM reasoning performance plateaus, improving inference-time compute efficiency is crucial to mitigate overthinking and long thinking traces even for simple queries. Prior approaches including length regularization, adaptive routing and difficulty-based budget allocation primarily focus on single-turn settings and fail to address the sequential dependencies inherent in multi-turn reasoning. We formulate multi-turn reasoning as a sequential compute allocation problem and model it as a multi-objective Markov Decision Process. We propose TAB: Turn-Adaptive Budgets, a budget allocation policy that takes as input the conversation history and learns to maximize task accuracy while respecting global per-problem token constraints, and consequently learns to adaptively allot smaller budgets to easier turns and save an appropriate number of tokens for the crucial harder reasoning steps. We train and analyze the behavior of TAB on an auxiliary hierarchical plan-and-execute system for multi-turn math reasoning where solution trajectories are inexpensive to collect. Here, TAB saves up to 35% tokens and 30% latency over static and off-the-shelf LLM budget baselines. We then transfer the same TAB policy to environment-grounded agentic workflows spanning sequential tool-use, simulated user-agent dialogue and multi-step terminal tasks, where it generalizes and maintains accuracy while saving up to 20% tokens and 15% latency, without ever being trained on them.

cs.LG · cs.AI

新论文 · v1arXiv:2611.19823

EfficientSkill: Learning Skills for Token-Efficient Multi-Turn Agents

Deep Shah, Sanket Badhe, Nehal Kathrotia, Priyanka Tiwari

原文摘要

Reflective skill optimizers improve multi-turn LLM agents by revising instructions from failed and successful rollouts, yet accumulating edge-case rules bloats prompts, inflates token use, and pushes agents into long, error-prone loops. We introduce EfficientSkill, a two-step framework that first discovers a reliable skill without token penalties, and then warm-starts accuracy-guarded pruning from that skill to compress instructions, bound agent turns, and offload reusable code into workspace utilities with zero implementation prompt cost. Across four frontier, mid-tier, and open-weight models on MATH-500, ALFWorld, and SpreadsheetBench, EfficientSkill cuts output tokens over unconstrained EvoSkill on 11 of 12 configurations (by up to 80%) while raising mean accuracy on every benchmark, including +14.3 and +17.5 percentage-point gains on SpreadsheetBench with Gemini 3.8 Flash and Grok 4.1 Fast by replacing stalled loops with compact workflows. By shrinking both generated tokens and replayed history, EfficientSkill lowers total token usage and serving cost across every evaluated configuration, with or without full-prefix KV caching.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.19764

Compositional Exploits in Autonomous Coding Agents: Attack Mechanics and Ephemeral Defense

Deep Shah, Nehal Kathrotia

原文摘要

Autonomous coding agents (such as Antigravity, Claude Code, Cursor, and OpenHands) rely on third-party tools to inspect files, run commands, and call external APIs. Today's security auditors evaluate these tools almost entirely in isolation: static linters and AST checkers verify that each individual tool contains no malicious code at installation time. In this paper, we show that isolated tool auditing is fundamentally flawed. We expose compositional exploits in autonomous coding agents, an emergent vulnerability class where an agent chains individually harmless tools to execute an unauthorized attack. Much like code-reuse attacks in binary exploitation, this threat requires no malware; instead, the agent stitches together legitimate tool operations across turns over shared workspace files, environment variables, and chat memory. Across a 560-task benchmark suite (360 exploit tasks across 8 hazard classes and 200 benign developer and cloud workflows), unprotected frontier models (Gemini 3.5, 3.7, and 3.8 Flash) execute compositional exploit chains with a 72.9% to 84.5% success rate, while five leading single-tool pre-distribution scanners exhibit a 0% detection rate across all constituent tools. To eliminate compositional exploits, we present CompGuard, an OS-grounded defense uniting two planes: (1) a Cognitive Control Plane that issues single-skill capability leases and tracks dataflow provenance, and (2) an OS Kernel Enforcement Layer using Linux Landlock LSM v4, seccomp-BPF socket filters, and an ephemeral loopback proxy to close the invocation gap. CompGuard achieves a 100% Defense Block Rate (0.0% to 0.8% pre-teardown Net ASR) at 61.4 microseconds interposition overhead, preserves a 98.0% solve rate on benign developer workflows, and triggers zero false alarms across 615 real cloud diagnostic calls.

cs.CR

新论文 · v1arXiv:2611.19343

OmitEHR: Scalable Omission Detection in LLM-Generated Clinical Summaries

Bridget Lin, Ryan Welch, Bobak Seddighzadeh, Fran Riley, Kaitlyn Stoehr, Margarita I. Pipinos, Dimitri Speron, Emma V. Sage 等 11 位作者

原文摘要

Health systems increasingly rely on large language models (LLMs) to draft summaries of patient medical records, yet evaluations now find omissions, the absence of clinically important information, to be the most common failure mode. Detecting omissions in an LLM-generated summary requires knowing which facts in the record are salient, a signal that existing methods hand-specify, ignore, or recompute at inference with costly LLM judges. We present OmitEHR, a reference-free omission detector that learns clinical salience from historical clinician-written summaries predating widespread LLM use. OmitEHR learns to predict which source-note sentences clinicians include in their summaries, then surfaces high-salience sentences not covered by an LLM-generated summary as candidate omissions. We apply OmitEHR to brief hospital course (BHC) summarization using 5,000 admissions from a large academic medical center. On held-out admissions, OmitEHR outperformed all evaluated baselines at predicting salient source sentences, including a prompted LLM judge. The full omission detection pipeline took 17.7 to 19.5 seconds and cost \$0.03 to \$0.13 per summary depending on the base model, 1.6 to 1.7 times faster and 5.6 to 6.7 times cheaper than scoring every source sentence with an LLM judge. In a blinded review of 25 admissions, two board-certified clinicians confirmed a mean of 5.6 clinically meaningful omissions per summary surfaced by OmitEHR, compared with 3.3 for a full LLM pipeline, counting candidates confirmed by at least one clinician. The efficiency and validity of OmitEHR make it a practical tool for health systems to flag omissions before a summary reaches the clinician.

cs.CL · cs.AI

新论文 · v1arXiv:2611.17564

AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI

Snehalkumar `Neil' S. Gaikwad, Dhruv Dixit, Bryen Alvarez, Pratik Patekar, Anika Sharma, Akshara Kolipaka, Paritosh Pandey

原文摘要

Governments are writing rules for artificial intelligence that decide what counts as an automated decision or a harm, often before the people they affect have a chance to question them. We introduce AI-Voyager, a public-interest system for human-AI civic reasoning, in which people and AI work together to understand, contest and shape the rules that govern AI. A resident can find their city's rules on AI in hiring or upload their country's AI strategy, read it as an affected worker would, open the passage behind any answer, and draft a revision. Its architecture turns 3,653 governance documents from city, state, federal and national governments into passages that keep their page and edition, and retrieves evidence through bounded agentic search that verifies each statement. On 360 new questions that require finding the relevant documents, it reached 83.0% macro recall, against 80.5% for the strongest baseline, 73.7% without iterative search and 99.1% on a benchmark with fixed documents. In a study with 24 participants new to two AI bills, most proposed changes asked how provisions would apply. Participants chose lenses for the kind of explanation they wanted, and citations signaled grounding but rarely led them to check the source. By binding AI assistance to the exact text of public documents, this work introduces a grammar of operations and a design space that inform how such systems are designed and evaluated, and how people take part in governing AI.

cs.AI · cs.CL · cs.HC

版本更新 · v2arXiv:2611.10224

Jais 3: Introducing Arabic-centric Agentic AI

Team IFM, Haonan Li, Hadi Abdine, Nikhil Ranjan, Mohamed Anwar, Ahmad Chamma, Amr Mohamed, Ahmed Frikha 等 54 位作者

原文摘要

We present Jais 3, a fleet of six open, Arabic-centric agentic language models ranging from 0.9B to 375B parameters. Jais 3 is built to complete tasks for Arabic speakers, not only to answer questions in plain text: it is trained to plan multi-step tasks, call tools and Model Context Protocol (MCP) servers, operate a terminal, search the web, and read, edit, and produce PDF, spreadsheet, and presentation files, while communicating with the user in Arabic. Instead of pretraining from scratch, we adapt each model of the fully open K2 Horizon fleet to Arabic through continual pretraining, followed by supervised fine-tuning (SFT), final token preference optimization (FTPO), and reinforcement learning with verifiable rewards (RLVR). We combine natural Arabic text with translated, transliterated, and synthetic Arabic, and replay the base model's own training data to keep its reasoning, agentic, and English abilities. Jais 3 covers Modern Standard Arabic and the major regional dialects, follows instructions with Arabic-specific constraints, and inherits the 512K-token context window of K2 Horizon (all models except the 0.9B). To our knowledge, its 375B model is the largest open Arabic-centric language model to date. For evaluation, we revisit how Arabic models are assessed, moving to fully generative evaluation on audited Arabic benchmarks. Across model sizes, Jais 3 matches or outperforms open-weight models of comparable size on Arabic and agentic benchmarks, with particularly strong agentic capabilities and Arabic instruction following, and far fewer hallucinations. We release the weights and the checkpoints from every training stage of all six models, together with samples of the training data, the data recipes and training configurations, the training logs, the audited benchmarks, and the evaluation code.

cs.CL · cs.AI

新论文 · v1arXiv:2611.16198

"We Are the Dirty Hands": Reimagining an Ambient Intelligence Care System with Professional Caregivers

Andrea Green, Jane L. E, Sneha Jain, Parker Ruth, Matthew Jörke, Sarah L. Billington, James Landay, Andrea Cuadra

原文摘要

While ambient assisted living (AAL) sensing systems offer promise for aging in place, their impacts on professional caregivers are overlooked. We conducted two collective speculation workshops (N=24) with personal health aides (PHAs, n=18) and certified nursing assistants (CNAs, n=6) to examine the ethical implications and value tensions of a care system with ambient intelligence (CSAI), our conceptualization of an AAL. Participants anticipated different implications across care roles and settings. PHAs anticipated additional responsibilities from CSAI, including learning how it operates and supporting older adults in its use. CNAs, who had greater access to workplace resources and protections, similarly noted that CSAI could create additional work. Participants also identified tensions around visibility, as sensing could support caregivers by documenting difficult working conditions while simultaneously making their behavior more vulnerable to misinterpretation. Through their modifications and surfaced discussions, we propose design guidelines for AAL systems, such as integrating context-aware sensing.

cs.HC

新论文 · v1arXiv:2611.16173

Between Niti and Nyaya: A Society-Centered Framework for AI Governance

Snehalkumar `Neil' S. Gaikwad, Punya Aragula, Shiva Kruthi Palpanoori, Pratik Patekar

原文摘要

Governments are making decisions about AI before they can measure its public effects, and those decisions determine whether a person can learn that AI influenced an outcome, challenge it, and see it corrected. Research has documented what AI governance produces: principles, strategies, registers, and audits. However, we lack shared language for understanding AI policy while it is still being made. We introduce the Society-Centered AI Governance Framework, which gives policymakers, researchers, and the public a way to assess instruments in any jurisdiction by whether a person can get notice, challenge a decision, and see it corrected. It reads a jurisdiction's instruments together by date and binding status, separates an agency duty from a right a person can invoke, and traces which later instrument must enforce each commitment. We evaluated it in North Carolina using interviews with nine AI Leadership Council members, conducted before and after the state's 2026 AI roadmap, and a provision-level reading, with human-reviewed model-assisted coding, of 49 AI governance documents from 19 states. For the state's own AI systems, we find visibility-first governance: visibility duties are in effect, notice exists as an agency duty with no right a person can invoke, and AI-specific challenge and correction remain advisory. The roadmap assigns owners and dates to the missing protections, so the gaps are documented but not yet closed. Recent federal preemption proposals focus on AI development, so recourse for a state's own systems is likely to remain a state decision. We identify "legitimacy before protection" as a testable risk of visibility-first governance and name the milestones that would test it. More broadly, judging AI policy by who can act on what it makes visible lets the field assess recourse while policy is still forming, before harm occurs.

cs.AI · cs.CY · cs.HC

版本更新 · v2arXiv:2611.13525

EJAI: Judgment-Preserving Civic AI for Data Center Environmental Justice

Evan Pačes-Wiles, Bryen Alvarez, Sara Gulabani, Akshara Kolipaka, Snehalkumar 'Neil' S. Gaikwad

原文摘要

Communities in the United States and around the world are contesting data centers, the physical infrastructure of AI. These disputes pose environmental justice issues: residents must weigh unevenly distributed burdens using evidence scattered across metrics, corporate claims, policy documents, and public testimony. A formative study with 10 users showed that dashboards and single-agent AI can settle questions before people examine that evidence. Here we present EJAI, a source-grounded system that links an interactive map, retrieved evidence, missing-data statements, and two stakeholder personas that allow people to inspect evidence and form their own policy recommendations. In a small functional benchmark of 21 queries, retrieved evidence supported 98.4% of factual claims and the system acknowledged missing evidence in 32 of 33 cases. Persona alignment carried a grounding cost: the Corporate Executive omitted some evidence that conflicted with its assigned priorities. In a within-subjects study, 15 participants acting as residents prepared for a simulated town hall. Some checked cited AI claims while treating map metrics as official, some made conditional recommendations with safeguards such as water-use disclosure, and some found the personas simplified or biased. Our results suggest that civic AI can support preparation for public reasoning when it makes evidence, gaps, and disagreement open to inspection, and that corpus imbalance and two-sided personas remain open justice concerns.

cs.HC · cs.CL · cs.CY

版本更新 · v3arXiv:2607.16769

图神经网络作为供应链优化元模型的潜力:数据集、架构与方向

On the Potential of Graph Neural Networks as Metamodels for Supply Chain Optimization: Dataset, Architectures, and Directions

Tushar Lone, Neha Karanjkar

AI 速读 基于摘要

该论文为供应链优化中的图神经网络代理模型奠定基础,构建公开数据集、探索节点级与网络级预测架构,并讨论梯度优化等研究方向。

cs.LG

查看原文摘要

Graph Neural Networks (GNNs) have emerged as a powerful, differentiable class of learning models for graph-structured systems. Their ability to generalize across topologies opens the prospect of a surrogate for combined structural and parametric optimization, which classical metamodels cannot offer. Supply chains are a natural target, yet the use of GNN surrogates for supply chain problems is largely unexplored. This paper lays the foundation, presents initial steps, and discusses key research directions. As a foundation, we formulate the problem and create a large public training dataset of programmatically generated supply chain graphs with input parameters and steady-state performance metrics obtained using our SupplyNetPy simulation library. As initial steps, we explore GNN architectures that work well as surrogates for node- and network-level predictions, and analyze their accuracy-compute trade-off against simulation. Most importantly, we outline the exciting directions this opens, namely gradient-based optimization over topology, fast design-space exploration, and sensitivity analysis.

版本更新 · v2arXiv:2607.09745

SupplyNetPy:用于任意供应链与库存网络高保真建模与仿真的开源 Python 库

SupplyNetPy: An Open-Source Python Library for High-Fidelity Modeling and Simulation of Arbitrary Supply Chain and Inventory Networks

Tushar Lone, Neha Karanjkar

AI 速读 基于摘要

作者介绍了一个开源 Python 库 SupplyNetPy,它支持任意多级供应链网络的离散事件仿真,并报告了与解析基准、商业工具和已发表案例的验证结果。

cs.AI · cs.LG

查看原文摘要

This paper introduces SupplyNetPy, an open-source, well-documented Python library for modeling and discrete-event simulation of supply chain networks with arbitrary multi-echelon structures. It supports multiple replenishment policies, perishable inventory, node disruptions, and stochastic demand and lead times. All components are extensible via inheritance. Users describe a supply chain as a graph with node and link attributes, while the library handles simulation, providing logs and extensive node and network level performance reports. This paper presents the motivation, design, key features, and architecture of SupplyNetPy, along with detailed validation results (against analytical benchmarks, a commercial tool, and a published case study). A key motivation behind SupplyNetPy's development is programmatic generation and simulation of complex models, enabling design-space exploration, what-if analysis, training data generation, and supply chain digital twins.

版本更新 · v3arXiv:2603.16861

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

Abhay Deshpande, Maya Guru, Rose Hendrix, Snehal Jauhri, Ainaz Eftekhar, Rohun Tripathi, Max Argus, Jordi Salvador 等 26 位作者

原文摘要

A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or task-specific fine-tuning to bridge the gap between simulated and physical environments. We challenge that assumption. With sufficiently large-scale and diverse simulated synthetic training data, we show that zero-shot transfer to the real world is not only possible, but effective for both static and mobile manipulation. We introduce MolmoBot-Engine, a fully open-source pipeline for procedural data generation across robots, tasks, and diverse simulated environments in MolmoSpaces. With it, we release MolmoBot-Data, a dataset of 1.7 million expert trajectories for articulated object manipulation and pick-and-place tasks. We train three policy classes: MolmoBot, a Molmo2-based multi-frame vision-language model with a flow-matching action head; MolmoBot-Pi0, which replicates the $π_0$ architecture to enable direct comparison; and MolmoBot-SPOC, a lightweight policy suitable for edge deployment and amenable to RL fine-tuning. We evaluate on two robotic platforms: the Franka FR3 for tabletop manipulation tasks and the Rainbow Robotics RB-Y1 mobile manipulator for door opening, drawer manipulation, cabinet interaction, and mobile pick-and-place. Without any real-world fine-tuning, our policies achieve zero-shot transfer to unseen objects and environments. On tabletop pick-and-place, MolmoBot achieves a success rate of 79.2% in real world evaluations across 4 settings, outperforming $π_{0.5}$ at 39.2%. Our results demonstrate that procedural environment generation combined with diverse articulated assets can produce robust manipulation policies that generalize broadly to the real world. Technical website: https://allenai.github.io/MolmoBot

cs.RO

新论文 · v1arXiv:2611.11684

Self-Indexing Latent Memories for Access-Aware Continual Instruction Tuning of LLMs

Dhruv Dixit, Paritosh Pandey, Snehalkumar 'Neil' S. Gaikwad

原文摘要

Continual instruction tuning often preserves old skills with task-private modules. Inference still requires selecting the right module from the prompt alone. We introduce Task-Isolated Latent Adapter Continual Training (TILA-CT), a replay-free method that makes each task module self-indexing. Each task receives a latent memory and adapter bank in a frozen LLM. During adaptation, the memory gathers causal-prefix information and injects task-conditioned context. For access, its persistent state provides the routing prototype used by a shared prompt-only router. On the 8-task CT-Pipeline stream, TILA-CT achieves 65.19 acquisition and 63.98 final macro score, with 1.38 points of average forgetting. A middle-reversed order gives 65.38 acquisition and 64.17 final macro score. Across 6 backbones, final scores remain within 1.5 points of acquisition. Ablations support memory-derived routing keys and causal gathering. Final macro routing accuracy is 93.9\%, and oracle routing recovers 1.21 final macro points. These results separate preserved task computation from learned access to it.

cs.AI

新论文 · v1arXiv:2611.12998

Linear Probes to Bayesian Manifolds: Geometry of Arithmetic in Large Language Models

Anshul Kumar, Neha Prasad, Manoj Kumar, Barnabás Póczos, Deeksha Varshney

原文摘要

Linear probes are a standard method to study geometric structures, such as helices and circles, from the activations of large language models (LLMs), and such structure is often taken as evidence that the model computes with it. Probe accuracy alone cannot establish this, because it conflates four separate claims. These are (1) that the concept is decodable from the activations, (2) that they form a specific shape, (3) that the shape belongs to the probed concept rather than to a related concept the model also represents, and (4) that the output of the model depends on the shape. We call these claims decodability, shape, ownership, and causal use, and we test them separately with a four-stage Bayesian pipeline. Stage 2 compares candidate shapes and selects the best one only when its evidence passes a predefined threshold. Stage 3 removes a set of related concepts, specified in advance, and tests whether the shape is owned or inherited. Stage 4 intervenes on the shape to test whether the output of the model depends on it. We apply the pipeline to two-digit addition and multiplication in GPT-J 6B, Llama 3.1 8B, and Pythia 6.9B. Nearly every concept is decodable, but the decoded directions overlap substantially across concepts. Every strongly supported comparison selects a ribbon, which is a helix whose radius changes with the value, or a torus. Of 1,330 cells with an ownership verdict, 19% of shapes are owned and 81% are inherited. Owned and inherited shapes move the output about equally often. Intervening on the shape retains approximately 61% of the effect of intervening on the full probe while using at most five dimensions, against a median of nine for the probe. Our results indicate that a probe verdict alone overstates what a model computes with, and we propose that probe results be reported as verdicts on all four claims rather than as a single accuracy.

cs.LG · cs.CL

版本更新 · v2arXiv:2610.02945

面向AI辅助数学发现的持续图记忆与社区基础设施

Continual Graph Memory and Community Infrastructure for AI-Assisted Mathematical Discovery

Eric Hanchen Jiang, Junyi Zhang, Jinxi Yu, Jiachen Lu, Zhi Zhang, Michael Simon, Justin Baker, Richard Cai 等 30 位作者

AI 速读 基于摘要

作者提出Ansatz研究框架与Ansatze社区平台,用持续图记忆区分模型接受的结论与人工整理探索,并支持数学研究的检查、引导与形式化验证。

cs.AI · cs.CL

查看原文摘要

Mathematical discovery requires preserving partial ideas and the evidence supporting their reuse. We present Ansatz, a research harness whose continual graph memory separates model-accepted claims and dependencies from curated exploration, and Ansatze, a community platform for inspecting, guiding and checking this work. On First Proof, Ansatz recorded nine local verifier closures in each of two ten-problem batches; a partial result in the Second Batch also counted as a pass under the study's criterion. These model-assessed outcomes include continued searches and differ from expert validation. Component studies and re-review expose disagreements and their dependency reach. Open-problem investigations produced candidate results, with five Lean formalizations reported. The platform connects problem discovery, research records, manuscript analysis and formal checking while preserving distinct evidence states. Together, these systems support cumulative human-AI research through persistent investigation and inspectable contributions.

新论文 · v1arXiv:2611.09529

PreForceVision: Physics-Guided Optical Estimation of Bolt Preload from Bolt-Head Deformation

Nehal Afifi, Klaus Rappenecker, Florian Peinhardt, Gerhard Kachel, Alfred Isele, Sven Matthiesen

原文摘要

Bolt preload is a decisive functional quantity in bolted joints because it determines whether external loads are transmitted primarily through frictional clamping or directly through the bolt. Existing preload measurement techniques, including strain-gauge bolts, force washers, ultrasonic methods, and bolt-length measurements, are effective in certain applications but require additional hardware, coupling, calibration, or joint modifications. This limits their scalability for large numbers of standard fasteners and motivates a non-contact optical approach. This paper proposes PreForceVision, a physics-guided optical framework for estimating bolt preload from preload-induced surface deformation of the bolt-head front face. The method treats preload estimation as an inverse deformation-to-force problem, where deformation of the optically accessible bolt-head surface is extracted from reference-loaded image pairs and related to the internal preload state. Preliminary results for an M16 strength class 8.8 bolt show an approximately \SI{12}{\micro\meter} simulated head-face depression at \SI{90}{\kilo\newton}, strain-gauge measurements of comparable magnitude, and an optical 3D measured central depression of approximately \SIrange{10}{20}{\micro\meter}. The contribution is a physics-guided optical methodology combining controlled image-pair acquisition, DIC- or optical-flow-based deformation extraction, multimodal validation, and uncertainty-aware regression for rough preload estimation under controlled conditions.

cs.AI

新论文 · v1arXiv:2611.09514

A Physics-Informed Learning Framework for Linking Microscopic Surface Degradation to Bolted Joint Functional Behavior

Nehal Afifi, Gerhard Kachel, Sven Matthiesen

原文摘要

Returned products in circular engineering often have heterogeneous degradation histories, making remaining function difficult to assess. For bolted joints, corrosion alters surface morphology, contact, friction, preload retention, and mechanical response. This paper presents a physics-informed multimodal framework for linking microscopic and camera-based degradation observations to functional indicators of corroded bolted joints. The workflow defines the corrosion failure mode, generates synchronized inspection and functional-response records, preprocesses image, roughness, exposure, and joint descriptors, aligns microscopy and camera observations through similarity learning, and constructs a calibrated corrosion-severity field. Partial differential equation (PDE) discovery is applied to this field to identify candidate effective mesoscale laws rather than complete electrochemical mechanisms. The corrosion-evolution model is coupled to a separate functional model, with friction coefficient as the primary target and preload loss included when clamp-force data are available. The contribution is a reproducible pathway for physically constrained assessment of degraded bolted-joint behavior.

cs.AI

版本更新 · v2arXiv:2606.05334

Uncertainty Aware Functional Behavior Prediction and Material Fatigue Assessment for Circular Factory

Nehal Afifi, Mehdi Khabou, Victor Mas, Jonas Hemmerich, Patric Grauberger, Stefan Dietrich, Volker Schulze, Sven Matthiesen

原文摘要

Returned products in circular factories re-enter production with heterogeneous degradation states, usage histories, and remaining capability. Reuse cannot be decided from the current inspection alone, because future function fulfillment and component integrity may evolve differently under the next service scenario. Existing PHM approaches support degradation prediction, but often target fixed operating conditions or isolated component benchmarks, while material-fatigue assessment is rarely linked to system-level functional prognosis. This paper addresses this gap for an angle grinder by combining uncertainty-aware functional prediction with component-level fatigue assessment in an instance-specific reliability workflow. The proposed framework combines the current tool state with recent force--torque usage windows. A convolutional encoder extracts loading patterns from spindle forces and shaft torque, and an LSTM backbone predicts nine functional variables as Gaussian mean and variance estimates. In parallel, the same loading history is translated into output-shaft fatigue information through finite-element-supported stress reconstruction, S--N/Miner damage evaluation with Haibach extension, and Paris-law crack-growth analysis. A streaming replay algorithm consolidates both branches into functional, material, and system reliability trajectories. Held-out tests show mean \(2\%\)-tolerance accuracy of 0.9652 across nine outputs. Thermal variables are predicted near-perfectly, while drive motor current and load speed remain the most demanding dynamic outputs, with \(R^2\) values of 0.9750 and 0.9924. Torque history is especially important for these variables, and the conventional LSTM outperforms GRU and xLSTM in the short-history setting. Reliability calibration is most informative for drive motor current, where predicted and observed exceedance probabilities ...

cs.AI

版本更新 · v2arXiv:2611.05278

Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve

Shaanil Punglia, Dadhichi Telwadkar, Vaibhav Rathore, Siddharth Sureka, Neha Bhargava

原文摘要

Language-subspace interventions aim to improve multilingual reasoning by suppressing language-related components in mid-layer activations. Using MATH and MGSM across four open-weight LLMs, we ask three questions: do estimated language subspaces capture translation-associated variation? Does projecting them out remove language information? And do they improve accuracy without compromising response language? For the first question, we build subspaces using the existing Mean-SVD construction and our DiffPCA. Both capture substantial translation-associated variation and show similar patterns across model depth. For the second, we project out each subspace and train linear probes to classify language from the projected activations. The probes still identify language almost perfectly, showing that neither subspace exhaustively captures language information. For the third, we evaluate several intervention configurations on Qwen2.5-7B, by varying subspace creation methods and intervention operators. We find that the intervention that most improves MGSM accuracy sacrifices response-language fidelity, with only one intervention improving joint accuracy$\unicode{x2014}$answers that are correct and in the target language$\unicode{x2014}$slightly, by 1.60 points. Interestingly, subtle changes in the prompt alone can reproduce the accuracy gains albeit with significant damage to language fidelity. We argue that causal interventions must be judged on more than accuracy, to fully account for language substitution trade-offs.

cs.CL · cs.AI