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

+479新增论文
+361其中 AI 相关
+64已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 02:08 — 2026-11-17 02:08(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:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,922 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 3,999 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.18553

WeightBench:评估语言模型作为权重空间程序员的能力

WeightBench: Evaluating Language Models as Weight-Space Programmers

Aayush Marasini, Barsat Khadka, Nick Rahimi

AI 速读 基于摘要

作者提出 WEIGHTBENCH 基准,用 42 个任务、五个方向考察大模型能否直接读写和修改其他神经网络的权重,而不依赖梯度下降。

cs.LG · cs.AI

查看原文摘要

Recent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability has been termed Weight-Space Programming (WSP). Exploring this new paradigm systematically requires a robust benchmark. We introduce WEIGHTBENCH, a benchmark that evaluates LLMs of increasing capability on 42 WSP tasks across five tracks: reading, fixing and writing weights, recognizing edits that are impossible, and data-free compression. The networks whose weights the LLMs read and edit range from 2K-parameter control policies to 7B-parameter language models. Experimental benchmark results show that frontier agents can already read small networks and write working control policies without ever running them, but cannot yet patch language models, compress them without data, or tell an impossible edit from a hard one. On all 42 tasks, Claude Opus 5.5 reaches a macro score of 0.535 (Sonnet 5.5 0.466, Haiku 5.5 0.402, DeepSeek v4-flash 0.215); on the 38 tasks it was run on, GPT-6.1-sol reaches 0.568 against Opus's 0.546. Code, the task registry, our OS-level sandbox harness, and the live leaderboard are publicly available at https://github.com/Aayush-Marasini/WeightBench.

版本更新 · v3arXiv:2604.14397

基于词典的跨语言义项投影生成概念词汇化

Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection

David Basil, Chirooth Girigowda, Bradley Hauer, Sahir Momin, Ning Shi, Grzegorz Kondrak

AI 速读 基于摘要

作者提出先用双语词典增强对齐器、再过滤错误义项投影的“投影—过滤”策略,把英语义项标注语料中的 synset 投射到对齐的目标语言词元上,从而为新语言生成 WordNet 式义项。

cs.CL · cs.AI

查看原文摘要

We study the task of automatically expanding WordNet-style lexical resources to new languages through sense generation. We generate senses by associating target-language lemmas with existing lexical concepts via semantic projection. Given a sense-tagged English corpus and its translation, our method projects the annotated synsets onto aligned target-language tokens and assigns the corresponding lemmas to those synsets. To generate alignments and ensure their quality, we augment a pretrained base aligner with a bilingual dictionary, which is also used to filter incorrect sense projections. We evaluate the method on multiple languages, comparing it to prior methods, as well as dictionary-based and large language model baselines. Results show that the proposed project-and-filter strategy improves precision while remaining interpretable and resource- efficient. We release our code, documentation, and generated sense inventories at https://github.com/UAlberta-NLP/ExpandNet.

版本更新 · v2arXiv:2607.04688

URSA:面向实用性逆合成评估的化学感知基准

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment

Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Anton Morgunov, Arkadii Lin, Maksim Kuznetsov, Rim Shayakhmetov, Vladimir Aladinskiy 等 10 位作者

AI 速读 基于摘要

作者提出URSA评估框架,从化学合理性角度对专用逆合成系统与通用大语言模型的合成路线规划能力进行基准比较。

cs.LG · cs.AI · cs.CE · cs.CL

查看原文摘要

Synthesis planning aiming to find pathways of reactions for a target molecule is one of the most important and challenging tasks in drug discovery. Recent progress has produced both specialized deep-learning retrosynthesis systems and general-purpose large language models, but objective comparison remains difficult due to the lack of flexible, chemically interpretable benchmarking protocols. In the current study, we are introducing the URSA (Utilitarian RetroSynthesis Assessment) evaluation framework that provides the opportunity to benchmark the synthetic routes not only from a formal perspective, such as convergence to commercially available starting materials, but also from a chemical plausibility perspective, mimicking the way expert chemists evaluate the reactions and routes. The study covers a comprehensive evaluation of both conventional end-to-end retrosynthesis solutions and LLMs for the synthesis planning task on a set of novel, diverse target molecules with undisclosed synthetic routes, which represent realistic tasks in the daily drug design routine. Although LLMs can support high-level strategic planning and even achieve SOTA performance in the OOD set, the Pareto frontier for estimated run cost and chemically plausible route solvability consists entirely of specialized retrosynthesis planners.

新论文 · v1arXiv:2611.18517

OpenLayout:面向整体VLSI物理设计与基准测试的开放智能体驱动平台

OpenLayout: An Open and Agentic-Driven Platform for Holistic VLSI Physical Design and Benchmarking

Qiufeng Li, Sizhe Tang, Quan Cheng, Zirui Wang, Wantong Li, Tian Lan, Weidong Cao

AI 速读 基于摘要

作者提出一个基于多智能体协作与内置设计知识的开放平台OpenLayout,并配套面向先进工艺节点、使用商业EDA工具的基准OpenLayout-Bench,用于自动化VLSI物理设计中的设计空间优化。

cs.AR

查看原文摘要

Physical design automation of very large-scale integrated circuits (VLSI) has made significant strides, progressing from single-stage placement and routing toward increasingly integrated full-flow implementation. Yet, existing approaches struggle with the vast design space optimization (DSO) arising from diverse technology nodes, circuit designs, and varied constraints. The substantial runtime of physical-design tools further exacerbates this challenge, leaving industrial workflows heavily dependent on experienced engineers to navigate the design space and achieve power, performance, and area (PPA) targets, incurring significant engineering effort. We argue that large language models (LLMs) with strong reasoning capabilities, enriched with distilled human design expertise, offer a promising path toward efficient and automated DSO. Unlike traditional algorithms, LLMs can interpret complex design contexts and naturally incorporate human expertise expressed in natural language for reasoning, acting, observing, and adapting throughout the design process, a capability that conventional optimization methods cannot exploit. To this end, we present OpenLayout, an agentic platform that leverages multi-agent collaboration with embedded design knowledge to enable self-iterative DSO. We further introduce OpenLayout-Bench, a benchmark targeting advanced technology nodes with commercial EDA tools to systematically evaluate physical design automation capabilities of LLMs. Experimental results demonstrate that OpenLayout achieves state-of-the-art performance, with approximately 20% accuracy improvement over baseline methods. Our work is open-sourced at https://github.com/fenggev56/OpenLayout

新论文 · v1arXiv:2611.18514

机制可解释性能否解释LLM智能体失败?以网页元素幻觉为例

Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination

Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao

AI 速读 基于摘要

该案例研究将机制可解释性工具用于分析网页智能体的元素幻觉,发现线性探针可预测并部分纠正幻觉,但解释效果受提示格式和计算分布性限制。

cs.AI · cs.CL

查看原文摘要

Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face when applied to realistic agentic failures. We focus on one such failure: web agents hallucinating actions that are not available on a website. We apply a series of mechanistic analyzes to Qwen2.5-7B-Instruct as it interacts with live websites. We find that a linear probe trained on the last prompt token can predict hallucinations before generation begins (0.80 AUC) and steering along a probe direction corrects 85\% of hallucinations, but disrupts 7\% of valid actions. However, these results only provide a partial explanation of why the agent hallucinates. The probe direction is sensitive to prompt formatting, losing much of its steering effect after a minor change to how actions are represented. Additionally, circuit identification can be difficult as the computation is distributed across multiple components and positions, and the information the agent relies on varies across examples. We discuss how these observations challenge the assumptions underlying standard MI methods for circuit discovery and feature identification, and outline future directions for making these methods better suited to explain failures in LLM-based agents.

新论文 · v1arXiv:2611.18513

MeReader:面向叙事类电子书阅读的离线、隐私保护、进度感知 AI 助手

MeReader: An Offline, Privacy-Preserving, Progress-Aware AI Assistant for Narrative eBook Reading

Mohammed Efaz, Udo Bub, Itilekha Podder

AI 速读 基于摘要

作者提出并评估了一个完全离线、只依据读者当前阅读位置进行检索与生成的本地 AI 阅读助手,旨在避免剧透并保护隐私。

cs.IR · cs.AI · cs.CL

查看原文摘要

This paper introduces MeReader, a privacy-preserving, offline and progress-aware AI assistant designed to function as a contextual companion for narrative reading on consumer hardware. Unlike conventional Large Language Model (LLM)-based systems that process documents/books online in an all-texts-at-once type of way, thereby risking narrative spoilers, MeReader confines both retrieval and generation to the reader's distinct position in the text. The system integrates a hybrid retrieval architecture, combining vector similarity, BM25, and summary embeddings, to ensure high fidelity to the reader's current context. We evaluate the system across classical English books using both quantitative comprehension metrics and qualitative LLM-based independent judging. The results identify a quality-latency frontier, showing that mid-sized local models (2b-4b) can achieve comprehension parity with larger counterparts (5b+) while maintaining acceptable response quality. Importantly, the proposed progress-aware boundary mechanism is shown to prevent future content leakage without compromising retrieval quality and correctness. These findings suggest that a localized, privacy-centric approach can augment, rather than replace, the digital reading experience, offering a good alternative to cloud-dependent services. Therein, there remains a lack of amalgamate systems which combine progress-aware, privacy-preserving, and narrative eBook reading with AI support. It is in this very gap that the development of MeReader came to be; synthesizing said strands into an offline, book-constrained assistant focused on enhancing comprehension without compromising narrative continuity or user privacy.

新论文 · v1arXiv:2611.18506

Agentic induction of common data elements and information extraction from sarcoma case report abstracts

Daniel Reichenpfader, Kwaku Appiagyei, Manovah Nadarajah, Ahmed Reda Bahr, Irina Filchenko, Fabio Dennstädt

原文摘要

Common data elements (CDEs) support clinical data comparability but are usually defined manually. We investigated whether large language model agents could derive a CDE schema from sarcoma case report abstracts and apply it at scale. An agent proposed 72,909 candidate CDEs from 24,588 PubMed abstracts; agentic consolidation yielded 1,570 CDEs. We retained 53 supported by at least 50 abstracts and attempted evidence-linked extraction across the corpus. Processing succeeded for all retained CDEs in 79.2% of abstracts, including responses indicating non-mention. Two human reviewers approved 83.0% of retained CDEs for relevance, 67.9% for clarity, and 56.6% for correctness. In 100 sampled abstracts, exact agreement with the value extracted by the LLM was 94.9% among 1,116 pairs with a non-empty answer (abstract-level bootstrap 95% CI, 93.0-96.4%). Errors concentrated in anatomical and temporal fields. These findings support agent-assisted schema drafting followed by expert curation before large-scale extraction.

cs.CL

新论文 · v1arXiv:2611.18504

面向容错量子电路发现的智能体式AI

Agentic AI for Discovering Fault-Tolerant Quantum Circuits

Aritra Lahiri, Florian Marquardt

AI 速读 基于摘要

作者提出将容错量子电路设计表述为智能体式进化程序合成,由大语言模型在电路验证器引导下自动演化出Clifford电路。

quant-ph · cs.AI

查看原文摘要

Scaling quantum computing toward practical quantum advantage is currently limited by the efficiency of circuits that operate on information encoded by quantum error-correcting codes. The full stack of quantum computing encompasses several tasks: preparation of logical code states, implementation of logical gates, logical routines on encoded qubits, etc. Yet, these circuits are largely designed by hand for individual cases, with some recent works incorporating machine learning for certain aspects. We formulate this problem as agentic evolutionary program synthesis, wherein a large language model, leveraging its pretraining knowledge and tool-use proficiency, and guided by a circuit verifier, evolves a program that defines a Clifford circuit for a wide range of curated tasks such as logical state preparation, logical gate design, and logical routines such as code-switching, code growth, etc. Our approach consistently finds fault-tolerant circuits for all of these tasks, each verified by an exhaustive check over faults.

新论文 · v1arXiv:2611.18453

基于集成之集成的大语言模型黑盒不确定性量化

Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles

Wang Ma, Debarun Bhattacharjya, Junkyu Lee, Nhan H Pham, Harsha Kokel, Qiang Ji

AI 速读 基于摘要

提出一种两级集成黑盒方法,通过随机解码和语义扰动分解大语言模型的偶然与认知不确定性,并给出理论保证与实验验证。

cs.LG · cs.AI

查看原文摘要

Reliable use of large language models (LLMs) requires uncertainty estimates that separate ambiguity intrinsic to a prompt from genuine knowledge gaps. Bayesian and deep-ensemble methods deliver this aleatoric/epistemic decomposition in principle, but are computationally prohibitive at LLM scale and require white-box access. Existing black-box methods, in contrast, summarize to a single scalar that cannot make the distinction. We introduce a two-level ensemble that bridges this gap. Stochastic decoding of a fixed prompt forms the inner ensemble; meaning-preserving semantic perturbations of the prompt form the outer ensemble. Variability is measured in a continuous embedding space, and the law of total covariance gives an exact within-/between-perturbation decomposition to estimate aleatoric and epistemic uncertainty (AU/EU); it requires only black-box sampling access. On top of this estimator, we contribute three theoretical results that ground the framework: (i) a finite-sample bias identity for nested Monte Carlo with a closed-form bias-corrected epistemic estimator; (ii) a Bayesian bridge bounding the gap between perturbation-population AU/EU and Bayesian targets; and (iii) a separation result identifying a class of failure modes that any consistency-only black-box method provably misses while perturbation-based EU detects. Across five short QA benchmarks and four instruction-tuned LLMs spanning two families and two scales, our estimator is competitive with strong white-box baselines, and at a matched generation budget it matches leading black-box methods on error ranking while decomposing AU and EU; controlled paired interventions show that AU and EU respond selectively to distinct, actionable sources of failure: prompt ambiguity and model knowledge gaps; and a long-form pilot on the NQ long-answer split shows the framework extends to claim-level factuality without retraining.

新论文 · v1arXiv:2611.18436

社会科学研究中的效率提升:面向预处理与代码优化的前瞻性硅采样协议

Efficiency Gains in Social Science Research: A Prospective Silicon Sampling Protocol for Pre-Treatment and Code Optimization

Noaïm Astitou, Etienne Aucouturier

AI 速读 基于摘要

作者报告利用三种大语言模型在真实数据收集前生成合成数据以优化代码和预处理流程,在代码开发上节省大量时间,但该方法有效性取决于主题可预测性。

cs.CY

查看原文摘要

This study evaluates the methodological potential of using large language models (LLMs) to generate synthetic datasets prior to real-world data collection, thereby streamlining subsequent processing and statistical analysis. The approach is applied to a survey conducted within the France Life Imaging (FLI) network, leveraging three distinct LLMs (Sonnet 4.6, GPT 5.3, and Kimi 2.6) to simulate responses and prepare data processing workflows. The findings demonstrate significant time savings in code development (85% to 90% reuse rate) and highlight the conditional validity of this preprocessing method, which depends on the thematic predictability of the models. While synthetic data effectively captures collective perceptions, it struggles with specialized or contextualized practices, reflecting limitations documented in the silicon sampling literature, such as homogenization and reduced variance. This work extends the Phase 0 concept (Trojacka et al. 2025) from instrument validation to a full-fledged methodological preprocessing step, paving the way for scalable applications in survey research.

新论文 · v1arXiv:2611.18417

CoPre-MoE: Consolidating and Preserving MoE for Multimodal Continual Instruction Tuning

Tao Hu, Ling-Xiang Zhang, Da-Wei Zhou

原文摘要

Multimodal continual instruction tuning requires multimodal large language models to sequentially acquire new capabilities without catastrophic forgetting. Mixture-of-experts (MoE) architectures offer a promising way to mitigate task interference through expert specialization and combination. However, while existing MoE-based methods avoid overwriting shared parameters by allocating separate experts for each task, this progressive expansion incurs severe cross-task redundancy and linear parameter growth. Specifically, experts across tasks often learn overlapping functions alongside task-specific capabilities. For instance, ScienceQA and TextVQA both locate relevant image regions. To curb parameter redundancy without inducing forgetting, we propose Consolidating and Preserving MoE (CoPre-MoE). For each incoming task, CoPre-MoE first learns task-specific MoE to capture specialized capabilities. To eliminate redundancy and reduce parameter growth across tasks, we design a shared-and-private expert architecture. Specifically, we first evaluate functional overlap to selectively consolidate overlapping experts across tasks into a fixed-capacity generic expert pool. We then factorize the remaining task-specific experts into shared projection bases and compact task-specific cores within a private expert pool. To mitigate forgetting, we construct the router by pairing each expert with learnable retrieval keys, where historical keys remain frozen during continual updates while newly added keys are regularized with an orthogonality penalty. At inference, input-dependent routing dynamically combines both pools without test-time task labels. Extensive experiments demonstrate that CoPre-MoE achieves superior performance while substantially reducing parameter overhead.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2605.21965

SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents

Mehrdad Saberi, Keivan Rezaei, Soheil Feizi

原文摘要

Large language models increasingly use external tools such as web search and document retrieval to solve information-intensive tasks. However, multi-hop tool use in complex tasks introduces substantial latency, since the model must repeatedly wait for tool observations before continuing. We study how to accelerate such trajectories without changing the final trajectory the model would have taken without acceleration, assuming access to faster but less reliable speculator tools. We develop a theoretical framework for lossless speculation in multi-hop tool-use settings, characterizing the optimal achievable latency gain. We propose SpecHop, a continuous speculation framework that maintains multiple speculative threads, verifies predicted observations asynchronously as target tool outputs arrive, commits correct branches, and rolls back incorrect ones. This preserves accuracy while reducing wall-clock latency. We show that SpecHop can approach oracle latency gains with enough active threads. Empirically, on retrieval-augmented multi-hop tasks, SpecHop closely matches theoretical predictions and reduces latency by up to 40\% in some settings. Code: https://github.com/mehrdadsaberi/spechop

cs.CL

新论文 · v1arXiv:2611.18371

Evaluating Human Sensitivity to Gender Biased AI-Generated Content through Human Assessment of Google's Autocomplete Function

Tamara Serrano, Nikoleta Pantelidou, Raquel Montero, Natalia Moskvina, Paolo Morosi, Evelina Leivada

原文摘要

Large Language Models (LLMs) are increasingly present, but their effects on human users remain underexplored. We tested whether AI-attributed information influences views regarding gender-related statements, a domain where biases are pervasive. Spanish-speaking participants recruited through Prolific evaluated biased statements derived from Google's autocomplete function and human-authored, non-biased gender-related facts. Participants were either informed that some of the material was AI-generated or received no information about its origin. AI attribution did not affect reaction times or agreement judgments. This result suggests that AI-generated content does not automatically raise credibility concerns and may be evaluated with less scrutiny compared to human-produced content.

cs.CL

新论文 · v1arXiv:2611.18370

f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models

Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash Harandi, Trung Le

原文摘要

Anomaly detection in tabular data poses significant challenges due to heterogeneous feature types-mixing numerical, categorical, and textual attributes, which complicate learning meaningful representations of normality. Recent work has applied large language models (LLMs) to this problem by serializing table rows as text sequences, yet these approaches rely on one-shot supervised fine-tuning that offers limited signal to tighten the model's description of normality. We propose DiSPaT, a self-play fine-tuning framework that strengthens the model's understanding of normal data. Building on the theoretical foundation of f-divergence minimization, we derive a tight approximation connecting our training objective to reducing the distributional gap between real normal data and model-generated samples. DiSPaT operates through an alternating optimization: at each iteration, the current policy generates synthetic samples that serve as pseudo-anomalies, while a critic discriminator learns to distinguish these from real normal samples; this signal drives policy updates that progressively align the model distribution with the true normal-data distribution. Extensive experiments on diverse benchmarks demonstrate that DiSPaT consistently outperforms prior LLM-based methods, deep learning approaches, and classical unsupervised detectors for tabular anomaly detection.

cs.LG · cs.CL

版本更新 · v2arXiv:2603.16411

RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery

Abhishek Kumar, Aashraya Sachdeva

原文摘要

Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air-traffic control, these errors are costly. If an entity is entirely absent from the ASR output, text-only post-correction has little signal to recover it. To address this, we introduce RECOVER, an agentic post-ASR entity-correction framework. It leverages multiple hypotheses as evidence from ASR, retrieves relevant entities, proposes Large Language Model (LLM) correction under constraints, filters them through deterministic guardrails and uses an LLM critic that judges each surviving edit and can trigger a targeted feedback round to recover an entity the first pass missed. The hypotheses are used by one of several strategies, namely 1-Best, Entity-Aware Select, Recognizer Output Voting Error Reduction (ROVER) Ensemble, LLM-Select and Adaptive Routing. Evaluated across five diverse datasets over a Whisper-large-v3 baseline, it achieves up to 49% relative reduction in entity-phrase word error rate (E-WER) and increases entity recall by up to 14 percentage points while preserving the overall word error rate (WER), with LLM-Select the strongest strategy.

cs.CL · eess.AS

版本更新 · v5arXiv:2604.14586

CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations

Xiping Li, Aier Yang, Jianghong Ma, Kangzhe Liu, Shanshan Feng, Haijun Zhang, Yi Zhao

原文摘要

The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network (GNN)-based methods primarily prioritize accuracy over diversity, overlooking their inherent trade-off. To address this, we previously proposed CPGRec, a balance-oriented gaming recommender system. However, CPGRec fails to account for critical disparities in player-game interactions, which carry varying significance in reflecting players' personal preferences and may exacerbate over-smoothness issues inherent in GNN-based models. Moreover, existing approaches underutilize the reasoning capabilities and extensive knowledge of large language models (LLMs) in addressing these limitations. To bridge this gap, we propose two new modules. First, Preference-informed Edge Reweighting (PER) module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions. Second, Preference-informed Representation Generation (PRG) module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests, thereby refining representations of players and games. Experiments on \textcolor{black}{two Steam datasets} demonstrate CPGRec+'s superior accuracy and diversity over state-of-the-art models. The code is accessible at https://github.com/HsipingLi/CPGRec-Plus.

cs.IR · cs.AI

新论文 · v1arXiv:2611.18274

Right Token, Right Time: From Per-Token Gating to Trajectory-Aware Activation Steering

Nima Eshraghi, Lovedeep Gondara, Sagarika Suresh, Xiaotong Xu, Jithin Pradeep, Fanny Chevalier

原文摘要

Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning. Yet, standard methods apply the steering signal at every generated token, displacing representations from the distribution the model was trained on and eroding generation quality. We show that \emph{when} along a generation the intervention is applied is a decisive axis of control. We cast steering as a per-token allocation problem under a fixed budget of steerable tokens, so that methods differ only in which tokens they select, making allocation the sole variable. Within this framework we introduce two gates. The first, Contrastive Feature Projection (CFP), is memoryless and selects the tokens least aligned with the target behavior through a sparse, interpretable feature projection. The second, Closed-Loop Adaptive Bernoulli Steering (CLABS), is trajectory aware. It treats allocation as closed-loop feedback control, tracking the alignment a generation has accumulated so far and spending budget where the trajectory falls behind. On a linear steering-response model we derive an explicit gain region that guarantees closed-loop stability of CLABS and show that its integral term reduces the steady-state tracking offset. Empirically, CFP and CLABS achieve the largest behavioral shift among budgeted gates at matched budgets, with CLABS strongest under the tight budgets where allocation matters most, while best preserving fluency.

cs.LG · cs.AI

新论文 · v1arXiv:2611.18272

From Bytes to Behavior: Request-Level Attribution from Live GPU Hidden States

Jonathan Pan, Yidi Yuan, Xin Wei Chia, Xinhui Su, Vincent Tan, Brenda Ong

原文摘要

Existing memory forensics for machine learning systems typically targets static artifacts, such as model weights or prompt logs, rather than the transient computational states of a live inference process. This gap limits an examiner's ability to analyze the specific behavior of a running large language model (LLM) service that cannot be restarted or modified. We present a method for acquiring per-layer residual-stream activations from a live GPU process using a non-modifying debugger, without requiring prior knowledge of the model's architecture parameters or weights. The approach employs a general six-stage process with platform-specific adapters, utilizing either a PyTorch allocator clock or a kernel-launch clock to identify and read tensor allocations from video memory. We validate this acquisition on 33 open-source decoder-only models across nine architecture classes, demonstrating that the recovered bytes are byte-exact and usable for downstream analysis. As a use case, we apply linear probes trained on standard framework activations to the recovered states, successfully distinguishing refusal from compliance with an AUROC of 0.88 on held-out prompts. This work establishes that live, observational access to intermediate hidden states is feasible on named inference platforms, providing a new source of evidence for examining the operational behavior of deployed AI systems.

cs.CR · cs.AI

版本更新 · v3arXiv:2607.07738

REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming

Nicolas Koller, Andreas U. Schmidt

原文摘要

Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it. Existing benchmarks for LLM-assisted binary analysis treat the construction of function-level ground truth as a solved pre-processing step and report accuracy without disclosing how many functions were reliably evaluable. We argue that the principal obstacle to fair evaluation is not model capability but the reliability of binary-to-source alignment under compiler optimization. This paper presents Reforge, a provenance-tracked pipeline that constructs function-level ground truth from C source through compilation, DWARF and syntactic extraction, alignment, and decompilation, and that operationalizes alignment uncertainty as an eight-gate confidence funnel with three-tier stratification. On a controlled micro-benchmark, high-confidence yield falls from 87.2% to 65.9% across optimization levels, and unpaired comparisons overstate optimization-induced performance decay through survivorship bias. A proof-of-concept evaluation of seven contemporary LLMs on function naming demonstrates the validity of the concept and generally motivates an uncertainty-aware benchmarking practice.

cs.SE · cs.AI · cs.CR · cs.PL

新论文 · v1arXiv:2611.18248

Dancing Tokens on the Vocabulary Network from LLM Generation

Yuan-Chao Hu

原文摘要

Large language models (LLMs) generate text one token at a time, yet how a particular generation relates to the geometry learned in pre-training remains unclear. The fundamental explainability of LLMs is elusive. Here, we build a similarity network from the input embeddings of six open LLMs and map generation onto it. The token-embedding network is scale-free while heavy-tailed, as are random embeddings with matched covariance, but far more fragmented. Distillation barely changes this topology because input embeddings are largely inherited. The knowledge space is thus deterministic from pre-training. Consecutive generated tokens are rarely graph neighbours and, in most models, no more often than in shuffled order, so generation is not a walk on the predefined network, although the tokens it visits are concentrated within it. Through the logit lens in a layer- wise manner, tokens settle late in depth in most models, and repetitive models remain confined to small domain-specific sub-graphs. These observables could serve as inference-time monitors of degeneration. We thus provide a fresh perspective on understanding LLM generation in the microscopic way from node or link prediction by graph learning.

cs.AI · cond-mat.dis-nn

新论文 · v1arXiv:2611.18235

NeoResearch: Literature- and Experience-Guided Autonomous Time Series Model Discovery

Ze Guo, Mingyue Cheng, Xiaoyu Tao, Shuo Yu, Shangtong Ye

原文摘要

Developing effective forecasting models for diverse time-series domains requires substantial expert knowledge, evidence from scientific literature on the web, and iterative experimentation. However, translating this knowledge and research experience into model designs requires preserving source context and testing applicability under task-specific assumptions. In this paper, we propose NeoResearch, a literature- and experience-guided autonomous research framework that leverages large language models (LLMs) as researchers to discover lightweight, domain-specific forecasting models. Specifically, NeoResearch establishes an expert-inspired dual-loop research workflow, coupling hypothesis-driven architecture exploration with iterative training and hyperparameter optimization through experimental feedback. To enable knowledge-grounded discovery, the agent autonomously mines scientific literature from the Web, extracting modeling mechanisms, empirical evidence, and applicability conditions to formulate task-grounded, testable architecture hypotheses. Furthermore, a hierarchical experience memory links literature findings to experimental outcomes and consolidates conditional lessons, guiding architecture discovery and training optimization while supporting reuse across forecasting tasks. Experiments on ten datasets show competitive performance and support dual loops, literature extraction, and memory reuse. Our code is available.

cs.LG

新论文 · v1arXiv:2611.18230

Personalization of Basic and Moral Values Guiding LLM-Controlled Assistant Robots

Mateusz Wozniak, Qi Gao, Agnieszka Wykowska

原文摘要

Personal assistant robots powered by large language models (LLMs) are likely to enter everyday life within the next decade, but the values that should guide their behaviour remain largely unspecified. Current alignment practice steers a single model toward an aggregate of human values, ignoring that individual users may prefer a robot whose value profile differs from their own. We administer parallel self- and robot-targeted versions of three established psycho-metric instruments - the simplified Schwartz Values Survey (SVS), the Portrait Values Questionnaire (PVQ-21), and the Moral Foundations Questionnaire (MFQ) - to potential future users (N=22), capturing both their personal values and the values they would want an assistant robot to embody. We compare the three instruments as personalization tools using the UEQ-S and benchmark fifteen contemporary LLMs against the resulting profiles. Participants wanted their robot to score markedly lower than themselves on personal-focus values and higher on social-focus values; moral profiles were nearly identical. LLMs prompted to act as robots shifted only weakly toward the desired profile, indicating that default model behaviour and prompt engineering are no substitute for explicit value personalization.

cs.HC · cs.AI

新论文 · v1arXiv:2611.18219

Large language models put existential risk from artificial intelligence at 10%

Julian Kauk

原文摘要

How likely is it that advanced artificial intelligence (AI) will cause human extinction or a similarly permanent disempowerment of humanity? Humans, including AI experts, frequently disagree on this question. Yet one important perspective is missing from this debate: that of AI systems themselves. We put the question to 241 large language models (LLMs) at every available reasoning setting. The models converged on a median risk of 10.0%, with the middle 90% of their estimates between 3.5% and 15.8%, far narrower than the spread among human experts. More expensive, and typically more capable, models stated higher risks; newer models showed more uniform, but not higher, risks. More reasoning barely changed the models' estimates but widened their uncertainty, mostly toward higher risk. Almost all models named loss of control over AI as the most likely cause. These answers are not independent judgments; they likely echo training data, including published expert polls, and choices made in aligning the models. Still, they document the position that current AI systems state on the risks of their own technology. Whether this position reflects any genuine understanding of the systems' own capabilities remains open. Repeated measurements can show whether it shifts as AI systems advance, and how training and alignment shape it is a question for both research and public debate.

cs.CY

新论文 · v1arXiv:2611.18183

When Should a Virtual Patient Ask? RISP-Guided Proactive Information Seeking in Multi-Agent Patient Simulation

Jingyao Cai, Shuaijun Liu, Abdul Rehman, Xiaowan Li, Qintian, Thomas Dolby, Sue M Green, Xiaosong Yang

原文摘要

Virtual patient (VP) systems support nursing communication training by providing simulated encounters in which learners practise explaining care and responding to patient concerns. Although large language models (LLMs) support flexible dialogue, current approaches give less explicit attention to how patients' information needs develop and guide the content and timing of their questions. We draw on the Risk Information Seeking and Processing (RISP) model, which relates information seeking to perceived risk and the gap between perceived knowledge and desired understanding. Guided by this perspective, we propose the RISP Multi-Agent System (RISP-MAS), a VP system for patient-initiated information seeking. The system links ongoing assessment of the patient's perceptions and information needs to coordinated decisions about whether to seek information, when to ask and which uncertainty to address. Evaluation of nursing student-VP interactions suggested that RISP-MAS exhibited plausible patient information-seeking behaviour, as indicated by expert assessments, while student feedback reflected positive interaction experiences. This work extends patient simulation by connecting a psychological account of information needs to explicit decisions about question initiation. The approach offers nursing students opportunities to practise recognising unresolved patient concerns and tailoring explanations to patients' information needs.

cs.MA

版本更新 · v2arXiv:2607.07824

CPM-MultiAgent: A CPM-Grounded Appraisal Framework for Simulating Dynamic Patient Emotional Evolution in Healthcare Dialogue

Jingyao Cai, Shuaijun Liu, Xiaowan Li, Yutong Guo, Abdul Rehman, Qintian, Thomas Dolby, Sue M Green 等 9 位作者

原文摘要

Large Language Models (LLMs) enable patient simulation for healthcare communication training, where learners practice responding to clinical information, concerns, and emotional reactions. However, existing patient simulation and affective dialogue systems often represent patient emotions as static attributes or focus on recognizing emotions and generating empathetic responses. They provide limited support for modeling how a simulated patient's emotional state evolves in response to a healthcare professional's communication. Changes in patient emotion constitute interactional feedback that learners must recognize and respond to across dialogue turns. We draw on the Component Process Model (CPM), a psychological theory that explains emotion as a dynamic process shaped by event appraisal. We propose CPM-MultiAgent, a CPM-grounded multi-agent framework for dynamic patient emotion simulation in healthcare communication training. The framework uses an emotion taxonomy informed by medical literature and expert input, and updates emotional states through healthcare-related trigger identification, structured CPM appraisal, and emotion-state integration, accounting for the patient's profile, clinical context, and prior emotional state. We evaluate the framework through student-led conversations and controlled trigger cases, combining nursing-expert assessments, LLM-judge comparisons, component ablations, backbone checks, and student feedback.

cs.MA · cs.AI

新论文 · v1arXiv:2611.18157

A Multi-Layered AI Pipeline for BPMN Generation from Natural Language

Alexandru Rancea, Ionut Anghel, Tudor Cioara, Ovidiu Anchidin, Ancuta Nemes

原文摘要

The automated transformation of unstructured natural language process descriptions into Business Process Model and Notation (BPMN) diagrams remains a challenging task, due to linguistic ambiguity and the difficulty to detect non-adjacent control-flow relationships. This paper proposes a solution for generating BPMN models from natural language descriptions through a multi-layered pipeline that integrates transformer-based architectures, Large Language Models and ontology population. The proposed method starts with natural language descriptions and separates textual processing, control-flow relation extraction, and structural validation into dedicated components. Entity extraction is performed using a fine-tuned RoBERTa-based transformer model while a control-flow engine captures non-adjacent relationships through LLM-based inference. To improve generalization under limited available data, the approach uses a dynamic few-shot strategy with con- trolled template input construction, enabling improved generalization under limited data availability. Additionally, an ontology population mechanism is introduced to represent the generated process models as semantic knowledge structures. For evaluation purposes we have used from the literature and industry reference processes. Additionally, we have validated the proposed method on a real-world heart disease patients transitional care process, capturing practical constraints and multi-actor collaboration, and serving as an expert-defined benchmark scenario. Experimental results demonstrate strong performance in the relation extraction task, achieving an accuracy of 90.7%, as well as maintaining structural alignment between the generated and reference BPMN models across multiple evaluation scenarios scenarios.

cs.CL

新论文 · v1arXiv:2611.18143

DRA-HTR: Disentangling Representation and Adaptation for Handwritten Text Recognition

Gayan H. Pathirage, Florent Imbert, Denis Coquenet, Elisa H. Barney Smith

原文摘要

Handwritten text recognition (HTR), particularly when applied to historical documents, remains challenging due to the scarcity of annotated data and the substantial domain shifts caused by variations in handwriting styles, document degradation, acquisition conditions, and linguistic characteristics. While large amounts of unlabeled target-domain data are often available, effectively exploiting them requires adaptation strategies tailored to the specific requirements of HTR. We propose DRA-HTR, an unsupervised generative domain adaptation pipeline specifically designed for HTR and built upon the DRANet framework. The proposed approach combines source-domain pretraining, unsupervised adaptation to the visual characteristics of the target domain, relying on the generation of target-style source samples for task-specific training. We further investigate the integration of post-HTR correction to complement visual adaptation with language adaptation, relying on large language models, which we introduce as DRAL-HTR. The proposed framework is evaluated across seven HTR datasets spanning four languages, using a single set of hyperparameters for all source-target combinations. The recognition model achieves state-of-the-art performance on four datasets and competitive results on the remaining three. In addition, the proposed DRA-HTR establishes a new state-of-the-art for domain adaptation across all seven datasets and substantially improves overall robustness and training stability compared to the original DRANet framework: it reduces the Character Error Rate (CER) in average by 13.52 percentage points, and the average standard deviation decreases from 7.23 to 1.11 percentage points. Finally, post-HTR correction further reduces the CER by 2.16 percentage points.

cs.CV

新论文 · v1arXiv:2611.18140

Large Language Model-Empowered Intelligent Agent for Adaptive Fast-Charging Control of Lithium-Ion Batteries

Joey Chan, Haoyu Pan, Zhen Chen, ErShun Pan

原文摘要

Fast charging of lithium-ion batteries is a multi-objective control problem that requires reducing charging time and sustaining high energy throughput while suppressing accelerated degradation and safety-critical electrochemical reactions. Conventional protocols are easy to implement but have limited ability to adapt to variations in battery chemistry, operating conditions, and aging state. Model-based optimization and conventional data-driven control often require accurate models, costly iterative search, or task-specific policies. We develop a large language model (LLM)-empowered intelligent agent for adaptive battery fast-charging control. In this closed-loop framework, the agent interprets structured battery states, generates executable charging actions, observes the resulting battery response, and continuously adjusts subsequent decisions. We construct a large-scale simulation corpus with PyBaMM across five battery chemistries and 11 parameter sets and convert the resulting state-action-response trajectories into structured process data for agent training. Our two-stage strategy combines supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). SFT establishes battery-control semantics and feasible decision priors from simulation-derived demonstrations. GRPO aligns the agent with a multi-objective control objective covering energy throughput, degradation mitigation, and operational constraints. Closed-loop simulations show that, under matched energy-throughput requirements, the agent achieves longer cycling life than conventional charging baselines and optimization-based strategies across heterogeneous battery configurations. This study provides a simulation-grounded proof of concept for using LLM agents as sequential decision makers in battery management and takes a step toward language-model-enabled control of physical energy systems.

cs.AI

新论文 · v1arXiv:2611.18133

Forget the Lineage: Forward-Secure, Lineage-Complete Cryptographic Erasure for LLM-Agent Memory

Yulliwas Ameur, Billal Mokhtari, Samia Bouzefrane

原文摘要

Large language model (LLM) agents keep a long-term memory that the model itself writes: summaries, extracted facts and embeddings derived from what users said. Deleting a message is therefore not enough: its derivatives, storage residue and backups survive. We define lineage-complete forward-secure erasure: after a forget request, an adversary that later obtains all storage and the agent's current keys learns nothing about the forgotten input or any memory derived from it. We present LinEra, which encrypts each memory under a key derived from its parents' keys along the derivation graph; source keys come from a puncturable pseudorandom function, so forgetting is a single puncture and every descendant becomes unreadable without being located. A sound lineage rule records as parents everything the writer saw, which confines all influence of a source to its descendants. We prove security and lineage integrity and integrate LinEra with mem0. With real LLMs from two families (1.5B to 7B parameters) writing the memory of LoCoMo conversations, an attacker holding every file and the current keys recovers, on all ten conversations written by the largest model, 70 of 71 forgotten secrets after logical deletion, 67 with per-object or epoch keys, and none with LinEra; the same holds for every writer tested. The price is a larger forgetting radius, which follows a simple law in the writer's fan-in: forgetting 1% of turns erases 73.0% of derived memories with session-level summaries but only 3.8% with four-turn windows, which also answer better; re-deriving restores what is lost.

cs.CR

新论文 · v1arXiv:2611.18130

JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Exams

Issa Sugiura, Taro Makino, Takashi Ishida

原文摘要

Large language models (LLMs) are increasingly applied to finance, creating a need for benchmarks that evaluate their capabilities across financial systems with different regulations and practices. However, existing financial benchmarks provide limited coverage of country-specific financial systems, and they are difficult to keep up to date as released questions leak into training data. We introduce JFinBench, a Japanese financial benchmark comprising 321 examples from the 2026 editions of six regularly administered certification exams covering accounting, tax, financial planning, and banking. To construct it, we develop a human-in-the-loop agentic pipeline in which a coding agent writes exam-specific conversion code and a review page, while a human verifies every example and feeds corrections back to the agent. This pipeline adapts to heterogeneous exam formats and reduces the effort of incorporating new exam editions, enabling periodic refreshes that mitigate data contamination. Evaluating 12 recent LLMs, we find that Claude Fable 5 and GPT-6 Astra exceed 93% overall, while even the best open-weight model, Kimi K3.1 Pro, trails Claude Fable 5 by 12 percentage points. When models can additionally use a terminal and web access, they retrieve the knowledge they lack and every model improves. The gap narrows but about 4 points remain, and the ranking of models stays largely the same, suggesting that knowledge held in the model itself remains valuable even with tools. We release the dataset, the evaluation code, and the construction pipeline.

cs.AI