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
+63已有论文修订
+93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 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 13:47 — 2026-11-16 13:47(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 13:44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6,921 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 23,827 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:2611.14279

AutoThreshold:面向自适应掩码二值化的联合混淆轮廓学习

AutoThreshold: Joint Confusion-Profile Learning for Adaptive Mask Binarization

Shaokai Wu, Xunchu Zhou, Pinzhi Wang, Bo Dong, Xiao Cui, Qi Kong, Yue Ding, Hongtao Lu

AI 速读 基于摘要

提出一种事后策略 AutoThreshold,通过预测分数分箱上正负像素的联合质量来参数化阈值索引的混淆计数,从而无需重训即可为任意 F_β 目标选择二值化阈值。

cs.CV

查看原文摘要

A single validation-tuned threshold can become brittle when dense-score distributions shift. We introduce AutoThreshold, a post-hoc policy that predicts the joint mass of positive and negative pixels over score bins. This target directly parameterizes threshold-indexed confusion counts, avoiding products of independently estimated prevalence and class-conditional rates. Softmax normalization and cumulative decoding yield coherent, monotone confusion profiles; a plug-in decoder then selects a threshold for any $F_β$ objective without retraining the head. Across three independently trained Kvasir pipelines transferred to four polyp datasets, Joint exceeds continuous Otsu by $0.0080 \pm 0.0046$ external macro Dice, with positive gains in 3/3 runs. On the reference pipeline, three head seeds achieve $0.6324 \pm 0.0027$, 0.0085 above Otsu; direct-utility Ridge achieves 0.6342, with the paired difference interval spanning zero. The same Joint checkpoints outperform Otsu for $F_{0.5}$, Dice, and $F_2$. On developmental KITTI Road leave-one-corruption-family-out evaluation, Joint improves over scalar regression by 0.0082 [0.0064, 0.0101], while direct utility is 0.0022 higher. These results establish joint confusion prediction as a useful, metric-retargetable inductive bias, without claiming Bayes-optimal $F_β$ decisions.

版本更新 · v9arXiv:2508.01415

RoboMemory:面向物理具身系统交互式环境学习的脑启发多记忆智能体框架

RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems

Mingcong Lei, Honghao Cai, Yuyuan Yang, Yimou Wu, Jinke Ren, Zezhou Cui, Liangchen Tan, Junkun Hong 等 20 位作者

AI 速读 基于摘要

作者提出一种融合时间、空间、语义与情景记忆的脑启发框架,用于提升具身智能体在长程任务中的规划与交互学习能力。

cs.RO · cs.AI

查看原文摘要

Long-horizon embodied tasks require agents to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and inefficient integration of heterogeneous memories, limiting their capacity for long-horizon adaptation. To address this, we introduce RoboMemory, a brain-inspired framework that unifies Temporal, Spatial, Semantic, and Episodic memory for efficient long-horizon planning and interactive learning. Its core innovations are a comprehensive memory system designed for embodied tasks, and a dynamic spatial knowledge graph for scalable, consistent memory updates. Extensive experiments on EmbodiedBench show that RoboMemory improves the average success rate of Qwen2.5-VL-72B-Ins by 26.5 percentage points and achieves performance comparable to strong closed-source VLM agents. Real-world trials further suggest RoboMemory's potential for interactive environmental learning by reusing accumulated experience across repeated task attempts. These results demonstrate RoboMemory as a scalable memory-augmented framework for embodied agents, improving long-horizon planning and cumulative learning in complex interactive environments.

版本更新 · v2arXiv:2610.25955

几乎 N^{2d} 时间内的有界整数规划

Bounded Integer Programming in Almost $N^{2d}$ Time

Lin Chen, Yuchen Mao, Guochuan Zhang

AI 速读 基于摘要

作者提出确定性算法,将标准形式有界整数规划的运行时间从 N^{O(d^2)} 改进到约 N^{2d+ε}(固定 d 与 ε)。

cs.DS

查看原文摘要

We study integer programs in standard form $\min\{\mathbf{c}^{\mathsf T}\mathbf{x}:A\mathbf{x}=\mathbf{b},\mathbf{l}\leq\mathbf{x}\leq\mathbf{u},\ \mathbf{x}\in\mathbb{Z}^n\}$, where $A\in\mathbb{Z}^{d\times n}$, all entries of $\mathbf{b},\mathbf{c},\mathbf{l},\mathbf{u}$ are integers, and every variable bound is finite. Let $N$ be an upper bound on the absolute values of the entries of $A$, and $c_{\max}$ one on the absolute values of the costs. For every fixed $d$ and every fixed $\varepsilon>0$ we give a deterministic algorithm running in time \[ T_{\textrm LP}+O_d(n)+O_{d,\varepsilon}\bigl(N^{2d+\varepsilon}\log^2(c_{\max}+2)\bigr), \] where $T_{\textrm LP}$ is the time to solve one linear programming relaxation exactly. Prior to our work, the best known running time for bounded variables was $N^{O(d^2)}$ [Eisenbrand \& Weismantel'20], and it has been a fundamental open problem whether the exponent $O(d^2)$ can be improved to one linear in $d$. We answer this question affirmatively, with the exponent $2d+\varepsilon$.

新论文 · v1arXiv:2611.14275

成分随机森林

Compositional random forest

Khaled Masoumifard, Stephan van der Westhuizen, Sugnet Gardner-Lubbe

AI 速读 基于摘要

该论文构建了一个适用于成分型响应变量的随机森林框架,可统一处理单纯形、对数比坐标和单位球面三种表示,并以对数似然增益作为分裂准则。

stat.ML · cs.LG

查看原文摘要

Compositional data have been analysed in the literature from three main points of view: directly on the simplex, in log-ratio coordinates, and as directional data on the unit sphere. In this paper, we construct a random forest framework for compositional responses that accommodates all three. Random forests are ensembles of decision trees, and the split criterion determines how each tree grows. We use the log-likelihood gain as the split criterion and consider distributions defined on the different spaces in which compositions can be represented. The Dirichlet likelihood has been studied in the literature, but its covariance is fixed by its mean up to a single scalar, and its maximum likelihood estimator has no closed form. To obtain more flexible criteria, we use two well-known transformations. First, the square-root transformation maps compositions onto the unit sphere, where existing directional distributions require numerical estimation. We introduce a tangent-normal (TN) distribution, which shares its parameters with the Kent distribution, and construct a split criterion whose gain is computed from additive sufficient statistics: the shape parameters are maximised out in closed form, up to an exponentially small truncation constant, so that no parameter is estimated iteratively. Second, the log-ratio transformation maps compositions to Euclidean space, where the multivariate logistic-normal distribution has a flexible covariance and a closed-form maximum log-likelihood, also based on additive sufficient statistics. Both criteria respond to a shift of the mean, measured relative to the covariance, and to a change in the covariance itself. In simulations, the most accurate forest depended on the covariance structure of the composition. The TN forest was the most accurate in two of the three designs.

新论文 · v1arXiv:2611.14274

从预测到行动:学习可变形线性物体操作中的物理上下文

From Prediction to Action: Learning Physical Context for Deformable Linear Object Manipulation

Chengxiao Dong, Alessio Caporali, Hongyu Lan, Gianluca Palli

AI 速读 基于摘要

论文研究可变形线性物体形状控制中预测效用与决策效用的区别,提出几何指针流策略并比较不同物理上下文表示对预测和控制的影响。

cs.RO

查看原文摘要

A representation that accurately predicts a deformable object's response is not necessarily the one most useful for choosing manipulation actions. We study this distinction between predictive utility and decision utility in planar single-grasp shape control of Deformable Linear Objects (DLOs). As a common decision backbone, we introduce Geometry-Pointer-Flow (GPF), a geometry-grounded policy that separates grasp-location selection from grasp-conditioned motion generation. Its geometry-only variant reduces one-step executed shape error by 32.8% relative to a DLO-specific diffusion policy, while using 18.7 times fewer parameters and achieving approximately 193 times faster inference. On this backbone, we compare physical context represented by ground-truth parameters, estimated parameters, and learned interaction-history representations, for both forward prediction and executed control. For prediction, ground-truth physical parameters reduce next-shape error by 15.8% over geometry alone, and estimated parameters are slightly more predictive than interaction history. This ordering does not carry over to control: estimated parameters provide no detectable one-step control gain, whereas history-conditioned GPF reduces executed error by 9.9% relative to geometry-only GPF across 470 paired simulation trials. In closed loop, interaction history improves strict-threshold attainment in simulation and yields the strongest zero-shot performance on hardware. All policies are trained exclusively in simulation and transferred to the physical robot without real-world training or fine-tuning. These results show that physical context should be evaluated by the decisions it supports rather than by predictive accuracy alone. Code will be released upon acceptance.

新论文 · v1arXiv:2611.14272

面向异步疫情暴发的跨区域疫情预测联邦学习

Federated Learning for Cross-Regional Epidemic Forecasting with Asynchronous Outbreaks

Ruibin Liu, Francisco Fernandes, Xuanfeng Li, Zige Liu, André Salgado, Chitin Hon, Zifeng Yang, Arlindo Oliveira 等 9 位作者

AI 速读 基于摘要

作者报告,在广东、澳门和葡萄牙的异步COVID-19疫情中,用联邦学习训练LSTM做短期预测,精度接近集中式训练且保持数据本地化。

cs.LG

查看原文摘要

Objective: Epidemic outbreaks are often asynchronous across regions, yet collaborative forecasting is hampered by privacy laws and heterogeneous public health interventions. We developed and evaluated, as a proof of concept, a federated learning (FL) framework for cross-regional COVID-19 forecasting under asynchronous outbreaks among Guangdong, Macau, and Portugal, while maintaining data sovereignty. Methods: Using daily case data from WHO and China CDC for the three regions, whose outbreaks were asynchronous and interventions heterogeneous, we trained Long Short-Term Memory networks via FL for short-term forecasting, benchmarked against localized and centralized training using Root Mean Square Error, Mean Absolute Error, and Symmetric Mean Absolute Percentage Error. All experiments used the Flower FL framework with consistent hyperparameters across sites. Publicly available, aggregated case-count data were used so that the centralized benchmark could be computed as a reference. Results: The dataset comprised 1,233 daily observations (411 days) of new confirmed COVID-19 cases from November 24, 2021, to January 8, 2023. The earlier Omicron wave in Portugal supplied transmission dynamics that improved forecasts in the later-onset regions of Macau and Guangdong. The FL model achieved a normalized Root Mean Square Error of 0.028, an 88.3% improvement over the local model (0.240) and comparable to the centralized model, with network overhead mainly determined by model size and aggregation rounds. Conclusion: FL achieved short-term forecasting accuracy close to centralized training while maintaining data residency, with acceptable overhead. Leveraging asynchronous outbreaks across regions may offer a practical path to privacy-preserving collaborative forecasting, though prospective validation is required.

版本更新 · v9arXiv:2502.18770

奖励塑形以缓解RLHF中的奖励黑客问题

Reward Shaping to Mitigate Reward Hacking in RLHF

Jiayi Fu, Xuandong Zhao, Chengyuan Yao, Heng Wang, Qi Han, Yanghua Xiao, Yuxia Wang

AI 速读 基于摘要

提出Preference as Reward(PAR)奖励塑形方法,将中心化奖励经sigmoid变换,以有界且快速上升后饱和的信号缓解RLHF中的奖励黑客并稳定训练。

cs.LG · cs.AI · cs.CL

查看原文摘要

Reinforcement learning from human feedback (RLHF) is widely used to align large language models with human preferences, but it remains vulnerable to \emph{reward hacking}, whereby a policy exploits flaws in the reward function at the expense of the intended behavior. Reward shaping can stabilize training and partially mitigate reward hacking, yet its design principles remain underexplored. Our systematic study of common shaping methods suggests that shaped rewards should be bounded and should rise rapidly before gradually saturating. We introduce \emph{Preference as Reward} (PAR), which applies a sigmoid to centered rewards to produce a signal that reflects the reward model's latent preferences. We show that PAR has a variance-reduction property that stabilizes training and substantially widens the window for effective early stopping. Using Proximal Policy Optimization (PPO) and Gemma2-2B, PAR consistently outperforms the other shaping methods evaluated and demonstrates high data efficiency and robustness. Comparisons with unshaped rewards across four base models and four reinforcement learning algorithms show that PAR is effective across models and particularly beneficial for actor--critic methods when value estimates become unstable. The code is available at https://github.com/PorUna-byte/PAR.

新论文 · v1arXiv:2611.14267

通过设计训练数据实现抗多普勒效应的鲁棒信道估计神经网络

Achieving Robust Channel Estimation Neural Networks on Doppler effects by Designed Training Data

Dianxin Luan, John Thompson

AI 速读 基于摘要

作者提出一套合成训练数据的设计准则,使离线训练的神经网络无需先验信息或在线训练,即可在不同多普勒频移和功率延迟谱(PDP)的无线信道上稳健地估计信道。

eess.SP · cs.AI

查看原文摘要

Channel estimation is crucial in wireless communication systems. Many existing works train and test their models using the same or similar channel. However, practical channels are infinitely diverse and time-variant while data-driven algorithms often degrade on new and previously unseen channels. This prohibits the practical implementation of neural networks for channel estimation, particularly in high speed scenarios characterized by rapidly channel profile changes and very high Doppler shifts. Online training can fine-tune models to adapt to new channels, but requires high computation resource and incurs significant latency for physical-layer devices. Moreover, online training cannot exhaustively cover all possible channels because there are infinitely many possible channels. Therefore, we investigate the ability of neural networks to generalize to wireless channels. This paper proposes design criteria to generate synthetic training data, which guaranty that the resulting networks perform robustly across wireless channels, especially for very high Doppler shifts and different Doppler spectra. It ensures that offline-trained neural networks require no prior information or online training to precisely estimate the new channels. To demonstrate general applicability, we use neural networks with different levels of complexity to show that the generalization achieved appears to be independent of architecture. From simulation results, neural networks achieve a certain performance across wireless channels with different unseen power delay profiles (PDP) and Doppler shifts.

新论文 · v1arXiv:2611.14266

面向涡扇发动机可解释健康表征学习的物理约束自编码器

Physics-Constrained Autoencoder for Interpretable Health Representation Learning in Turbofan Engines

Leonardo Baldo, Jokin Alcibar Ibarzabal, Daniel Cisneros Acevedo, Kai Goebel, Manuel Arias Chao

AI 速读 基于摘要

提出一种将物理方程嵌入解码器与损失函数的物理约束自编码器,使潜变量对应预定义物理量,从而获得可解释的部件级健康指标。

cs.LG · eess.SP

查看原文摘要

Health Indices (HIs) summarize degradation from operational data and support diagnostic and prognostic tasks in Prognostics and Health Management (PHM). Their usefulness depends on capturing degradation and interpreting system condition. Autoencoders learn such representations from unlabelled monitoring data; however, when training is driven only by reconstruction, the physical meaning of latent variables remains undefined, limiting their interpretation and diagnostic value. This work proposes a physics-constrained autoencoder that embeds system knowledge as an inductive bias in the decoder architecture and as a learning bias in the loss function. The decoder contains differentiable physical equations that receive latent variables and operating conditions as inputs, structurally guiding each latent variable to represent a predefined physical quantity and enabling component-level analysis before aggregation into a system-level HI.The methodology is benchmarked on the N-CMAPSS dataset against alternative representations. Reconstruction reaches an $R^2$ of 0.9993 and an MAE of 0.0036, comparable to fully data-driven models. After operating-condition correction, the inferred physical quantities track degradation, and their aggregation produces an HI with a Spearman correlation of 0.9791 with the ground truth, an RMSE of 0.0286, and an MAE of 0.0233. The methodology is further evaluated using a single model trained across four datasets representing distinct degradation scenarios. This model preserves component-level signatures that distinguish compression-side from expansion-side degradation without diagnostic labels.Finally, the proposed framework enables degradation trends to be visualized on component maps, providing a health representation in a form familiar to engine operators and domain experts.

新论文 · v1arXiv:2611.14263

物理链:以工程启发的大语言模型推理支持故障诊断

Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning

Wenqi Zhou, Leonardo Baldo, Kai Goebel, Manuel Arias Chao

AI 速读 基于摘要

提出 Chain of Physics(CoP)框架,利用由资产文档自动构建的约束知识图谱检索故障传播链,并以图路径作为上下文示例提升 LLM 故障诊断准确率。

cs.LG · eess.SP

查看原文摘要

Fault diagnosis in complex systems requires linking observed changes in physical quantities to the failure mechanisms that produce them. Experienced engineers perform this task by combining sensor information with knowledge of system behavior and fault propagation. Large Language Models (LLMs) can support this process, but their diagnostic reasoning depends on the availability of asset-specific engineering knowledge and on how this knowledge is represented and used during inference. This work introduces Chain of Physics (CoP), an LLM-based fault-diagnosis framework built around a Constrained Knowledge Graph (CKG) generated automatically from asset-specific reference documentation. CoP addresses failure-sensor association from textual engineering knowledge. The CKG stores diagnostic chains connecting failure modes, changes in physical quantities, and monitoring sensors. During inference, semantically similar graph paths are retrieved for each question and used as both information and in-context examples for the reasoning process. Candidate failure modes are extracted from the question and analysed independently through dedicated LLM calls, which generate plausible failure-to-observation chains. A final decision module compares these chains with the available answer choices. CoP is evaluated on the FailureSensorIQ benchmark across four industrial asset classes and three LLMs. Compared with direct prompting and conventional Retrieval-Augmented Generation (RAG), CoP improves diagnostic accuracy across all evaluated models, with gains ranging from 7.8 to 19.6 percentage points and from 11.7 to 18.2 percentage points, respectively. The results show that structured engineering knowledge can improve LLM-based diagnostic reasoning when graph retrieval is combined with in-context examples of fault propagation.

新论文 · v1arXiv:2611.14262

脉冲神经网络强化学习中的循环模块化结构

Recurrent Modular Structure in Spiking Neural Network Reinforcement Learning

Vikram Ramavarapu, Himanshu Udupi, Ashish Gautam

AI 速读 基于摘要

作者提出将循环脉冲神经网络划分为具有固定角色的社区(CoRe SNN),并用局部三因子学习规则训练,在多个控制任务上比较模块化程度的影响。

cs.AI · cs.LG · cs.NE

查看原文摘要

Biological neural circuits are both modular and recurrent, with dense communities sparsely linked to one another. Spiking neural networks (SNNs) for reinforcement learning are usually feed-forward, and it is unclear how to obtain functional modules in a recurrent SNN or what they buy. In this work, we introduce a class of spiking networks, called Community Recurrent SNNs (CoRe SNNs): recurrent networks partitioned into communities with fixed roles. A controller community receives the stimulus, each action has its own community, and latent communities carry internal state. Spiking activity is then a walk between communities, and the action is the community the walk reaches. All learning is local and three-factor, and the recurrent communities are closer to cortical microcircuits than a feed-forward actor. We compare three regimes for obtaining the communities: dynamic modularity, in which a new learning rule we introduce, Map-STDP, encourages modular structure during learning; partial modularity, in which a stochastic block model (SBM) initialization enforces it partly; and full modularity, in which sealing enforces it fully. On CartPole, across three spiking neuron models, Map-STDP improves learning over the same network without it matches full modularity (sealed communities) on two of the three models, and makes the observed spike walk more compressible. Replacing the feed-forward actor of a TD-STDP actor-critic with recurrent action communities improves on the feed-forward network on CartPole and LunarLander, and matches it on Acrobot. How strongly to enforce modularity depends on the task: full modularity helps most on Acrobot, while on LunarLander the dynamic, partial and full regimes perform alike. Overall, these recurrent modular networks can match or even improve upon feed-forward approaches, with improvements in bio-plausibility and energy efficiency.

版本更新 · v2arXiv:2611.10398

冷缓存下表格数据格式的测量:基于真实数据集的序列化、扫描与索引性能复现基准

Measuring Tabular Data Formats Cold: A Replicated Cold-Cache Benchmark of Serialization, Scan, and Index Performance on Real Datasets

Asra Fathima, Kristoffer Roberts

AI 速读 基于摘要

该研究在显式冷缓存、随机执行顺序和三次独立会话条件下,对两种真实数据集上的十五种表格数据格式与访问路径配置进行基准测试,并用统计检验分析性能差异。

cs.DB · cs.PF · cs.SE

查看原文摘要

Choosing a file format for tabular data is a routine engineering decision, yet published comparisons often time reads served from the operating-system page cache, use one session, or rely on a single synthetic dataset. This article benchmarks fifteen format and access-path configurations (CSV, JSON Lines, Pickle, Feather, Parquet, ORC, DuckDB, and SQLite, with several access paths) on two real public datasets, New York City taxi trips and United States airline on-time records, at 50,000 to 3 million rows. Every measurement uses an explicitly cold cache, randomized execution order, and three independent sessions (with restarts on the laptop), and is analyzed with bootstrap intervals and Holm-adjusted permutation tests. Parquet answered a filtered aggregation 2.6 to 11 times faster than CSV, while JSON Lines was 10 to 27 times slower. A secondary index made SQLite queries 2.6 to 4.8 times slower on randomly ordered data and helped only on data sorted by the filtered column, at low selectivity. A row filter inside the Parquet reader was significantly faster than a projected scan on flight data from one million rows and on both datasets at three million, and row-group skipping needs several row groups, which the default writer produced only at 3 million rows. A 4 GB Linux host ran out of memory on configurations that a 24 GB laptop completed and reversed some orderings, such as Pickle versus Parquet. Code, derived data, and raw timings are released.

新论文 · v1arXiv:2611.14260

Lilo:面向儿童数字沟通的多智能体对话沙盒

Lilo: A Multi-Agent Conversational Sandbox for Children's Digital Communication

Ofri Elbaum, Amit Malik, Tomer Malkevich, Zohar Elyoseph, Adir Solomon, Rotem Dror, Oshrat Ayalon

AI 速读 基于摘要

Lilo 是一个多智能体对话沙盒,让儿童在 AI 同伴争吵中练习应对不愉快消息,并由导师角色通过“停—想—做”红绿灯进行引导。

cs.HC · cs.AI

查看原文摘要

Children's peer conflicts increasingly play out in group chats, where tone and timing are stripped away, and a hurtful message is easier to send than to say aloud. We present Lilo, a multi-agent conversational system that lets children practice such conversations, so they are better prepared when they encounter them in real digital communication. In Lilo, the child joins two AI-driven peers mid-argument, coached by a mentor character, also named Lilo, through a Stop-Think-Act traffic light. Through an exploratory study with 28 children (aged 9-11), we examine how children engage with Lilo's simulated peer conflict and the mentor's traffic-light interventions. The study included an intervention with Lilo, surveys before and after the intervention, and exit interviews. Participants reported significantly higher self-efficacy for coping with unpleasant messages after their interaction with Lilo. They felt safe experimenting, knowing nothing they wrote would be held against them.

版本更新 · v2arXiv:2606.00625

NICE:面向声明式与机器可校验漏洞复现的框架

NICE: A Framework for Declarative and Machine-Checkable Vulnerability Reproduction

Minh-Luân Nguyen, Olivier Levillain, Julien Malka, Stefano Zacchiroli, Théo Zimmermann

AI 速读 基于摘要

提出基于 NixOS 声明式配方构建并自动校验漏洞环境的 NICE 框架,并构建含 56 个已复现漏洞的公开档案,评估 LLM 辅助配方生成的可行性。

cs.CR

查看原文摘要

Reproducing software vulnerabilities is fundamental to security researchers, open-source maintainers, and educators. Yet, vulnerabilities are often hard to reproduce, and even when they can be reproduced once, recreating a software environment where the vulnerability can be exploited becomes harder and harder over time. We present NICE, the NIx CvE reproduction framework, which uses declarative recipes to build and automatically validate vulnerable environments. In NICE, a reproduced CVE comprises one or more NixOS virtual machine configurations, a scripted exploitation scenario, and machine-checkable assertions that provide factual evidence of exploitation. This design facilitates sharing, validation, review, and long-term reproducibility. Building on NICE, we construct a public archive of 56 reproduced vulnerabilities spanning multiple CWE categories, attack vectors, and target types (user-space, system software, kernel, and graphical applications), combining manually authored recipes with recipes produced by an LLM-based automated pipeline and merged after human review. We evaluate the feasibility of the automated pipeline on 110 real-world CVEs, achieving fully automated reproduction in 54.5% of the cases, at an average cost of $0.73 per CVE. The evaluation demonstrates that NICE provides a practical target for LLM-assisted recipe generation, while also identifying where human refinement or additional automation remains necessary.

新论文 · v1arXiv:2611.14257

Elastic-WAM:面向高效机器人控制的自适应时空想象

Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control

Haitian Li, Tianfu Li, Xuxi Zhao, Zizheng Liu, Yangcheng Yu, Yiwen Hou, Zeyu Xiao, Mutian Xu 等 11 位作者

AI 速读 基于摘要

提出 Elastic-WAM,用统一时空细化需求场自适应分配世界模型的计算,在降低推理开销的同时提升机器人控制表现。

cs.RO · cs.CV

查看原文摘要

World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred refinement depths vary across tasks and states, while different future regions exhibit varying relevance to action generation. Motivated by these findings, we propose Elastic-WAM, which adaptively allocates world refinement computation across temporal denoising time and spatial future space. A unified spatiotemporal refinement demand field governs when to stop world refinement, how far to advance each denoising step, and which regions to refresh. We parameterize this field with a shared temporal basis and spatial amplitudes, and learn it through a three-stage action-grounded supervised procedure. At inference, the learned field guides recurrent sparse world refinement to improve task success while reducing inference overhead. Evaluations across diverse simulation benchmarks and real-world long-horizon manipulation demonstrate state-of-the-art control performance with reduced inference latency.

新论文 · v1arXiv:2611.14256

跨场景自演化多模态智能体综述与分析

A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents

Jingjing Jiang

AI 速读 基于摘要

该综述以经验生成、反馈获取与更新巩固三阶段自演化循环为分析框架,考察多模态推理、多模态生成、GUI与Web导航、具身操作四个场景中自演化机制跨场景迁移的不对称性。

cs.AI

查看原文摘要

Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey investigates the structural source of asymmetric mechanism transfer across four scenarios: multimodal reasoning, multimodal generation, GUI and Web navigation, and embodied manipulation. We first formalize the self-evolving multimodal agent by four criteria and a differentia of self-reference, and adopt the three-stage self-evolving loop of experience generation, feedback acquisition, and update consolidation as our analytical framework to position the scenarios along ceilings on rollout count and feedback fidelity. Comparing self-evolving with fixed loops within each scenario separates the limitations that the scenario imposes from those inherent in the self-evolving design. We then recast each mechanism as a trade-off that raises a scarce factor by presupposing a task-structural resource, such as output equivalence or checkable outcomes, and judge it portable, conditional, blocked, or redundant across scenarios. We attribute the asymmetry to divergent combinations of scarce factors and resources across opposite transfer directions, and identify the matched-budget measurements that could overturn these still untested verdicts.

新论文 · v1arXiv:2611.14254

位置很重要:面向扩散个性化人脸隐私的稀疏潜方差攻击

Location Matters: Sparse Latent-Variance Attacks for Face Privacy against Diffusion Personalization

Shuting Yang, Shuxin Li, Linyan Dai, Xinwei Zhang, Dong Huang, Renyang Liu, See-Kiong Ng

AI 速读 基于摘要

提出稀疏对抗保护框架 SEAL,仅修改人脸图像 5% 的空间位置,在保持高视觉质量的同时干扰扩散模型对身份的个性化学习。

cs.CV · cs.CR

查看原文摘要

Text-to-image diffusion models can learn and reproduce an individual's identity from only a few reference photos, creating risks of unauthorized and misleading content generation. Proactive defenses address this risk by adding adversarial perturbations to facial images before release, thereby disrupting identity acquisition during downstream personalization. However, existing methods typically rely on dense $L_\infty$-bounded perturbations, whose accumulated distortions can become visible around facial structures. Recent methods improve protected-image quality, but often at the cost of reduced protection effectiveness. In this paper, we propose Sparse Encoder Attack on Latent Variance (SEAL), a sparse adversarial protection framework that modifies only 5% of the spatial locations in a facial image. SEAL combines a differentiable top-k masking scheme that jointly optimizes perturbation locations and values with a variance-oriented objective over the frozen VAE encoder's latent distribution to disrupt identity-consistent representations. A saliency-guided dispersion penalty further discourages perturbation concentration in perceptually salient facial regions. Experiments on CelebA-HQ and VGGFace2 show that SEAL achieves the best protected-image quality among the compared methods, exceeding 41 dB PSNR with 0.97 SSIM and at most 0.07 LPIPS, while reducing identity similarity to at most 0.15 after diffusion personalization. These results demonstrate that sparse location optimization enables strong identity protection while preserving high visual quality. Code and data are available at https://github.com/Lvxan/SEAL

新论文 · v1arXiv:2611.14252

语义链:从可达事实到有据可依的答案

Semantic Chains: From Reachable Facts to Justified Answers

Misha Andreev

AI 速读 基于摘要

该文在逻辑事实图模型下,研究如何从问题出发搜索到能支撑完整答案的根事实,并把论证组织成由若干相互衔接的陈述构成的语义链。

cs.CL

查看原文摘要

How can the facts that justify an answer be found from a question and presented as a sequence of connected statements? This paper models a context as a graph of logical facts and takes as given which expressions represent each fact. A parent fact can express a relation among its subfacts, and a preserving edge allows the content of a subfact to be recovered within a full representation of its parent. Suppose a root fact justifies the full answer and a path of preserving edges leads from that root to a fact that designates an object shared by the question and the answer. Under the conditions of the model, a search starting from the objects in the question reaches the root and covers every fact in the selected expansion. The root then admits a text that forms a single link connecting the question to the full answer and justifying it. For chains with several links, the paper gives a complete enumeration of candidate orders within the stated class and specifies when the link texts jointly preserve the justification and support every transition.

版本更新 · v2arXiv:2606.12247

超越第三人称审计:面向用户中心的LLM偏见研究的情境化交互审计

Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research

Andrés Abeliuk, Cinthia Sanchez Macias, Valentina Alarcón, Álvaro Madariaga, Claudia Lopez

AI 速读 基于摘要

提出情境化交互审计(SIA)框架,用于统一和比较以用户为中心的第一人称LLM偏见研究。

cs.CY · cs.CL

查看原文摘要

Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural blind spot because the user is absent from the audit. In practice, LLMs are used in open-ended, personal interactions, during which the model implicitly represents the user and adjusts its responses accordingly. When identical requests yield different responses depending on who is asking, bias manifests not in how the model describes others but in how it treats its interlocutor. Empirical first-person bias studies are multiplying, but they use different cues, outcomes, and validation choices, which makes their results hard to compare. We propose Situated Interaction Auditing (SIA), a shared diagnostic framework for this literature. It introduces a typology of user profile signals---names and surface markers, writing style and dialect, and stated identity---together with design principles and outcome measures that let studies be compared and accumulated. We instantiate the framework in a case study of Chilean first and last names across nine task domains and three models, and we close with guidance for practitioners and open questions for researchers.

版本更新 · v3arXiv:2605.11911

理解预测编码中的样本效率

Understanding Sample Efficiency in Predictive Coding

Gaspard Oliviers, Elene Lominadze, Rafal Bogacz

AI 速读 基于摘要

该文通过“目标对齐”指标在深度线性网络中解析并实证比较预测编码(PC)与反向传播(BP)的学习效率,作者报告PC更高效,且在深层、窄、预训练网络中更明显。

cs.LG

查看原文摘要

Predictive Coding (PC) is an influential account of cortical learning. Much of recent work has focused on comparing PC to Backpropagation (BP) to find whether PC offers any advantages. Small scale experiments show that PC enables learning that is more sample efficient and effective in many contexts, though a thorough theoretical understanding of the phenomena remains elusive. To address this, we quantify the efficiency of learning in BP and PC through a metric called ``target alignment'', which measures how closely the change in the output of the network is aligned to the output prediction error. We then derive and empirically validate analytical expressions for target alignment in Deep Linear Networks. We show that learning in PC is more efficient than BP, which is especially pronounced in deep, narrow and pre-trained networks. We also derive exact conditions for guaranteed optimal target alignment in PC and validate our findings through experiments. We study full training trajectories of linear and non-linear models, and find the predicted benefits of PC persist in practice even when some assumptions are violated. Overall, this work provides a mechanistic understanding of the higher learning efficiency observed for PC over BP in previous works, and can guide how PC should be parametrised to learn most effectively.

新论文 · v1arXiv:2611.14247

人机谈判中基于持续学习的个性化情感感知

Personalized Affective Perception via Continual Learning in Human-Agent Negotiation

Mehmet Onur Keskin, Berk Buzcu, Nikhil Churamani, Reyhan Aydogan, Hatice Gunes, Catholijn Jonker

AI 速读 基于摘要

作者提出将持续学习的面部表情识别(CLIFER)与差分反馈结合,在实时人机谈判中个性化效价-唤醒感知并调整智能体策略。

cs.AI · cs.HC · cs.LG · cs.MA · cs.RO

查看原文摘要

Self-interested intelligent agents that negotiate with humans should interpret nonverbal expressions and adapt their behavior accordingly. However, generic facial-affect models degrade across individuals and contexts, creating a generalization gap. We introduce an affect-adaptive negotiation strategy that incorporates Continual Learning with Imagination for Facial Expression Recognition (CLIFER) to personalize valence-arousal perception in real time. Differential feedback converts changes in valence-arousal direction and intensity into adjustments of the agent's target utility. An asynchronous architecture updates CLIFER in the background during live interaction. In a counterbalanced within-subject study in which 66 participants negotiated with a humanoid robot, the CL-enabled agent achieved significantly higher individual utility and elicited higher participant concession rates than the FaceChannel baseline. The CL condition yielded significantly higher mean arousal estimates, alongside a broader output range. Participant utility and Nash distance did not change significantly between conditions. These outcomes support the practical value of coupling continual affective personalization with differential feedback for real-time negotiation.

版本更新 · v2arXiv:2508.08807

面向节点与超边的高效属性超图嵌入

Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges

Yiran Li, Gongyao Guo, Chen Feng, Jieming Shi

AI 速读 基于摘要

提出 SAHE,统一学习属性超图中节点与超边的嵌入,并通过高阶相似度与近似优化兼顾质量与效率。

cs.SI

查看原文摘要

An attributed hypergraph comprises nodes with attributes and hyperedges that connect varying numbers of nodes. Attributed hypergraph node and hyperedge embedding (AHNEE) maps nodes and hyperedges to compact vectors for use in important tasks such as node classification, hyperedge link prediction, and hyperedge classification. Generating high-quality embeddings is challenging due to the complexity of attributed hypergraphs and the need to embed both nodes and hyperedges, especially in large-scale data. Existing solutions often fall short by focusing only on nodes or lacking native support for attributed hypergraphs, leading to inferior quality, and struggle with scalability on large attributed hypergraphs. We propose SAHE, an efficient and effective approach that unifies node and hyperedge embeddings for AHNEE computation, advancing the state of the art via comprehensive embedding formulations and algorithmic designs. First, we introduce two higher-order similarity measures, HMS-N and HMS-E, to capture similarities between node pairs and hyperedge pairs, respectively. These measures consider multi-hop connections and global topology within an extended hypergraph that incorporates attribute-based hyperedges. SAHE formulates the AHNEE objective to jointly preserve all-pair HMS-N and HMS-N similarities. Direct optimization is computationally expensive, so we analyze and unify core approximations of all-pair HMS-N and HMS-N to solve them simultaneously. To enhance efficiency, we design several non-trivial optimizations that avoid iteratively materializing large dense matrices while maintaining high-quality results. Extensive experiments on diverse attributed hypergraphs and 3 downstream tasks, compared against 11 baselines, show that SAHE consistently outperforms existing methods in embedding quality and is up to orders of magnitude faster.

版本更新 · v3arXiv:2605.04574

VL-UniTrack:面向无人机-地面视觉跟踪的视觉-语言提示统一框架

VL-UniTrack: A Unified Framework with Visual-Language Prompts for UAV-Ground Visual Tracking

Boyue Xu, Ruichao Hou, Tongwei Ren, Gangshan Wu

AI 速读 基于摘要

提出一个共享编码器加视觉-语言视角提示的统一框架,用于无人机与地面双视角对同一目标的联合跟踪。

cs.CV

查看原文摘要

UAV-ground visual tracking (UGVT) aims to simultaneously track the same target from both UAV and ground views. However, existing two-stream methods suffer from isolated feature extraction and rely heavily on implicit appearance matching, which often fails to establish reliable cross-view correspondence under drastic viewpoint discrepancies, thereby leading to unstable tracking. To address these issues, we propose VL-UniTrack, a unified framework enhanced by visual-language prompts. By encoding features from both views with a single shared encoder, our method reduces feature isolation between the two views and enables sufficient cross-view interaction. To alleviate the ambiguity caused by appearance-only matching, we further design a visual-language viewpoint prompting module that fuses language descriptions with visual features to generate learnable prompts. These prompts are then injected into a prompt-guided cross-view adapter to facilitate cross-view interaction and guide the learning of view-specific feature representations. In addition, we introduce a confidence-modulated mutual distillation loss to regularize training by suppressing noise propagation. Extensive experiments demonstrate that VL-UniTrack achieves state-of-the-art performance on the latest benchmark. The code is available at https://github.com/xuboyue1999/VL-UniTrack.git.

新论文 · v1arXiv:2611.14246

SinkState:面向高效混合LLM服务的循环状态即时SVD

SinkState: On-the-Fly SVD of Recurrent States for Efficient Hybrid LLM Serving

Haolin Jiang, Weihang Li, Zhongzhu Zhou, Jinwen Pan, Santosh Pandey, Hang Liu

AI 速读 基于摘要

作者提出SinkState,利用线性注意力状态的低秩特性,在推理过程中对循环状态做自适应低秩存储与即时SVD,以降低混合LLM服务的内存占用和解码开销。

cs.LG

查看原文摘要

Hybrid models combine softmax attention with linear attention, which compresses history into fixed-size recurrent states to balance model quality and inference efficiency. However, linear attention has not pushed this compression to its limit: we find that the queries, keys, and values of linear layers concentrate in a stable, low-dimensional subspace, a phenomenon we call the linear attention sink, so each state is effectively low-rank, with a rank that varies across states. Yet existing serving systems keep these redundant states dense, reading and rewriting them in full at every decoding step, so their memory traffic grows with the batch size and dominates the decoding cost. Thus SinkState stores each recurrent state in an adaptive low-rank form throughout inference with buffered updates and a local SVD restricted to the top subspace. SinkState further consolidates the remaining components asynchronously on the CPU. On four hybrid models with Mamba-2 and Gated DeltaNet (GDN) layers, from 4B to 120B parameters, SinkState reduces the peak memory of recurrent states by up to 2.6x (1.9x on average) and speeds up decoding by up to 1.58x (1.25x on average) over Mamba-SSM and FLA, while maintaining accuracy.

新论文 · v1arXiv:2611.14242

PARLEY:通过合作式非对称谜题评估大语言模型协作

PARLEY: Evaluating LLM Collaboration Through Cooperative Asymmetric Puzzles

Javier Hernandez, Andrew D. Wilson

AI 速读 基于摘要

作者提出 PARLEY 平台,用四类认知心理学启发的非对称谜题任务研究 LLM 智能体协作,并据此归纳失败类型、尝试分类引导的干预。

cs.MA

查看原文摘要

As large language models power autonomous agents, understanding how they collaborate and where they fail becomes critical. We introduce PARLEY, an extensible platform for studying LLM agent collaboration through four asymmetric puzzle tasks grounded in cognitive psychology (referential communication, joint coordination, perspective-taking, and spatial reasoning). GPT-4o agent pairs succeeded in 60.5% of conversations (N=400, 100 per task), with task-level variation (34-80%) reflecting distinct collaborative demands. From these conversations, we derived the data-driven PAC taxonomy: six failure types organized into Perception (visual interpretation and spatial reasoning), Adaptation (progress tracking and feedback integration), and Coordination (verification and grounding). Failure to incorporate external feedback was a critical indicator of unsuccessful collaboration, with agents repeatedly applying unsuccessful strategies. We also show that a taxonomy-guided intervention (N=200) improved average task success to 70.5%. These results demonstrate how PARLEY can be used to derive meaningful, data-driven insights that can in turn lead to improved agentic collaboration.

新论文 · v1arXiv:2611.14241

DyShip:利用声学特征从双人对话中分类说话人关系

Dyship: Leveraging Acoustic Features For Speaker Relationship Classification From Dyadic Conversations

Kieran Sturges, Thomas Thebaud, Yaohan Guan, Najim Dehak

AI 速读 基于摘要

该论文提出 DyShip 框架,在 Seamless Interaction 语料库上比较五种语音表示,用于从双人对话中判断说话人之间的熟悉程度与亲属关系。

cs.CL · cs.AI

查看原文摘要

We introduce DyShip, a framework for classifying speaker familiarity and kinship from dyadic conversations in the Seamless Interaction corpus. We compare five speech representations: spectrograms, MFCCs, self-supervised WavLM representations, x-vectors, and estimated articulatory movements. Spectral features perform best for familiarity classification, reaching an accuracy of 87.81%, while WavLM achieves the highest kinship accuracy of 85.17%. X-vectors and articulatory features yield weaker results on familiarity classifiaction, but shine for kinship classification, with an AUC of 0.909 for x-vectors. Most classifiers exceed previously reported human and audio language model scores on the same dataset. These findings highlight the potential of conventional acoustic features for relationship inference and motivate further investigation of the conversational cues captured by different representations.

新论文 · v1arXiv:2611.14239

部分参与下满足一般方差条件的联邦平均算法研究

On Federated Averaging with Partial Participation under a General Variance Condition

Ziming Wang, Kun Huang, Karl Henrik Johansson, Shi Pu

AI 速读 基于摘要

在ABC方差条件下分析部分参与FedAvg的收敛性,给出不依赖有界梯度差异假设的有限时间平稳性界与几乎必然收敛结果。

math.OC · cs.DC · cs.LG

查看原文摘要

In this paper, we study the convergence of Federated Averaging (FedAvg) with partial participation under a general variance condition. In each communication round, the server samples $S$ of the $n$ clients uniformly at random without replacement. The stochastic gradients are assumed to satisfy the so-called ABC condition, which allows their variance to grow with the local objective gaps. For smooth nonconvex objectives, we establish a finite-time stationarity bound in terms of the heterogeneity measure $σ_f^\star:=f^\star-\frac{1}{n}\sum_{i=1}^n f_i^\star$ and the client sampling factor $I_S:=(n-S)/(n-1)$. Here, $f^\star$ and $f_i^\star$ denote the infima of the global average objective and client $i$'s local objective, respectively. The bound exhibits a linear speedup in the number of sampled clients $S$ and recovers the full-participation result when $S=n$. Under diminishing stepsizes, we further prove that the gradient norm converges to zero both in expectation and almost surely. Notably, compared with existing analyses of FedAvg with partial participation, our results require no additional data heterogeneity assumption such as bounded gradient dissimilarity (BGD), and the sampling-induced term in our bound is not amplified by the number of local updates at the leading order. The importance of removing the BGD assumption is illustrated by an example that is smooth and lower bounded but violates BGD, yet is covered by our analysis.

版本更新 · v2arXiv:2602.13414

FUTON:用于隐式神经表示的傅里叶张量网络

FUTON: Fourier Tensor Networks for Implicit Neural Representations

Pooya Ashtari, Pourya Behmandpoor, Nikos Deligiannis, Aleksandra Pizurica

AI 速读 基于摘要

作者提出 FUTON,用低秩张量分解参数化广义傅里叶级数系数,以提升隐式神经表示的收敛速度、精度与效率。

eess.IV · cs.CV · cs.LG · eess.SP

查看原文摘要

Implicit neural representations (INRs) have emerged as powerful tools for encoding signals, yet dominant MLP-based designs often suffer from slow convergence, and how their accuracy depends on their size is known only empirically. We introduce FUTON (Fourier Tensor Network), which models signals as generalized Fourier series whose coefficients are parameterized by a low-rank tensor decomposition, read out by a linear or MLP head. FUTON combines complementary inductive biases: Fourier bases capture smoothness and periodicity, while the low-rank parameterization enforces low-dimensional spectral structure. Beyond universal approximation, we show that with a linear head, the best FUTON's error splits exactly into the truncation of the signal's series and the best low-rank error of its coefficients, which we bracket from the samples before training, with a FUTON that attains the upper bound. On image fitting, occupancy volumes, and novel view synthesis, against twelve INRs of matched size, FUTON achieves the best average quality, reaches the final quality of each task's strongest baseline 4-34x sooner than that baseline, infers fastest, and trains in the least memory.

新论文 · v1arXiv:2611.14236

StaRSE:基于符号编码静态编码器的紧凑俄语句子嵌入

StaRSE: Compact Russian Sentence Embeddings with a Sign-Coded Static Encoder

Boris Malashenko, Ivan Jarsky, Egor Soldatov, Vladislav Luzhnov, Sviatoslav Stumpf, Vladislav Shmatkov, Viacheslav Shalamov, Andrey Stankevich 等 9 位作者

AI 速读 基于摘要

StaRSE 是一种紧凑的俄语静态句子编码器,它把词元方向存为符号位、范数单独存储,部署时无需 Transformer 推理,以低 CPU 延迟取得优于静态基线的检索效果。

cs.CL · cs.IR

查看原文摘要

Transformer sentence encoders provide strong retrieval quality, but their inference cost becomes a bottleneck when embeddings must be produced on CPUs or refreshed frequently. We introduce StaRSE, a compact Russian static sentence encoder that removes Transformer inference at deployment time: token directions are stored as sign bits, token norms are stored separately, and sentences are encoded by mean pooling over norm-scaled sign directions. StaRSE is initialized from ruBERT-base, fine-tuned on Russian adjacent-sentence and task-shaped pairs, and post-trained with a contrastive stage that directly optimizes the sign-projected token table. On RuMTEB, StaRSE reaches a task mean of $51.16$, $7.98$ points above the strongest included static baseline. The packaged model occupies $11.3$ MiB and has a mean CPU latency of $0.08$ ms per sentence, compared with an estimated $55.7$ MiB 16-bit parameter footprint and $1.43$ ms mean CPU latency for the closest-quality contextual encoder. Ablations examine adjacent-sentence supervision, token norms, and direct sign-projected post-training.

版本更新 · v2arXiv:2607.22639

TRACE:面向企业大模型知识保持型参数化工具检索的业务规则推理课程

TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs

Sai Shruthi Sistla, Ashutosh Hathidara, Christopher Toukmaji, Mayank Shrivastava, Karthikeyan Asokkumar

AI 速读 基于摘要

TRACE 提出两阶段课程训练,在保留参数化工具知识的同时,用带推理轨迹的单束贪心解码实现企业级工具检索。

cs.AI

查看原文摘要

Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via constrained beam search. Toolsense shows that this regime has two critical drawbacks: it destroys parametric tool knowledge during training, and its beam-search decoding is too slow for real-time deployment. We introduce TRACE (Tool Retrieval via Augmented Chain-of-thought and Enterprise rules), a two-stage curriculum that resolves this dissociation. Stage 1 reuses the multi-format memorization SFT from ToolSense to seed tool knowledge with LoRA. Stage 2 is our core contribution: the model is trained to emit a thinking trace before producing a JSON list of tool tokens, using two data sources -- RRB pairs from ToolSense and queries synthesized to target business rules curated by domain experts -- both augmented with reasoning traces. This training objective preserves Stage 1 MCQ and QA probing accuracy while enabling single-beam greedy decoding at production latency. Evaluated on a combined enterprise catalog of 8,300+ tools across two enterprise product lines, TRACE training for Stage 2 not only preserves but improves tool understanding: MCQ accuracy gains +3.2 pp and QA probing gains +9 pp over Stage 1. On retrieval, TRACE achieves ~86% recall on Domain A and ~60% on Domain B -- compared to embedding baseline performance of ~27% & ~52% -- both with single-beam greedy decoding, making it directly deployable at production latency.