跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 17:39 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 18:32 — 2026-11-08 18:32（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：2026-11-08 17:39最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 17:37（北京时间）
版本更新 · v9arXiv:2606.08343

GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators

Jason Sulskis, Sathya Ravi

原文摘要

We propose GENERIC-FNO, a neural operator that embeds the metriplectic (GENERIC) degeneracy structure of nonequilibrium thermodynamics in function space, coupling reversible, energy-conserving dynamics to irreversible, entropy-producing dynamics via the degeneracy conditions. Prior structure-preserving neural operators enforce at most one conservation law or a Hamiltonian form, and thermodynamically consistent learning has been confined to finite-dimensional, graph, or particle systems. GENERIC-FNO learns the energy and entropy functionals as neural operators and builds the reversible and irreversible operators as diagonal Fourier multipliers flanked by rank-one projections that enforce both degeneracy conditions exactly, by construction, with no penalty, update projection, or residual; the Jacobi identity is not enforced. The identities hold to machine precision (~10^-13) for any initialization, dimension, or resolution, so the continuous-time dynamics conserve the learned energy and produce the learned entropy exactly, with explicit time stepping adding only an O(dt^2) drift. These are guarantees about the learned functionals within GENERIC's scope of closed conservative-dissipative dynamics, not a certificate of physical accuracy, and the (E,S,L,M) decomposition is not unique; we make this gauge freedom explicit and propose a gauge-invariant dissipation diagnostic independent of the learned functionals. Across three backbones (1D/2D FNO, DeepONet) and four canonical scalar PDEs, the guarantees transfer zero-shot over a 4x super-resolution range and hold in 3D; the diagnostic identifies the reversible and the most dissipative system in every backbone; and over 200-step rollouts, where every unconstrained model we test diverges or collapses, GENERIC-FNO stays bounded, at half the parameters but 4-10x the compute, while losing accuracy on pure transport and on the smallest 1D backbone.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01939

VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph

Yuntae Jeon, Younho Jeon, Sujin Jin, Sungho Jo, Seunghee Park

原文摘要

Learning semantic representations for 3D Gaussian Splatting has recently emerged as a promising direction for 3D scene understanding. However, existing 2D-to-3D semantic lifting approaches rely primarily on 2D segmentation supervision and lack object-level priors, causing the learned representation to be driven by local mask evidence rather than holistic object structure. In this paper, we present VLSplat, a vision-language guided approach for object-centric semantic lifting in 3D Gaussian Splatting. Our method augments mask-based lifting with object-level semantic priors derived from vision-language models and refines Gaussian representations using an object-group scene graph. The refinement is performed through two language-guided modules: intra-group refinement suppresses semantic noise within object groups, while inter-group acquisition expands object support regions by incorporating structurally relevant candidates from neighboring groups. Extensive experiments on indoor scene datasets demonstrate that VLSplat improves the semantic consistency and structural completeness of object-level categories. Our code and models are available at https://vlsplat.github.io/.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.01853

Achieving Optimal Redundancy for Small Dynamic Rank/Select Dictionaries

Gabriel Marques Domingues

原文摘要

In this paper, we study the number of bits required to construct a dynamic dictionary with optimal time for $\texttt{rank}/\texttt{select}$ operations. Using the standard (multiplication) Word-RAM model with $w$-bit words, we construct a data-structure for a dynamic $\texttt{rank}/\texttt{select}$ dictionary for a set $S\subseteq\{0,1,\cdots,u-1\}$ of $n$ elements that, given a parameter $1\leq k\leq \log^*w$, uses $$\operatorname{lg}\binom{u}{n}+\mathcal{O}(n\log^{(k)}w)\text{ bits}$$ taking optimal $\mathcal{O}(k+\log_w n)$ time (worst-case) for all operations. We show optimality for $n=w^{\mathcal{O}(1)}$ and $\log u=Θ(w)$ by extending the lower bound of Li, Liang, Yu, and Zhou [FOCS 2023] to super-polynomial universes: any dynamic dictionary for $n\leq \sqrt{u}$ elements that uses $\operatorname{lg}\binom{u}{n}+\mathcal{O}(n\log^{(k)}n)$ bits requires $Ω(k)$ time for operations. Lastly, we extend the data-structure to a dynamic fully indexable dictionary (that also supports $\texttt{rank}/\texttt{select}$ on the complement of $S$).

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01938

Parameterisation of NMC and LFP 4680 cells for electrochemical and thermal modelling

Remus Teodorescu, Nicolai A. Weinreich, Berke Bilgin, Yi Zhuang, Wenzel Prochazka

原文摘要

An electrochemical-thermal model of the 4680 cylindrical cell is presented: a Doyle-Fuller-Newman model of the electrode stack coupled to a two-node thermal balance of the roll and the can (a thermal DFN, TDFN), solved by an implicit finite-volume scheme. Two cells are parameterised from teardown geometry and open literature, with every value tagged by provenance: the Tesla NMC811/graphite tabless cell and the BYD FC4680 LiFePO4 multi-tab cell. The reaction heat is evaluated at the open-circuit potential of the particle-mean concentration, which restores the heat of mixing. Both sets are calibrated in the same way, with the test fixture identified from the measurement alone. Against the 1C and 2C charge test of Ank et al., the calibrated NMC set follows the mean can temperature within 0.52 and 1.46 K, with a contact heat of 0.94 mOhm matching the authors' estimate for their holder. For the LFP cell, 1C and 2C discharges to 2.0 V were measured on the authors' bench; the fixture conductance (0.337 W/K) follows from the energy balance and the heat capacity (277 J/K) from the cooling. With the end-of-lithiation drop of LiFePO4 restored in the cathode open-circuit potential, the calibrated set follows the can temperature within 0.44 K (1C) and 0.76 K (2C), reproduces the peaks and the relaxation after cut-off. What remains is what a single can node and a single representative particle do not describe: the axial gradient of the NMC can under contact heating, and a gradual decline of the LFP voltage before the knee at 2C, which points to the distribution of particle states in the electrode. The parameter sets (BPX, CSV) and the bench data are openly available.

eess.SY · cs.CE · physics.chem-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01937

Spade-SLAM: Sparse Correspondence Anchors for Dense Self-Supervised Visual SLAM

Julian Philipp Schmitt, Weirong Chen, Ganlin Zhang, Felix Wimbauer, Daniel Cremers

原文摘要

We introduce Spade-SLAM, a self-supervised dense visual SLAM framework that substantially narrows the long-standing performance gap to supervised methods in a zero-shot setting. By demonstrating that high-fidelity tracking can be achieved without explicit ground-truth pose and depth labels, our approach offers a highly effective and label-efficient alternative to fully supervised pretraining. Our core contribution is a complementary sparse-to-dense training regime: While a warping-based photometric loss provides a dense training signal, we stabilize the optimization and suppress drift in ambiguous regions using a sparse correspondence loss derived from image feature matches. Extensive experiments demonstrate that Spade-SLAM significantly improves robustness and accuracy compared to existing self-supervised baselines, closely rivaling SLAM systems trained with explicit pose and depth supervision. The code will be made publicly available at https://github.com/JulianPSchmitt/Spade-SLAM.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2607.26998

AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Web Penetration Agents

Ruoyu Wang, Heng Zhao, Renjie Wu, Tianhang Zheng, Mengnan Zhao, Wanyu Lin, Kui Ren

原文摘要

Large language model agents automate web penetration testing through observation-action loops, enabling defenders to influence decisions with deceptive decoy observations. Advanced agents can recognize and bypass static decoys, then refocus on real targets. We propose AgentSnare, a trajectory-adaptive deception system that expands a decoy environment alongside exploration. For online deployment, ShadowOS combines an LLM-driven decoy constructor with a virtual kernel. Conditioned on exploration, it generates decoy artifacts that the kernel materializes and handles consistently across interactions, sustaining long-horizon exploration. Because deploying a powerful LLM for decoy construction is costly and slow, we train a small LLM using an offline adversarial interaction-simulation framework. It synthesizes multi-round trajectories by generating candidates and retaining those that sustain simulated interactions. Across 15 CVE-Bench web applications and four attacker models, AgentSnare absorbs 49.9% of tool calls to delay attacks, retains 57.2% of post-entry actions in the decoy to divert trajectories, and grounds 89.5% of completion reports in decoy evidence to defuse threats; across 60 attacker-CVE pairs, no real target is exploited at pass@3.

cs.CR · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01936

Ascend-SpMM: Accelerating Sparse Matrix-Dense Matrix Multiplication on Ascend NPUs

Jiahe Wang, Yingxia Shao, Shuhan Wang, Qingbo Ge, Hongzheng Li, Yucheng Zhang

原文摘要

Sparse Matrix-Dense Matrix Multiplication (SpMM) is a fundamental kernel in graph neural networks and scientific computing, yet its optimization on Ascend NPUs remains largely unexplored. The physically decoupled Cube/Vector architecture and single-threaded scalar instruction dispatch of modern NPUs introduce unique challenges. We present Ascend-SpMM, a novel and systematic framework tailored to the physically decoupled architecture of Ascend NPUs.We introduce a memory-centric cost model that quantifies hardware affinity and guides a conflict-bounded, densityaware task-mapping strategy. The strategy maps dense regions to the high-throughput Cube path and sparse residuals to the flexible Vector path, with a theoretical bound on cross-processor conflicts. To execute these workloads with high efficiency, we further develop highly customized sub-kernels. These kernels leverage hierarchy-aware pipelining and round-robin ring buffer-based implicit synchronization to effectively mask memory latency and reduce instruction pipeline stalls. Extensive experiments demonstrate that Ascend-SpMM achieves a geometric-mean speedup of 12.70-20.55X over the strongest evaluated NPU baseline for each matrix, accelerates end-to-end GNN training by up to 6.8X, and delivers performance competitive with state-of-the-art GPU implementations. The source code of Ascend-SpMM is publicly available at https://github.com/IDMG-Lab/Ascend-SpMM.

cs.DC · cs.DB

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.29624

A Tight Space Lower Bound for Pivot-Based Distance Oracles

Avi Kadria, Liam Roditty

原文摘要

An approximate distance oracle (ADO) is a compact data structure that answers distance queries within a multiplicative \emph{stretch} $k$. The classical oracle of Thorup and Zwick~[STOC'01, JACM'05] has stretch $k=2\ell-1$ and uses $O(\ell n^{1+1/\ell})$ space, for every integer $\ell\ge1$. This trade-off is optimal for dense graphs under the Erdős girth conjecture. However, for sparse graphs ($m=O(n)$), their lower bound yields nothing beyond $Ω(m)$ space. The main result of this paper is a nearly tight lower bound for pivot-based $1$-hop ADOs in sparse graphs. A pivot-based $1$-hop ADO gives every vertex $\tilde{O}(1)$ pivots and returns as an estimate the length of a walk of the form $u\to p_u \to p_v \to v$, where $p_u$ is a pivot of $u$, $p_v$ is a pivot of $v$, and $p_u\to p_v$ is a stored distance. We observe that all the state-of-the-art ADOs with $\tilde{O}(1)$ query time are in fact pivot-based $1$-hop ADOs. We prove that every \emph{pivot-based} $1$-hop ADO with \emph{real} stretch $k$ requires $\widetildeΩ(m^{1+2/(k+1)})$ space, under the Erdős girth conjecture for graphs with constant degree. This matches the best known ADOs with $\tilde{O}(1)$ query time, at every known stretch, up to polylogarithmic factors. We also extend our lower bound to pivot-based ADOs with any constant number $β$ of hops, showing that they require $\widetildeΩ(m^{1+2/(β(k+1))})$ space. In addition, we obtain a tight lower bound for two-hop hopsets and improved lower bounds for general $β$-hop hopsets.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01934

TriPhysBench: Evaluating Physical Intelligence for Embodied Agents

Zhongxiang Sun, Chenghao Yang, Haojie Ding, Boheng Zhang, Fan Yang, Qingsong Wen, Kun Wang

原文摘要

Embodied agents need physical intelligence to understand their surroundings through physical perception, physical knowledge retrieval, and physical reasoning. These capabilities must work together to interpret events and make quantitative judgments. Existing benchmarks advance physical understanding and general-purpose tool use, yet the coordination of these capabilities in physical scenarios remains insufficiently characterized. Inspired by Popper's Three Worlds, we introduce TriPhysBench, a benchmark of 410 questions from 200 videos that brings physical perception, physical knowledge retrieval, and physical reasoning into a shared evaluation setting. Its measurement-grounded and knowledge-grounded subtasks impose complementary demands on obtaining observations and acquiring external specifications, then applying them to quantitative problems. Among six representative vision-language models, the best achieves an answer accuracy of only 50.38%, revealing limited performance on tasks that require these capabilities to work together. We further introduce TriPhys, a framework that learns a unified policy for physical perception, knowledge retrieval, and quantitative reasoning from complete tool-integrated trajectories. The policy uses intermediate reasoning to guide retrieval and computation, then incorporates tool feedback into subsequent physical inference. On 110 questions from videos excluded from training, TriPhys improves answer and solution scores across three Qwen configurations, with a 17.7% relative gain in answer accuracy for TriPhys-27B over its Qwen3.6-27B backbone. This work provides a benchmark and a learning pathway toward embodied agents that move beyond recognizing events to understanding and reasoning about the physical processes behind them.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01932

Geometric Morphology Learning: Empowering Foundation Models from Structure to Spacetime Intelligence

Li Sun, Philip S. Yu

原文摘要

Geometry is the very form that connects space, time, and matter, serving as the fundamental fabric of the physical world, from continuous fields to discrete structures. Despite its importance, deep learning is inherently blind to geometry. Riemannian geometry stands as a well-established mathematical foundation for studying geometry, yet it remains largely incompatible with deep learning architectures. To bridge this gap, we establish a new learning framework--Geometric Morphology Learning--that learns geometric or topological structures, shapes or conformations for representation learning, reasoning and action modeling. Moving beyond early attempts limited to specific geometric priors, this theory centers on modeling the intrinsic geometry of objects and learning from such geometric or topological knowledge. Specifically, we construct a neural bundle, a unified scaffolding linking local and global structures, and formulate differentiable operators, including connection and curvature, thereby enabling the study of geometry with advanced geometric concepts such as holonomy and cohomology. Consequently, Geometric Morphology Learning opens new horizons in foundation models, reasoning and planning, graph modeling, physical simulation, PDE systems, and dynamics, marking a fundamental shift toward instilling systematic geometry in artificial intelligence.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.13686

IndicDBBench - Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages

Aviral Dawar, Roshan Karanth, Vikram Goyal, Rakhee Kulshrestha, Sumanta Pasari, Dhruv Kumar

原文摘要

While Large Language Models (LLMs) have significantly advanced Text-to-SQL performance, existing benchmarks largely focus on Western contexts leaving a gap in real-world, non-Western applications. We introduce IndicDBBench, a comprehensive multilingual Text-to-SQL benchmark designed to evaluate cross-lingual semantic parsing across diverse Indic language families. The underlying schemas are derived from real-world open-data platforms (NDAP and IDP), ensuring realistic structural complexity. IndicDBBench comprises 20 databases spanning 237 tables. To construct complex relational structures from denormalized government data, we employ a three-agent pipeline (Architect, Auditor, Refiner), achieving high relational density (11.85 tables per database) and join depths of up to six. We generate 15,612 tasks spanning seven languages: English and six Indic languages, ensuring that queries are grounded in real database values and require multi-table reasoning. We evaluate state-of-the-art models, including DeepSeek V3.2, MiniMax M2.7, Llama 3.3, and Qwen3, across seven linguistic variants. Our results reveal a 9.0-point drop in execution accuracy from English to Indic languages, exposing an "Indic Gap" that, for the two models tested, persists even when gold tables and literal values are supplied, since this grounding raises accuracy in every language by similar amounts. The dataset and code are publicly available at https://anonymous.4open.science/r/multilingualText2Sql-Indic--DDCC/

cs.CL · cs.AI · cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01930

RECEIPT: Measuring and Repairing the Return Assumption of LLM Agents in Web Service Operations

Boyang Yang, Ziyao Yang, Yu Zhang, Duo Chai, Xiaoming Chen, Haoye Tian

原文摘要

LLM agents operate Web infrastructure from the command line and rely on a return assumption, namely that each tool call returns within a bounded time and with its requested action finished. Many commands, however, ask a question before they act, and the agent's harness either closes the program's input or keeps it open as a terminal at which nobody types. With closed input, the program can return status 0 without the requested action. With open input, it waits until a time limit, and the agent pays in time and tokens. To the best of our knowledge, this paper is the first to measure and repair the return assumption. We collect 91,469 production tool calls and 89,047 public agent trajectories, test how 8 widely used harnesses launch commands, and build Litmus, a catalog of 158 checked command-line invocations, and Tripwire, a benchmark of 25 task pairs that differ only in whether a question guards the requested action. We then propose RECEIPT, which keeps the input open, reads what each process waits for from system calls, and returns this state to an unmodified agent through a model-checked protocol. On Litmus, closed input causes 11.5% of tested invocations to return status 0 without performing the requested action, and 7 of 8 harnesses close input when no terminal is attached. An unanswered question at a plain terminal multiplies a task's token use by 2.9, and the input connection moves an LLM from 7th to 3rd place among 8. Across 5 LLMs, RECEIPT reduces false claims of success by 73.5% and completes all 25 guarded tasks on a second harness. An agent's reliability therefore depends on what its harness lets it observe as well as on its LLM. Agent builders should report what each tool call did, not only how it ended, and benchmark maintainers should fix and report the input connection before they rank LLMs.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01929

Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate Schedule

Eitan Gronich, Gal Vardi

原文摘要

We study the implicit bias of Adam and its similarity to sign gradient descent on homogeneous models in binary classification tasks. Perhaps surprisingly, we uncover that these depend on the learning rate schedule. While previous works studied strongly decaying learning rate schedules $η(t)=\mathrm o \left(t^{1/L-1}\right)$, where $L$ is the homogeneity degree, and showed $\ell_\infty$-margin-maximization biases, we focus on the more common complementary regime, including constant and weakly decaying schedules. For a polynomial schedule $t^α$ and homogeneity degree $L$, we show that when $α> \frac 1L - \frac12$, Adam has no trajectory-independent margin-maximization bias for deep linear networks (in the KKT sense): first, there is no non-trivial, locally Lipschitz, convex implicit regularizer in this setting, including any squared norm. Second, on width-$1$ networks, the result holds without requiring convexity, implying that any implicit regularizer for wide networks must be trivial when restricted to a width-$1$ network. Nevertheless, we positively characterize the implicit bias in this regime as maximizing a trajectory-dependent weighted-$\ell_2$ margin for any $L$-homogeneous model. The fundamental mechanism behind our results is convergence of Adam's preconditioner to a trajectory-dependent vector, which also allows showing that the limiting parameter direction depends on initialization. In the intermediate regime $\frac 1L - 1 \leq α\leq \frac1L - \frac12$ we prove an $\ell_\infty$ bias, conditional on gradient directional convergence to a full-support vector. Of independent interest, we establish a loss decay rate for full batch Adam on general homogeneous models, whose leading order depends only on the second-moment parameter.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37297

TRUCO: A Scalable Lock-Free Algorithm for Parallel Contour Extraction

Rafael Munoz-Salinas, Francisco J. Romero-Ramirez, Manuel J. Marin-Jimenez

原文摘要

Extracting closed pixel contours from a binary image, together with the hierarchy that records which contours enclose which, is a basic step in many computer vision pipelines, from fiducial marker detection to the vectorization of segmentation masks. The reference algorithm, by Suzuki and Abe, is inherently sequential: each contour is found by a raster scan that depends on the labels left by all previous contours, and its parent is obtained from the last contour met by the scan. This paper presents TRUCO (Threaded Raster Unrestricted Contour Ownership), a multi-core algorithm that returns exactly the output of Suzuki--Abe (the same contours, in the same order, with the same hierarchy) without locks, read-modify-write operations or a stitching phase. The method rests on two ideas. First, the image is divided into horizontal stripes, one per thread, and two rules, row-local writes and geometric contour ownership, let each thread trace complete contours independently of the others. Second, the tracing of the contours is separated from the computation of the hierarchy, which is recovered afterwards from one reference per contour; the trace therefore stores no contour numbers in the label image, which also makes it more efficient than that of the original algorithm when a single thread is used. We prove that the output is deterministic and identical to that of Suzuki--Abe, and that the algorithm is free of data races. Experiments on synthetic images, high-resolution photographs and segmentation masks, on a desktop and a server CPU, show that TRUCO scales with the number of threads and is several times faster than the fastest sequential methods, with and without the hierarchy. With a single thread, it is already faster than Suzuki--Abe.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01927

Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks

Yu Jiang, Yue Huang, Hang Hua, Yuyang Wu, Zixuan Weng, Olexandr Isayev, Yue Zhao, Zinan Lin 等 9 位作者

原文摘要

Long-horizon terminal tasks are used to evaluate and train agents. Human-curated datasets are scarce, so many synthesis methods have emerged. They usually measure the length of a task by the turns a model needs to pass it, and its difficulty by labels the LLM sets during generation. We find, however, that the turn count largely reflects the habits of the model, not only the demands of the task, and that the labels barely track how often models pass. We describe a terminal task by its work, the number of operations it requires, and its depth, the number of turns that must happen in sequence because the commands of each turn can only be chosen after reading the output of the previous one. Estimating depth as the smallest turn cap, stated to the agent, under which the task passes, we audit 734 tasks from six existing datasets. Synthesis has mostly added work, not depth: 94% of the solved synthetic tasks pass within three turns, yet depth, unlike the turn count, predicts difficulty beyond work. We propose DEPTH, in which a generation agent writes each task one segment at a time in a real software environment, carrying out each segment before writing it and starting the next from the state it leaves. Our 105 tasks exceed every audited dataset in depth and work, and none of six current models passes half of them. Fine-tuning Qwen3-8B on runs from these tasks improves it on two terminal benchmarks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01926

TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens

Juseon Do, Sangmin Bae, Jeesu Jung, Hwanjun Song

原文摘要

LLM-based agentic systems are increasingly combined with CoT reasoning to solve tasks that require accurate reasoning, external knowledge, and multi-step deliberation. Yet, explicit CoT incurs substantial generation overhead, while implicit CoT, which replaces textual rationales with compact continuous tokens, does not naturally support the explicit communication interface required for agentic tool-use. We propose TAC-CoT, a tool-empowered adaptive implicit CoT framework that replaces explicit reasoning traces with compact latent reasoning segments while retaining textual tokens only for tool calls, observations, and final answers. This interleaved design enables agentic tool-use without verbalizing every intermediate reasoning step. Experiments on agentic math and QA benchmarks show that TAC-CoT improves accuracy by up to 8.8 points while reducing model forward passes by up to 6.8x. Furthermore, analyses show that TAC-CoT improves tool-use quality in both single- and multi-tool settings.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01921

Vision-language classification of Torsades de Pointes risk from pseudo-coloured ECG images: do T-wave morphology and colour context help or hinder?

Dario Labrador Alonso, Alaa Alahmadi

原文摘要

Contextual prompting is widely presented as a cheap route to better performance from vision models, but the evidence comes largely from benchmarks in which an attribute named in a prompt is also present in the image, confounding the two channels. We investigate the significance of context for a semantically complex biomedical signal classification task using a domain-adapted vision-language model, BiomedCLIP. Building on our previous work that renders electrocardiogram (ECG) signals as colour-enhanced images to flag Torsades de Pointes risk using the QT-nomogram and pseudo-colouring technique, we cross four context strategies with four T-wave morphology label sets, evaluated zero-shot and with a class-balanced linear probe, under five-fold stratified cross-validation on 9,789 images. Zero-shot inference is unusable. Once trained, the colour-enhanced images outperform the colourless ones on every metric: balanced accuracy 0.903 versus 0.825, sensitivity 0.914 versus 0.827, specificity 0.892 versus 0.823, ROC-AUC 0.955 versus 0.888 and Matthews correlation coefficient (MCC) 0.437 versus 0.311. Crossing colour-in-image with colour-in-prompt separates the confounded channels: the image contributes +0.126 MCC (+0.078 balanced accuracy, +0.067 ROC-AUC) whether or not the prompt names colour, whereas naming it changes nothing under any metric. Context is two-sided: the best prompt set gains 0.008 MCC where colour is present and 0.016 where it is not, while the worst loses 0.017 and 0.013. For a signal rendered as an image, the leverage lies in how the signal is drawn rather than in how it is described - and where the endpoint is an interval measurement, prompts naming T-wave morphology describe the wrong quantity.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v8arXiv:2508.02833

TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback

Lei Pang, Jun Luo, Ruinan Jin

原文摘要

Group Relative Policy Optimization (GRPO) trains language models without a value critic using rewards centered within sampled response groups. We study how importance weighting, clipping, and length normalization affect its stochastic updates and propose Trajectory-level Importance-Corrected GRPO (TIC-GRPO), combining an upper importance-ratio cap with a full-trajectory likelihood ratio. Under common maximum-length normalization, a trajectory change of measure gives a score second moment proportional to the response horizon. We propagate this estimate through the actual empirical baseline and all inner updates. With separately optimized constant steps, the sampling term in TIC's stationarity bound has a linear horizon coefficient, versus order three halves for token-level GRPO$_2$. Matching upper and lower bounds separate the capped methods' worst-case response-level variances by a factor $T$. The bounds track prompt count, response-group size, vocabulary size, reward scale, and score regularity; per-response-normalized GRPO also retains a length-covariance term. Experiments at two Qwen3 scales on four reasoning and coding benchmarks evaluate both mechanisms in sampled-token-normalized training.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01920

Multiplicative Weights for Mixed Block Constraints and Maximum Multicommodity Flow

Vladimir Kolmogorov

原文摘要

We study multiplicative-weights (MWU) algorithms for block-separable feasibility problems containing both packing and covering constraints. Each iteration optimizes a weighted linear objective over one block, either chosen uniformly at random or visited in a fixed cyclic order. We show that the cyclic algorithm returns an $O(\varepsilon)$-approximate solution after $O(kρ\varepsilon^{-2}\log m)$ oracle calls where $k$ is the number of blocks and $ρ$ is the width of the oracle. The same holds for the randomized version with high probability. Previously, such bounds were shown when the coupling constraints have the same sign [Radzik'95; Villavicencio-Grigoriadis'96]. These analyses critically depended on monotonicity arguments that are not available in the mixed case. As an application, we obtain a deterministic $(1-\varepsilon)$-approximation for maximum multicommodity flow (M-MCF) using $O(k\varepsilon^{-2}\log m\log(km/\varepsilon))$ approximate single-commodity min-cost-flow calls. For planar graphs, and more generally for graph families admitting a near-linear-time min-cost-flow algorithm, this gives total running time $\widetilde O(km\varepsilon^{-2})$. Compared with the $O(km^{1+o(1)}\varepsilon^{-1})$ algorithm of [Chen-Graur-Sidford'25], this improves the dependence on $m$ for these graph families at the cost of a worse dependence on $\varepsilon$. Finally, we give an exponentiation-free finite-precision implementation of the cyclic algorithm. It represents each internal weight by a logarithmic-bit mantissa and exponent, while every price supplied to the block oracle is rational and has a polynomially bounded common denominator.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01918

AgenticMobility: An Open-Source Platform for Multi-AI-Agent Mobility Dynamics

Jiaheng Xiao, Jiangtao Han, Jiachen Wang, Honghai Li, Lijun Sun, Kay Axhausen, Chang Liu, Zhengbing He

原文摘要

Understanding mobility dynamics and the effects of urban transportation management policies requires examining how individual travel decisions, traffic conditions, and policy interventions influence one another over time. We present AgenticMobility, an open-source experimental platform for studying how mobility AI agents and other AI agents interact, adapt through repeated experience, and collectively shape mobility outcomes. Persistent agents retain identities and relevant states across rounds, with explicit interfaces defining information access, admissible actions, and decision schedules; linked records trace decisions, execution, and feedback. In the current implementation, large language model (LLM) agents act as travelers choosing routes and departure times and as a manager periodically adjusting link charges within MATSim. A preliminary demonstration spans 100 simulated days in each of five configurations, with one run per configuration and a shared simulation seed. In the joint traveler--manager run, all 1,179,300 finalized target decisions satisfied action constraints; execution checks verified implementation of accepted choices and preservation of personal memories across days. Trajectories show stable route choices alongside departure-time adjustments and differences between controlled-trip and population-wide outcomes. The platform supports experiments on individual adaptation, collective outcomes, and management interventions by varying information access, retained experience, and management feedback. Source code is available at https://github.com/Agentic-City-Research/Agentic-Mobility

cs.MA · cs.AI · physics.soc-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.39576

Bayesian Offline Multi-Agent Reinforcement Learning with Latent World Models

Xi Xiong, Lu Liu, Yiming Li, Jakob Foerster

原文摘要

Model-based offline multi-agent reinforcement learning (MARL) provides a promising approach to multi-agent decision-making under partial observability, where the global state is unavailable from offline data. However, limited dataset coverage can lead to substantial out-of-distribution (OOD) model errors, which may mislead policy optimization and degrade downstream performance. Existing model-based offline MARL methods typically rely on access to global states or mitigate model errors through pessimistic or conservative policy optimization, leaving the reliability and refinement of learned world models less explored. We propose a Bayesian offline MARL framework that infers latent global states from decentralized observation-action histories and iteratively refines a posterior world model using only offline data. Building on posterior information loss, we extend this criterion to the multi-agent setting as multi-agent posterior information loss (MPIL), which provides a reliability measure for world model refinement and offline evaluation. Theoretically, we establish an upper bound on policy regret that is monotonic in MPIL and further characterize its dependence on the size and state-joint-action coverage of the offline dataset. Experiments on partially observable multi-agent variants of D4RL MuJoCo tasks demonstrate competitive policy performance across diverse offline data conditions, while MPIL-guided refinement improves world model prediction and downstream policy performance. These results support a principled connection between world model reliability, offline data coverage, and policy performance in partially observable offline MARL.

cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01914

Machine Learning Beyond Statistical Consistency for Hybrid AI

Jinsook Kim, Jinho Kang

原文摘要

We propose a new definition of machine learning, according to which a machine learns a function when it computes the function successfully, that is, when the value it returns for each input has a proper derivation in a formal system. We extend Gödel's Representability Theorem, which equates computation with derivation, to empirical targets in two ways: the theorem is extended to the computable reals, and the data are admitted into the system as empirical definitions that record what has been observed. We prove that a machine learns a true probability if and only if two conditions are met. The Truth Condition is that its estimate converges to the true probability, which is statistical consistency. The Assurance Condition is that the machine properly derives its own convergence inside the system. Learning thus lies beyond statistical consistency, for it requires a derivation of the convergence from the record. A global assumption about the data, such as the i.i.d. assumption, does not supply such a derivation, because it leads only to a circular one, as we show for PAC learning. On the other hand, the two conditions are met for the probability of a sentence over a finite ideal corpus. A real machine can approximate a true probability only if an ideal machine can learn it precisely, that is, only in a domain that meets the two conditions. Modern AI works in such a domain, and we offer this as a clue to its success. Modern AI is hybrid as well, in two senses: First, it performs two kinds of tasks, namely probabilistic ones such as predicting the next word and deductive ones such as proving and coding. Second, it combines two parts of different kinds, a statistical proposer and a deductive verifier, for proving and coding. Our framework explains both senses of hybridity in one formal system.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01913

SurgQ-VLM: Question-Conditioned Dual-Stream Compression and Answer-Type-Aware Reinforcement for Surgical Video Question Answering

Dhruv Makwana, Ananya Mantravadi

原文摘要

Reasoning about surgical video -- which phase is underway, which instruments act, and when events occur -- underpins operative documentation, workflow analysis, and skill assessment. Yet surgical visual question answering is still largely built on single frames and closed labels that cannot express a duration, an ordering, or a count, and the video models that lift the frame limit typically compress every clip the same way regardless of the question, discarding the temporal evidence the answer needs. Worse, the answers are structurally heterogeneous, spanning five incompatible structures -- binary, classification, multi-label, counting, and sentence-temporal -- that no single training signal scores uniformly well. We propose SurgQ-VLM, a two-stage model for surgical video question answering. Stage 1 trains a question-conditioned dual-stream (slow/fast) compressor for a LoRA-adapted Qwen2.5-VL-7B: cross-attention conditions both streams on the question, and each clip's visual tokens shrink 49x from the raw ViT patches (11x vs. post-merge backbone tokens). Stage 2 post-trains with GRPO under an answer-type-aware reward that scores each question on the metric matching its answer structure (micro-F1 for label sets, normalised error for counts, a content-timing blend for temporal windows). On a sealed 21,840-question test split over Cholec80 and CholecT50, SurgQ-VLM reaches 0.779 keyword accuracy and a 10x BLEU-4 gain over zero-shot; GRPO adds 2.5 pp K-Acc (2.0 pp attributable to the answer-type-aware reward), concentrated in the structurally hard types, with answer format unchanged (ROUGE-L). Code is available at https://github.com/DhruvMakwana/SurgQ-VLM.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01910

EAGR: Evidence-Guided Adaptive Graph Retrieval

Sonam Gupta, Vignesh P, Vishwajeet Kumar, Adnan Qidwai, Anand Eswaran, Jaydeep Sen, Sachindra Joshi

原文摘要

Retrieval-Augmented Generation (RAG) for multi-hop reasoning requires retrieval to adapt as intermediate evidence reveals new information needs. Existing approaches support such retrieval through explicit graph structures or iterative query reformulation, introducing graph-construction or query-time overhead. We present Evidence-Guided Adaptive Graph Retrieval (EAGR), a framework in which accumulated evidence dynamically determines which semantic directions to explore next, and which requires no dedicated graph database and no explicit graph materialization. EAGR operates over an implicit semantic graph induced by compact passage metadata pre-ingested into a standard VectorDB. Starting from dense-retrieval seed passages, an LLM iteratively assesses accumulated evidence, identifies promising semantic directions, expands the retrieval frontier through metadata-based neighborhood lookup, and terminates once sufficient evidence has been collected. By precomputing semantic metadata, EAGR enables evidence-conditioned graph exploration without materializing an explicit graph, maintaining a dedicated GraphDB, or iteratively rewriting the query. Across three widely used multi-hop QA benchmarks, EAGR achieves the highest LLM-based answer accuracy among evaluated methods, outperforming the vanilla RAG by 17\% and strongest graph-aware baseline by 4\% percentage points averaged across three popular benchmarks HotPotQA, 2WikiMultiHopQA, and MuSiQue.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01909

Who Asks, Who Answers: Linear Attention Builds the Query in Hybrid Language Models

Wenqi Zeng, Chen Feng, YuAng Chen

原文摘要

Hybrid language models interleave linear-attention layers with a small number of softmax-attention layers. Prior work largely attributes in-context retrieval to softmax attention, treating linear attention primarily as a mechanism for compressing past context. We revisit this division of labor and show that linear attention plays a direct role in retrieval by constructing the query used by softmax attention. Studying Qwen3.5 (Gated DeltaNet) and Granite4.0 (Mamba-2), we identify an Encode--Address circuit. An early Encode block preserves token identity, while an Address block constructs the final-position representation from which a softmax \emph{reader} forms its attention query. Transplanting this representation between prompts with different queried keys redirects retrieval in 0.97--0.99 of cases. The Address block's recurrent state carries the retrieval target, and its computation transfers across architectures: replacing Granite's Address block with Qwen's restores retrieval accuracy to 0.92--0.94 without updating either model's weights. Across six Qwen3.5 models, Address computation becomes distributed at larger scales over a chain of blocks, each guiding a successive reader, as the query no longer passes from one reader to the next through attention. These findings reveal a division of labor in hybrid retrieval: linear attention constructs the query, while softmax attention performs the lookup. Code is available at https://github.com/yuang-chen/LinearQuery

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01908

Does reflective LLM feedback survive a wet-lab-scale label budget?

Haoxuan Zeng, Xin Luo

原文摘要

Can reflective language-model feedback improve a biological predictor when each cycle buys only one plate of labels? We separate three possible sources of benefit: proposing model edits, choosing measurements, and revising decisions through repeated feedback. We replay $36$ ProteinGym assays, starting with $96$ labels and acquiring $96$ per round for six rounds, with a sealed test set and a shared edit schema. The pre-specified comparison of full LLM control against random edits detects no advantage in test rank correlation ($Δz=-0.008$, $95\%$ CI $[-0.034,+0.018]$); equivalence is also unestablished. Exploratory ablations nevertheless identify useful model editing. With random acquisition fixed, LLM edits improve Fisher-transformed test Spearman by $0.043$ over no edits; with acquisition fixed to upper confidence bound, they improve normalized top-variant recovery by $0.023$. LLM acquisition alone does not detectably outperform fixed adaptive rules, and repeated feedback does not detectably outperform one initial recommendation under full control. Thus, the observed gains support constrained specialist editing, while the incremental value of recursive reflection remains unestablished at this label budget.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01907

Online Active Learning Architecture for Safety-Critical Control Systems

Shuiwen Shen, Jinhua Zhang, Yan Wang, Huanqiang Zeng, Yueyun Xu, Song Gao, Haifeng Xiang, Yifu Shen

原文摘要

The transition of information-centric artificial intelligence to safety-critical applications is impeded by the limitations of conventional offline-training paradigms in open-world environments. This paper presents Control AI, an architecture for Online Active Learning (OAL) inspired by the continuous Prediction-Evaluation-Correction process of biological intelligence. The framework combines the hierarchical representation capacity of deep neural networks with the real-time error-feedback adaptation of adaptive control. A prediction model maps sensory input into a latent manifold, an optional latent model represents transitions in that space, and a reconstruction model maps the latent state back to observable signals. Residuals between predictions and measurements provide the internal learning signal. Spatial and temporal cross-reconstruction architectures prevent OAL from collapsing to a trivial identity mapping, while coupled, dual, and localized variants shorten error-transmission paths. Localized predictive coding style OAL is implemented through guidance-backpropagation and target-backpropagation architectures, and hybrid and scaled variants support high-dimensional deployment. The paper focuses on the architectural rationale and the progression from a conceptual feedback loop to practical large-scale configurations.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01906

Improved lower bounds for the kissing number in dimensions 49 to 61

Dmitry Kamenetsky

原文摘要

We give explicit kissing configurations in R^d for every d = 49, ..., 61. The lower bound is improved over the best previously published value in all thirteen dimensions, by margins from 232 to 159,220 points and by 506,461 points in total. The configurations are obtained from the antipodal block lift of Yang et al. applied to the 52,416,000-point minimal shell of the extremal even unimodular lattice P_48p, using a class of 7,193 minimal lines and, in each dimension, a kissing configuration of R^k (k <= 15) with the largest available number of antipodal pairs. Two ingredients are new. The published class of 7,077 lines is grown to 7,193 by local search in three stages, as a sequence of exchanges between candidate lines and class lines; and the point count, which equals 52,416,000 + 2S + 2t with t the number of antipodal pairs and S the size of the union of t isometric images of the class, is maximised as a maximum-coverage problem by greedy search with iterated local search over pools of 4,000 automorphic images, reaching 92-100% of the trivial bound 7,193t. All results are verified in exact integer arithmetic, and the certificates are distributed with the code. Code and data: https://github.com/dimkadimon/KissingNumbers

math.MG · cs.IT · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01904

Superscalar Loop Processors

Luca Colagrande, Pascal Etterli, Luca Benini

原文摘要

To sustain the computational demands of modern ML and HPC workloads, programmable accelerators integrate large arrays of processing elements (PEs), typically built around single-issue in-order cores to maximize integration density and energy efficiency. As a result, each PE's instruction throughput is upper-bounded at one instruction per cycle (IPC), often suffering from significant underutilization of its functional units (FUs). Conventional superscalar processors can improve FU utilization by increasing IPC, but they typically incur substantial area and energy overheads. This work proposes the Superscalar Loop Processor (SLP) architecture, a lightweight approach to superscalar execution that targets regular, compute-intensive loop kernels. We present the SLP execution model, which exploits the static structure of these workloads to enable efficient multiple-issue execution without the complexity of dynamic out-of-order scheduling. We demonstrate the SLP architecture through an open-source prototype implementation, Schnizo, developed as an enhancement of a tiny RV32I core with floating-point support. Across several ML and HPC microkernels, Schnizo achieves substantially higher IPC and FPU utilization than the scalar baseline while retaining the efficiency of lightweight in-order designs. These results demonstrate that SLPs can provide an efficient architectural solution for programmable accelerators targeting regular, compute-intensive workloads.

cs.AR · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01903

Federated Estimation of Loading Spaces in Tensor Factor Models under Differential Privacy

Zetai Cen, Fan Wang, Haeran Cho

原文摘要

Tensor factor models provide low-dimensional representations of tensor-valued observations while preserving their multiway structure. When these observations are held by different clients, privacy constraints may prevent them from being pooled for centralized analysis. We study estimation of common loading spaces in Tucker tensor factor models under federated differential privacy, allowing heterogeneous sample sizes, privacy budgets, and factor strengths. The proposed method combines private stability testing, Huber aggregation, and Gaussian perturbation at each client with weighted aggregation at the server. We establish non-asymptotic upper bounds governed by a scaled harmonic mean of the squared local error rates, and prove minimax optimality up to logarithmic factors under strong factors, fixed factor ranks, and fixed noise variance. We further develop a private calibration procedure that selects the local tuning parameters and aggregation weights without knowledge of the noise level or client-specific factor strengths. The resulting adaptive estimator preserves the privacy guarantee and attains the error rate obtained with oracle tuning. We illustrate the finite-sample performance of the proposed estimators through simulation experiments and an application to a Meditation Traits EEG dataset.

math.ST · cs.IT · stat.ML

查看论文
arXiv ↗PDF ↗