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
+99新增 AI 导读

arXiv 最近完成扫描：2026-11-08 00:56 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 01:02 — 2026-11-08 01:02（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 00:56最近发现新增版本：2026-11-07 17:43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4,056 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 00:54（北京时间）
版本更新 · v3arXiv:2608.15591

Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback

Pouya Ghiasnezhad Omran, Michael Zimmermann, Duncan Cambridge, Ashmita Kapoor, Tanya Dixit

原文摘要

Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve. Existing approaches address agent construction and one-time evaluation but provide no structured mechanism for continuous post-deployment behavioral correction without modifying the agent's source code. Most of the approaches offered in the market, require intense collection of logs and traces, and re-examining the agent design by the engineering team, a process which is heavy, long and negates the economical value of agentic transformation. We introduce Agent Gym, a modular, domain-agnostic framework that wraps any existing LLM-based agent in a continuous evaluation-and-evolution loop. The framework provides six composable capabilities --- Act, Evaluate, Investigate, Correct, Learn, and Observe --- organized across three architectural zones: a constitution layer that codifies domain knowledge in configuration artifacts, a runtime inference pipeline that chains acting, investigation, and adaptive correction, and a learning loop that enables subject matter experts to discover and validate new correction rules through natural language interaction. The key technical contributions include a hybrid deterministic-LLM correction engine with 21 condition operators and three-tier actions, a three-layer investigation architecture for ground-truth-free compliance validation, and a programmatic safety loop that guarantees rule correctness before human approval. We further introduce the Spec-to-Note Gap, an autoencoder-inspired view of agentic system transparency. An open-source reference implementation for invoice processing demonstrates that the framework is fully operational and ready for adoption.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.23262

Designing Benchmarks for Knowledge Work

Yining Hua, Hongbin Na, Cyrus Ayubcha, Levi Lian

原文摘要

Agent benchmarks have attracted substantial attention; yet, benchmarks for AI agents performing knowledge work are still mostly described only by their tasks, environments, and metrics. Starting from the definition of knowledge work, this paper derives four other design choices that often remain implicit. Three research threads on how knowledge work is organized each yield one choice: studies of professions, situated action, and boundary objects and coordination, while validity theory provides the fourth. Following this reasoning, we propose a benchmark representation centered on the work being performed. Based on this representation, we propose reporting practices for four largely missing fields: represented activity, tested setting, required work product, and evaluated result. Benchmarks designed in disparate ways thereby share a common description and can be compared side by side. To support the reporting of work activities, we cluster O*NET task statements into 18 shared work activities through unsupervised learning paired with human review. We then use this representation to analyze cases from three popular knowledge work benchmarks: GDPval, OfficeQA Pro, and APEX-SWE. Across all three benchmarks, the scope covered by the evaluated result is narrower than that of the required work product. We audited the tests of all 25 public APEX-SWE Integration tasks, independently coded by two authors. We found from the test code that in 13 of these tasks, a deliverable can alter established content from the source data and still pass all tests. We synthesize these four fields into a one-page record, accompanied by a worked example and a fillable template.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05738

OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments

Changyeon Lee, Kelin Yu, Zheng Wei, Shuna Ni, Ruohan Gao

原文摘要

Olfaction provides critical information about airborne chemical cues, yet it remains largely underexplored in embodied AI, with limited prior machine olfaction work focusing primarily on semantic odor perception. We introduce OdorSpaces, a physics-based simulation platform and benchmark for visual-olfactory embodied navigation. OdorSpaces augments Habitat-Sim with 3D odor transport and dispersion simulated by Fire Dynamics Simulator (FDS), enabling agents to navigate photorealistic indoor environments using both visual and olfactory observations. The benchmark includes two representative source-seeking scenarios: invisible gas-leak localization and early-stage fire localization. We develop an initial multimodal reinforcement learning policy that integrates visual observations and olfactory measurements over time. Experiments show that the policy outperforms a diverse set of baselines, establishing a strong reference for future research on visual-olfactory embodied navigation.

cs.RO · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05737

C-WFDM: A ControlNet-Guided Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Completion

Muhammad Nabi Yasinzai, Remika Mito, Mangor Pedersen

原文摘要

Multimodal brain MRI provides complementary anatomical, tissue, and pathological information to support downstream artificial intelligence (AI) applications. However, modality availability is uneven across public and pooled neuroimaging datasets: T1-weighted (T1w) MRI is widely represented, T2-weighted (T2w) and fluid-attenuated inversion recovery (FLAIR) MRI are less consistently available, and gadolinium-enhanced T1-weighted (T1Gd) MRI is relatively scarce. Pooled datasets therefore contain participants with different combinations of acquired MRI contrasts, reflecting variation in the study designs, acquisition protocols, and clinical or research objectives of the contributing studies. Many missing-modality benchmarks simulate incomplete MRI by withholding contrasts from complete four-modality cases, which may not represent the observed availability patterns in pooled datasets. To address this gap, we introduce C-WFDM, a ControlNet extension of our Wavelet-Fusion Diffusion Model (WFDM), for subject-specific missing-modality completion. C-WFDM is built on an earlier BrainScape snapshot comprising 157 public MRI datasets and 45,880 preprocessed scans. The pretrained WFDM backbone retains target-modality and metadata conditioning, while target-specific ControlNet adapters use MRI contrasts from the same participant to guide synthesis. C-WFDM synthesizes T2w from T1w, FLAIR from T1w and T2w, and T1Gd from T1w, T2w, and FLAIR. Acquired conditioning contrasts are used when available, and generated intermediate contrasts are used only when required. We compare C-WFDM with ALDM, cWDM, and Pix2Pix using paired structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and mean absolute error (MAE). In the BrainScape completion experiment, C-WFDM achieves the best T2w and FLAIR results among the evaluated models, with SSIM values of 0.9232 and 0.8904, respectively.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.29929

Privacy Preference Controls for Agentic Systems

Shreya Kochar, Peeranat Sugsavanvit, Vidur Gupta, Joseph A. Calandrino, Deepak Kumar, Brett Frischmann, Sebastian Zimmeck

原文摘要

In response to vast and widespread online tracking, regulators and technologists alike have worked to develop laws and tools that allow people to express their privacy preferences. These measures seek to offer users greater control over the sale and sharing of personal information, putting agency in their hands to protect their privacy. However, the web is undergoing a seismic shift, away from strictly user-driven behavior towards agentic behavior, where AI agents take autonomous actions on behalf of users. In this study, we ask: What should privacy preference controls look like in the agentic web and agentic systems more generally? To answer this question, we develop a taxonomy of enforceable privacy preferences for agentic systems. Our taxonomy is informed both by laws and empirical studies of existing privacy tools as well as an audit of 30 leading AI assistants and agent platforms. To explore how our taxonomy can be implemented, we design and develop eight open-source prototypes that mirror real-world agentic applications and demonstrate how major aspects of our taxonomy can be structurally integrated in agentic protocols, such as the Model Control Protocol and Agent2Agent protocol. Ultimately, our study seeks to provide the groundwork for ensuring end-user privacy and autonomy is not lost in the newly arriving agentic world.

cs.CY · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.08898

Towards Visual Query Segmentation in the Wild

Bing Fan, Minghao Li, Hanzhi Zhang, Shaohua Dong, Naga Prudhvi Mareedu, Xiaoqiong Liu, Weishi Shi, Yunhe Feng 等 10 位作者

原文摘要

In this paper, we introduce visual query segmentation (VQS), a new paradigm of visual query localization (VQL) that aims to segment all pixel-level occurrences of an object of interest in an untrimmed video, given a visual query. Compared with existing VQL locating only the last appearance of a target using bounding boxes, VQS enables more comprehensive (i.e., all object occurrences) and precise (i.e., pixel-level masks) localization, making it more practical for real-world scenarios. To foster research on this task, we introduce VQS-4K, a large-scale benchmark dedicated to VQS. Specifically, VQS-4K consists of 4,111 videos with more than 1.3 million frames, and covers a diverse set of 222 object categories. Each video is paired with a visual query defined by a frame outside search video and its target mask, and annotated with spatial-temporal masklets corresponding to the queried target. To ensure high quality, all videos in VQS-4K are manually labeled with meticulous inspection and iterative refinement. To our best knowledge, VQS-4K is the first benchmark specifically designed for VQS. Furthermore, to stimulate future research, we present a simple yet effective method, named VQ-SAM, which extends SAM 2 by leveraging target-specific and background distractor cues from the video to progressively evolve the memory through a novel multi-stage framework with an adaptive memory generation (AMG) module for VQS, significantly improving the performance. In our experiments on VQS-4K, VQ-SAM achieves promising results and surpasses existing methods, evidencing its effectiveness. With VQS-4K and VQ-SAM, we expect to inspire more future research and applications on VQS. Our benchmark and code are released at https://github.com/VAIL-Fan/VQS.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05735

Self-Supervised Learning of Universal Latent Spaces for Operator Learning

Sepehr Mousavi, Levi Lingsch, Siddhartha Mishra, Laura De Lorenzis

原文摘要

Neural operators fit their representation of functions to the task they are trained on, so every new task rebuilds a reduced space from labeled data. Following the self-supervised pre-training that made representations shareable in natural language processing and computer vision, we decouple representation learning from operator learning. A functional autoencoder is pre-trained on analytic functions synthesized on the fly, with no solver and no labels, to represent functions on arbitrary point clouds, and the latent space it induces is frozen and reused across tasks. The representation is exactly equivariant to translation, dilation, and amplitude, and reconstructs solutions of partial differential equations (PDEs) and natural images on geometries it never saw. Being task-agnostic, the latent space can be interpreted in its own right. The whole space is used and decodes to valid fields, it preserves the ordering of distances between physical fields, its geodesics interpolate physical evolutions, and edit directions transfer across fields. With frozen representation maps, a dataset is encoded once and a neural operator is trained entirely on cached embeddings, which saves memory and training time. On 28 tasks in fluid dynamics, solid mechanics, acoustics, and the Helmholtz and Poisson equations, this paradigm can exceed the accuracy of state-of-the-art end-to-end architectures, with up to an order of magnitude higher throughput and memory savings that fit models nearly two orders of magnitude larger on consumer-grade GPUs. At inference, latent rollouts run up to an order of magnitude faster than regular rollouts, and chunked inference processes functions of over half a billion points on a single consumer-grade GPU.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05734

Mitigating Spurious Invariance in Contrastive Learning: A Probabilistic Self-Supervised Learning Framework for Medical Image Analysis

Wei Wei, Yading Yuan

原文摘要

Owing to the prohibitive cost of manual annotation for enormous medical images, self-supervised learning (SSL) has gained substantial attention and shown promise in various medical imaging tasks. Among SSL approaches, contrastive learning has emerged as a prominent one, encouraging models to encode semantic information that remains invariant between different augmented views. However, this invariance can be spurious for medical images, as subtle but critical medical features can be suppressed during augmentations. In this paper, we mitigate this issue by encoding the learned feature embeddings as probability distributions rather than fixed vectors, thus capturing a richer and more nuanced spectrum of information. Furthermore, we propose a unified probabilistic framework that seamlessly integrates multiple SSL approaches. Our method achieves superior performance over the state-of-the-art SSL methods on various downstream tasks across multiple datasets, including medical image segmentation and classification. We further validate the method through additional analyses of robustness to stronger augmentations, label efficiency under limited fine-tuning labels, and computational trade-offs. The code is released at https://github.com/wwzjer/ProbSSL.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2009.03996

Combining Determinism and Indeterminism

Michael Stephen Fiske

原文摘要

Our goal is to construct mathematical operations that combine indeterminism measured from quantum randomness with computational determinism so that non-mechanistic behavior is preserved in the computation. Formally, some results about operations applied to computably enumerable (c.e.) and bi-immune sets are proven here, where the objective is for the operations to preserve bi-immunity. While developing rearrangement operations on the natural numbers, we discovered that the bi-immune rearrangements generate an uncountable subgroup of the infinite symmetric group (Sym$(\mathbb{N})$) on the natural numbers $\mathbb{N}$. This new uncountable subgroup is called the bi-immune symmetric group. We show that the bi-immune symmetric group contains the finitary symmetric group on the natural numbers, and consequently is highly transitive. Furthermore, the bi-immune symmetric group is dense in Sym$(\mathbb{N})$ with respect to the pointwise convergence topology. The complete structure of the bi-immune symmetric group and its subgroups generated by one or more bi-immune rearrangements is unknown.

math.LO · cs.CC · cs.CL · math.GR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.02383

A Game-Theoretic Decision Framework for Optimal Selection of Coordination Detection Methods in Multi-UAV Fleet Operations

Christian Manasseh, Savana Ammons

原文摘要

Detecting coordination among unmanned aerial vehicle (UAV) fleets operating in shared airspace and identifying the route-lead aircraft whose navigation decisions govern fleet behavior presents a fundamental speed--accuracy trade-off: fast methods enable real-time traffic management but sacrifice detection fidelity, while accurate methods may exceed the time budget for actionable airspace deconfliction. This paper presents a game-theoretic decision framework that resolves this trade-off by formulating method selection as a two-player zero-sum game between a Monitor (selecting computational methods and parameters) and Nature (selecting the unknown traffic scenario). We construct an end-to-end pipeline from trajectory surveillance data through eight candidate detection algorithms, a Monte Carlo sensitivity analysis characterizing their stochastic performance, and finally a multi-objective optimization layer that identifies Pareto-optimal method portfolios. The minimax solution provides a robust mixed strategy with a probability distribution over methods that guarantees worst-case performance regardless of scenario uncertainty. Experimental evaluation across 200 randomized configurations spanning 5--50 aircraft demonstrates that the framework recommends distinct method portfolios depending on operational priority: Koopman Phase dominates balanced (70.6%) and speed-priority (79.7%) profiles, while CRQA emerges as primary (47.4%) when route-lead identification is prioritized. The framework achieves a guaranteed game value of 0.29--0.53 (normalized utility) across all tested preference profiles, providing the first principled, scenario-adaptive methodology for computational method selection in UTM fleet monitoring operations.

cs.MA · cs.GT · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05731

Prospective Memory for Proactive LLM Agents

Yuanchen Bei, Zhining Liu, Tianxin Wei, Weizhi Zhang, Zhichen Zeng, Philip S. Yu, Hendrik Hamann, Jingrui He 等 9 位作者

原文摘要

Most memory systems for LLM agents are retrospective, preserving and retrieving past information to inform current decisions. Proactive agents, however, also require prospective memory: retaining future-directed intentions and realizing them when appropriate opportunities arise, even without explicit requests. Crucially, remembering the right intention does not guarantee acting at the right time: a related observation may call for waiting, while a later cue may make the same intention actionable. Inspired by cognitive theories of human prospective memory, we introduce Pro-Memory, a memory framework that separates maintaining future intentions from deciding when and how to realize them. Pro-Memory preserves pending objectives linked to their supporting evidence, assesses new observations against their original goals and activation conditions, and coordinates appropriate contributions with the agent's ongoing actions. It further updates intention states based on actions actually issued or evidence of resolution, while an experience memory distills feedback from completed episodes into guidance for future decisions. Experiments on two benchmarks spanning delayed-intention tasks and open-ended proactive assistance demonstrate consistent improvements in proactive task performance over representative memory approaches across multiple LLM backbones, while limiting unnecessary interventions.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.26516

Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning

Julian Asilis, Shaddin Dughmi, Vatsal Sharan, Alec Sun, Shang-Hua Teng, Chang Wang

原文摘要

Two of the most fundamental questions in statistical learning theory are the following: which prediction problems are learnable, and how should they be learned? For the former, elegant answers often take the form of combinatorial dimensions. The latter question, however, has proved considerably more elusive: all known general-purpose multiclass learners rely on intricate orientations of exponentially large one-inclusion structures, and familiar algorithmic principles such as proper learning and regularization remain poorly understood. Motivated by prior work, we ask whether learning reduces to proper learning---possibly over a larger hypothesis class---and whether proper or improper multiclass learning can ultimately be captured by suitable regularizers. Our primary results answer both questions negatively, resolving three open problems from prior work. First, we exhibit a learnable multiclass problem that cannot be embedded in any properly learnable class, meaning learning cannot be reduced to proper learning by enlarging the hypothesis class. Second, we demonstrate that proper learning can require training error and characterize this phenomenon precisely: every properly learnable class admits a proper learner making $o(m)$ errors on samples of size $m$, but every prescribed sublinear scale $a_m=o(m)$ is necessary for some properly learnable problem. Third, regularization is not a general learner: we exhibit a properly learnable class that cannot be learned by any Structural Risk Minimization (SRM) learner, and a learnable class that cannot be learned by any local regularizer. We complement these impossibility results with a positive theory that gives two sufficient conditions for SRM learnability and characterizes SRM representability through integrability of revealed preferences.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05728

Generative Modeling for Cascading Extremes via Autoregressive Transformers

Miguel de Carvalho, Myung Won Lee, Jordan Richards, Sotirios Sabanis

原文摘要

Extreme events often occur sequentially, from earthquake-tsunami cascades to successive extreme losses in financial markets. We introduce an extremal token representation that encodes multivariate observations as a categorical sequence. A quiet token records the absence of threshold exceedances; otherwise, the token identifies the exceeding component with the largest marginal probability-scale score. The representation is invariant to componentwise strictly increasing transformations. It preserves the identity and temporal ordering of dominant exceedances but discards their magnitudes and the identities of nondominant simultaneous exceedances. A decoder-only transformer estimates the history-dependent next-token kernel on this representation, and recursive sampling generates future token sequences from the induced joint predictive law. We amortize our generative model by pretraining across simulated process families with varying parameters and dependence persistence. Next-token predictions are evaluated against exact conditional probabilities for held-out categorical processes and particle filter references for heavy-tailed vector autoregressive processes. Applied to ten-second returns for five semiconductor stocks, the pretrained model supports zero-shot transfer, while a few epochs of adaptation improve agreement between observed and generated token frequencies and transition patterns. These results support task-specific tokenization and simulation-based pretraining for modeling which dimensions dominate multivariate extremes.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05726

Do Language Models Know Which Constraints Belong Together?

Junbo Jacob Lian, Kaixuan Chen, Hanzhang Qin, Huiling Chen, Chaoyu Zhang, Chung-Piaw Teo

原文摘要

Dantzig-Wolfe reformulation strengthens the linear relaxation of a mixed-integer program by convexifying a chosen set of constraint families, and every candidate costs a column generation run. The choice is hard when families strengthen the bound only together, because a search that adds one family at a time then stops at the linear relaxation. The classical inequalities of lot sizing, network design and facility location rest on such zero-marginal groups. We prove that when each evaluation convexifies at most $s$ of $k$ families, any method that observes only bounds needs a covering number of evaluations, of order $k^w$, to find a hidden group of $w$ families, also on actual Dantzig-Wolfe relaxations. A prediction that misses $e$ members reduces the cost to $Θ(k^e)$, through one staged search that does not need to know $e$, so the evaluations a prediction saves measure what the predictor knows. We study two sources of predictions. A one-pass lookahead at an optimal LP dual is provably blind to groups whose families share no variable, and a language model reads the names and text of the model. JointDW verifies the prediction of the language model with the staged search and interleaves it with the lookahead at a bounded loss. Groups that strengthen the bound only jointly appear in a quarter of the MIPLIB-NL models whose bound can be improved. There the strongest language models identify them about as often as the lookahead, their predictions rest on the names for textbook models, and reasoning about doubles the accuracy of the same model. On larger models with distracting families, the lookahead finds the group in one evaluation of three families. Language models given only the text seldom name it, while one reasoning model given every coefficient names it in all but one answer and then needs fewer evaluations than the lookahead for pairs of families.

cs.LG · cs.AI · cs.DS · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05725

Faster Approximate Text-to-Pattern Hamming Distances via Near-Optimal Sumset Estimation

Nick Fischer, Yael Kirkpatrick, Vasileios Nakos

原文摘要

\emph{Text-to-Pattern Hamming Distances} is one of the most studied problems in string algorithms: given a text $T$ of length~$n$ and a pattern~$P$, the task is to compute the Hamming distance between~$P$ and every length-$|P|$ substring of~$T$. As exact algorithms have been stuck at time~$\tilde O(n^{3/2})$ for decades, a long line of work has turned to the $(1+ε)$-approximate version of the problem. Milestones include Karloff's $\tilde O(ε^{-2} n)$-time algorithm [IPL '93], followed by randomized improvements to $\tilde O(ε^{-1} n)$ by Kopelowitz and Porat [FOCS '15] and recently to $\tilde O(ε^{-0.915} n)$ by Chan, Jin, Vassilevska W., and Xu [FOCS '23]. In this work, we significantly improve this bound to $\tilde O(ε^{-2/3} n)$, using a considerably simpler algorithm. Our algorithm follows the framework of Chan, Jin, Vassilevska W., and Xu, which reduces the problem to a variant of 3SUM that we call \emph{Sumset Estimation}. We solve Sumset Estimation optimally (up to logarithmic factors) by replacing their matrix multiplication techniques with ideas from sparse recovery. Specifically, we adapt the classic Count Sketch by replacing its random signs with random complex roots of unity---a simple idea that may find further applications for other additive problems. Finally, we give evidence that our running time might in fact be optimal: we show that the $ε^{-2/3}$ dependence is \emph{best possible} for a certain natural class of algorithms, including ours and all previous algorithms.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05724

Give the Drafter a Second Chance to Guess: Parallel Reconsideration for Speculative Decoding

Hoang Anh Duy Le, Huibing Dong, Alireza Khadem, Ziteng Sun, Xiang Song, Yizheng Huang, Soroush Radpour, Anshumali Shrivastava 等 9 位作者

原文摘要

Speculative decoding accelerates large language model inference with a small drafter, whose per-guess acceptance rate determines the achievable speedup. Feature-level drafters share a design choice: every token, easy or hard, is drafted under a single forward pass. Many of the tokens the target rejects are ones the drafter is itself unsure about yet the target answers decisively. To address this, we introduce Parallel Reconsideration: guided by its own uncertainty, the drafter reconsiders its hesitant guesses with extra passes that run in parallel with the one-pass draft, adding negligible latency. A co-designed training recipe and serving-time drafting algorithm append these reconsidered guesses to the original draft tree as refined candidates. Across models and benchmarks, on average, Parallel Reconsideration improves over the baselines by 5.3% to 10.2% on acceptance length and by 3.5% to 9.2% on speedup.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05722

Trinetra.Q: Statistical and Behavioral Detection of Attacks on the Quantum-Error-Correction Layer and Classical Control Stack of Quantum Computing Systems

Garrv Sipani

原文摘要

Most quantum-computer security work targets physical-layer attacks on qubits, while two surfaces remain inadequately defended: the quantum-error-correction (QEC) syndrome-and-decoder pipeline, and the classical control and software stack that runs it. Tampering on these surfaces can corrupt a computation while the physical error rate appears normal, and can stay within a single-circuit integrity tolerance. We present Trinetra.Q, a detection layer of cooperating detectors, each monitoring a statistical or behavioral property of quantum-domain data against an envelope calibrated from honest operation, and raising an indication only on a statistically significant deviation. The detectors cover (A) QEC integrity over per-stabilizer firing rates, syndrome defect-count, and repeated-syndrome rate; (B) decoder confidence over the margin between minimum-weight error explanations in distinct logical classes; (C) behavioral output divergence, flagging crosstalk-class and novel attacks by their effect on a victim's output relative to a matched control; (D) control-stack tampering via known-answer canary circuits, built to be indistinguishable to a resident implant, with a cross-job consistency statistic; and (E) compilation/execution integrity. Each gates on significance, so honest operation raises no alarm. We evaluate in faithful simulation and on three production IBM Heron processors, and bound the physical attack surface with a systematic negative map: most physical-layer attacks return statistically null, the exception an implemented, measured within-job feed-forward covert-channel primitive. Every detector is also evaluated against an adaptive attacker with full knowledge of it. To our knowledge this is the first unified statistical-and-behavioral detection layer for the QEC layer and classical control stack of a quantum computing system, demonstrated on production hardware.

quant-ph · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.14994

Sharp Bounds on the Eigenvalues of Kikuchi Graphs and Applications to Quantum Max Cut

Ainesh Bakshi, Arpon Basu, Pravesh Kothari, Anqi Li

原文摘要

We prove that the maximum eigenvalue of the (both signed and unsigned) Laplacian of level $k$ Kikuchi graph of any graph $G$ with $m$ edges is at most $m+k$. This confirms four recent conjectures of Apte, Parekh, and Sud. As applications, we obtain that tensor products of one and two qubit product states achieve an approximation ratio of $5/8$ for Quantum Max Cut and $5/7$ for the XY Hamiltonian. Moreover, combining our bounds with the algorithms analyzed by Apte, Parekh, and Sud, yields efficient algorithms achieving an approximation ratio of $0.614$ for Quantum Max Cut and $0.674$ for the XY Hamiltonian. Finally, we also make modest progress on Brouwer's conjecture and improve Lew's bound on the sum of the top-$k$ eigenvalues of a Graph Laplacian.

quant-ph · cs.DS · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06957

An Integrality-Gap Lower Bound of 1.2325 for Minimum Multiway Cut

Dimitar Chakarov, Yury Makarychev

原文摘要

We prove that the integrality gap of the Călinescu-Karloff-Rabani relaxation for Minimum Multiway Cut is at least $1.2325$ when the number of terminals is large. By a result of Manokaran, Naor, Raghavendra, and Schwartz (2008), it is therefore NP-hard, under the Unique Games Conjecture, to approximate Minimum Multiway Cut within a factor of $1.2325$. This improves the previously best known lower bound of $1.20016$ due to Bérczi, Chandrasekaran, Király, and Madan (2020).

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05720

Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis

Yanru Xiao, Yingwei Yu

原文摘要

Search can help LLM agents correct mistakes, but their starting conditions may shape which evidence they find and use. Drawing on cognitive-bias paradigms, we develop a controlled search harness to examine result order, records of prior work, and initial hypotheses while holding each question and document collection fixed. Matched controls distinguish order effects from differences in document composition and the effects of failed work from context length. Across 10 models and 1,000 synthetic search worlds, we track queries, retrieved documents, document openings, and final answers. Our comparisons suggest that final answers are more sensitive to initial evidence order during active search than when all evidence is supplied in full. Dead-end histories can reduce strategy switching relative to matched neutral histories, indicating an effect beyond context length. Under wrong hypotheses, stage measurements distinguish reduced retrieval or opening from errors that persist after counter-evidence is opened. Exploratory interventions show that opening counter-evidence more often can coincide with lower accuracy, while accuracy can improve with little change in opening.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.10834

Landscape Analysis of Simultaneous Blind Deconvolution and Phase Retrieval via Structured Low-Rank Tensor Recovery

Xiao Liang, Zhen Qin, Zhihui Zhu, Shuang Li

原文摘要

This paper studies the landscape of the simultaneous blind deconvolution and phase retrieval (BDPR) problem via a structured low-rank tensor recovery framework. Since the complicated sensing structure makes direct landscape analysis technically challenging, we introduce a tractable tensor sensing surrogate that preserves the essential low-rank structure. We first analyze its population risk, characterize the global landscape on the unit sphere, and establish local linear convergence of Riemannian gradient descent (RGD) under mild conditions. We then extend the analysis to tensor sensing under a tensor restricted isometry property (TRIP), establishing local geometric and RGD convergence guarantees, and quantify robustness to measurement noise. Our theoretical results are further supported by extensive numerical experiments. These findings offer insights into the optimization landscape of the surrogate tensor sensing problem, thereby providing guidance for studying and solving the original BDPR problem.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02356

Exploiting Textual Semantics for Robust Cross-View Object Correspondence

Bing Fan, Yunhe Feng, Yan Huang, Heng Fan

原文摘要

Cross-view object correspondence (CVOC) aims to establish associations of the same target between query and search videos captured from different viewpoints. Existing methods often rely on visual cues for CVOC. Despite recent progress, these methods struggle in complicated scenarios with substantial viewpoint changes and appearance variations, due to lacking sufficient target information. Addressing this, we introduce TeSCo, a framework that exploits rich Textual Semantics of an object, in addition to its visual cues, for cross-view object Correspondence. Our key insight is, textual description of a target, by capturing diverse attributes such as category, texture, and color, provides viewpoint- and appearance-invariant semantics, which are complementary to visual cues and can hence enhance correspondence robustness in complicated scenes. Inspired by this, TeSCo first generates a textual expression of the target from the given query view using a vision-language model, and then extracts textual feature to enhance visual features for localization in the search view. To realize this, we introduce a text-conditioned cross-modal fusion (TCF) module that incorporates the textual feature into visual features with text-guided modulation, producing more robust multimodal target representation for object correspondence. Since not all textual cues are equally compatible with the target in current search-view frame, we propose an iterative textual feature refinement (ITFR) module that progressively adjusts textual feature using search-view information before the TCF module, enabling search-view-aware textual semantics to be fused into visual features and leading to better performance. In extensive experiments on Ego-Exo4D and HANDAL-X, TeSCo demonstrates state-of-the-art results and largely outperforms other models, validating its efficacy. Our code is released at https://github.com/VAIL-Fan/TeSCo.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05717

Same Method, Different Task: What the Bitter Lesson Does Not License in Social Simulation

Justin Downes, Robby Milletich, Newel Hirst

原文摘要

The bitter lesson holds that general methods leveraging computation defeat hand-encoded domain knowledge. We argue it carries a condition its popular reading omits: in every case Sutton cites, the general method was scaled against the same task the domain engineering was solving. Social simulation substituted across tasks instead, replacing hand-built agents with an artifact optimized for predicting text. The move is bitter-lesson-shaped, but the lesson does not license it. Prediction is a solitary act: the predictor bears no consequences from the interaction it models. Cooperation, defection, and norm enforcement are phenomena of interested parties; they do not exist for a disinterested observer at any scale. What is missing is not emergence, which LLM populations already show, but stakes. We show that several anomalies reported in prior work (excess cooperation that predates alignment training, collective agreement without individual fidelity, and population homogeneity) follow from this account. A 540-agent pilot with pre-specified hypotheses, which tests sensitivity to persistent consequences rather than cooperation, finds that consequences reshape strategies in two of three model families but never produce human-like heterogeneity. We argue for mixed-motive settings that shape agents rather than only test them, and ask whether agents should be pretrained differently from predictors.

cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05716

How Much Do Modern Embeddings Reveal? Inversion Attacks on Commercial Embedding Models

Kareem Elaasar, Cristina Lopes

原文摘要

Text embedding inversion reconstructs source text from fixed-dimensional vectors, posing a privacy risk to systems that store embeddings instead of raw text. We adapt the vec2text framework (Morris et al., 2023) to support text-embedding-3-small and mistral-embed alongside GTR-base. We evaluate 800 samples per category across general instructions, Wikipedia passages, paraphrased instructions, health-related instructions, and short literal code snippets, using a common 60-80-character range and paired original and paraphrased instructions. Under the evaluated vec2text configuration, text-embedding-3-small achieves the highest exact-match rate in all five categories, including 47.4% on health-related instructions and 24.5% on general instructions under the evaluation's case-insensitive, whitespace-stripped matching rule. BERTScore F1 exceeds 87 on the 0-100 scale for every prose category and embedder, indicating high contextual similarity to the references. Short code snippets yield lower reconstruction scores. These findings characterize one attack configuration and the selected datasets; they do not establish attack-independent rankings or sensitive-attribute recovery rates. They nevertheless motivate explicit assessment of inversion risk and access controls for stored embeddings.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06956

Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning

Tianming Sha

原文摘要

Multi-agent LLM systems explore in parallel by spawning sub-agents with isolated context windows, whereas single-agent systems append every search and verification step into one growing trajectory. However, existing multi-agent frameworks duplicate prefix KV caches across branches, exchange findings by re-prefilling text summaries, and flatten or drop cross-branch dependencies during reinforcement learning (RL). We introduce Octopus, a single-model multi-agent RL framework in which all threads share one backbone and coordinate over a GPU-resident directed acyclic graph (DAG) of KV states through five primitives (fork, read_thread, wait_threads, rewind, commit). Octopus combines three co-designed mechanisms: (1) Zero-Copy Radix Forking, which spawns branches as $\mathcal{O}(1)$ cursor views over shared physical KV pages; (2) Attention-Only KV Mounting, which mounts a sibling thread's terminal KV blocks directly into full-attention layers while bypassing linear-recurrent states (Gated DeltaNet / Mamba-2), cutting off-task hijacking by $21\times$ ($57.9\% \to 2.7\%$) while retaining $92.2\%$ of full-text mutual information at zero extra KV allocation; and (3) a Packed DAG-GRPO Trainer, which packs all episode branches into one block-sparse attention pass and assigns counterfactual branch credit via leave-one-branch-out marginal rewards. Trained end-to-end with GRPO on Qwen3.5-4B over a sparse BM25 corpus, Octopus reaches $49.6\%$ accuracy on BrowseComp-Plus ($+17.5$ points over single-agent GRPO at 143K context and $+12.5$ points over text-summary multi-agent RL) and $51.2\%$ on OpenResearcher, outperforming dense-retrieval agents up to $250\times$ larger while increasing training throughput $3.3\times$ and cutting peak KV memory $2.8\times$.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05715

CoReFlow: Consistency-Relaxed Flow Maps for Probabilistic Traffic Forecasting

Pengnan Chi, Zhiguo Zhang, Xiaoliang Ma

原文摘要

Probabilistic traffic forecasting is essential for reliable Intelligent Transportation Systems (ITS), as it captures uncertainties in complex road networks. Recent diffusion- and flow-based generative models have facilitated uncertainty modeling through a multi-step sampling process. However, beyond slow inference, this process is designed to capture complex multimodal distributions, which misaligns with the limited complexity of the conditional traffic data distribution, causing models to underperform deterministic baselines. To address this, we introduce the \underline{Co}nsistency-\underline{Re}laxed \underline{Flow} Map (CoReFlow) model, presenting the first effort to leverage the one-step generation capability of flow maps, known as solution operators of probability-flow ordinary differential equations. Besides, we improve accuracy using a concise training objective that supervises the model via interpolation endpoints over finite time intervals. Unlike existing methods (e.g., self-distillation and MeanFlow Identity) that maintain trajectory consistency to model multimodal distributions, our objective leverages conditional mean to restrict the consistency, thereby achieving higher accuracy in the probabilistic traffic forecasting task. Extensive experiments on four real-world datasets show CoReFlow achieves state-of-the-art forecasting accuracy. It surpasses recent baselines, provides competitive uncertainty modeling, and reduces inference costs compared to existing generative baselines.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.18008

TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots

Fangrui Huang, Souhad Chbeir, Arpandeep Khatua, Sheng Wang, Sijun Tan, Kenan Ye, Lily Bailey, Merryn Daniel 等 11 位作者

原文摘要

Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks--fail to capture the clinically critical dimensions of psychotherapy. We introduce THERAPYGYM, a framework that evaluates and improves therapy chatbots along two clinical pillars: fidelity and safety. Fidelity is measured using the Cognitive Therapy Rating Scale (CTRS), implemented as an automated pipeline that scores adherence to CBT techniques over multi-turn sessions. Safety is assessed using a multi-label annotation scheme, covering therapy-specific risks (e.g., failing to address harm or abuse). To mitigate bias and unreliability in LLM-based judges, we further release THERAPYJUDGEBENCH, a validation set of 116 dialogues with 1,270 expert ratings for auditing and calibration against licensed clinicians. THERAPYGYM also serves as a training harness: CTRS and safety-based rewards drive RL with configurable patient simulations spanning diverse symptom profiles. Models trained in THERAPYGYM improve on expert ratings, with average CTRS rising from 0.10 to 0.60 (and 0.16 to 0.59 under LLM judges). Our work enables scalable development of therapy chatbots that are faithful to evidence-based practice and safer in high-stakes use.

cs.CL · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05713

Incremental Minimum Spanning Trees on a Napkin

Lucian Bicsi, Adrian Budău

原文摘要

In the incremental minimum spanning forest problem, weighted edges arrive one at a time. After each insertion we must report the edge that leaves the minimum spanning forest, and queries ask for the bottleneck distance of two vertices: the smallest possible maximum edge cost on a path between them. Link-cut trees solve both in $O(\log n)$ amortized time. In 2021 we wrote the folklore BottleneckTree, a short competitive-programming structure that stores one parent pointer and one cost per vertex, and conjectured that it also runs in $O(\log n)$ amortized time. We show that this conjecture is false: on a family of inputs, its amortized cost per operation is $Ω(\sqrt{n})$. We then present a structure with the same state, two arrays and a single loop, and prove that it runs in $O(\log n)$ amortized time per insertion and per query. Unlike the AM-tree of Ding, Gu and Sun, which attains the same bound, it stores no subtree sizes and maintains no balance invariant. For a connected graph with distinct costs, the structure can be viewed as an implicit link-cut tree on the Kruskal reconstruction tree: each rotation corresponds to exactly one preferred-child change, and each skip acts on a stale path-parent pointer. In experiments it is 1.3-2.1 times faster than the folklore BottleneckTree on insertions, up to 480 times faster on its adversarial input, and 6.3-16 times faster than an explicit link-cut tree.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05712

Reachability Diameter: Beyond the Square-Root Barrier, with Polynomial Hardness

Hector Tierno, Shuang Yang

原文摘要

The reachability diameter of a directed graph is the maximum finite shortest-path distance across all pairs of vertices. It has received recent attention under this name, although the underlying quantity has long played a central role in shortcut set and parallel reachability. Notably, Bals et al. establish hardness for every polynomial-factor approximation in nearly-linear time for weighted digraphs. Yet they give $n^{1/2+o(1)}$-approximation in the unweighted regime with nearly-linear running time, and their conditional lower bounds rule out certain constants only, leaving open whether polynomial loss is necessary. We give a randomized algorithm that estimates the reachability diameter of an unweighted digraph within a factor $n^{1/3+o(1)}$, with high probability, in $\widetilde{O}(m+n)$ time. We complement our algorithm with a lower bound conditional on the 3-uniform Hyperclique hypothesis, ruling out an $n^{2/15-\varepsilon}$-approximation in $\widetilde{O}(m+n)$ time for every fixed $\varepsilon\in(0,2/15)$, establishing the necessity of polynomial loss for nearly-linear time algorithms.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.14386

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning

Taebong Kim, Youngsik Hong, Minsik Kim, Sunyoung Choi, Jaewon Jang, Junghoon Shin, Minseo Kim

原文摘要

We present Darwin Family, a framework for training-free evolutionary merging of large language models via gradient-free weight-space recombination. We ask whether frontier-level reasoning performance can be improved without additional training, by reorganizing latent capabilities already encoded in existing checkpoints. Darwin introduces three key ideas: (i) a 14-dimensional adaptive merge genome enabling fine-grained component- and block-level recombination; (ii) MRI-Trust Fusion, which adaptively balances diagnostic layer-importance signals with evolutionary search through a learnable trust parameter; and (iii) an Architecture Mapper that enables cross-architecture breeding between heterogeneous model families. Empirically, the flagship Darwin-27B-Opus achieves 86.9% on GPQA Diamond, ranking #6 among 1,252 evaluated models, and outperforming its fully trained foundation model without any gradient-based training. Across scales from 4B to 35B parameters, Darwin models consistently improve over their parents, support recursive multi-generation evolution, and enable a training-free evolutionary merge that combines Transformer- and Mamba-based components. Together, the Darwin Family demonstrates that diagnostic-guided evolutionary merging is a practical and reproducible alternative to costly post-training pipelines for reasoning-centric language models.

cs.NE · cs.AI

查看论文
arXiv ↗PDF ↗