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：2026-11-07 20:41 · 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 2026-11-06 21:46 — 2026-11-07 21:46（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：2026-11-07 20:41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 2026-11-07 20:35（北京时间）
版本更新 · v2arXiv:2510.07697

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs

Man Hu, Xinyi Wu, Zhufeng Suo, Jinbo Feng, Linghui Meng, Yanhao Jia, Anh Tuan Luu, Shuai Zhao

原文摘要

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as adversaries can exploit these capabilities to conduct backdoor attacks. Existing surveys on backdoor attacks and reasoning security offer comprehensive overviews but lack in-depth analysis of backdoor attacks and defenses targeting LLMs' reasoning abilities. In this paper, we take the first step toward providing a comprehensive review of reasoning-based backdoor attacks in LLMs by analyzing their underlying mechanisms, methodological frameworks, and unresolved challenges. Specifically, we introduce a new taxonomy that offers a unified perspective for summarizing existing approaches, categorizing reasoning-based backdoor attacks into associative, passive, and active. We also present defense strategies against such attacks and discuss current challenges alongside potential directions for future research. This work offers a novel perspective, paving the way for further exploration of secure and trustworthy LLM communities.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03418

Myoelectric Control for Upper-Limb Exoskeletons: A Decoder-Shaper-Controller Framework, Design Guidelines, and Future Directions

Davide Costanzi, Eldison Dimo, Emanuele Feola, Mario Sedilesu, Francesco Pascucci, Andrea Calanca

原文摘要

Myoelectric Control Systems (MCSs) enable voluntary control of wearable robots through muscle activity. However, intention decoding, assistance shaping, and low-level actuator control are often not explicitly distinguished, making their contributions difficult to evaluate and compare. This review introduces a functional decoder-shaper-controller framework for continuous myoelectric control of upper-limb exoskeletons. The decoder estimates an intention-related variable from surface electromyography (sEMG), the shaper maps it to a control reference according to an assistance policy, and the controller realizes that reference through actuator control. This decomposition separates intention estimation from assistance-policy design and enables comparison of heterogeneous architectures. Representative approaches are critically examined in terms of module design, calibration, and evaluation. The analysis highlights that the shaper, despite determining the magnitude and shape of assistance, lacks established design and tuning methodologies and is often embedded within the decoder or controller. Key open issues include inconsistent reporting of assistance levels, limited use of interaction-aware stability and passivity tools, and insufficient validation across degrees of freedom, users, and tasks. Building on these findings, this review provides design guidelines for systematic module-wise tuning and identifies future research priorities to bridge the gap between accurate intention decoding and safe, effective, and generalizable assistance under real-world operating conditions.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06412

A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks

Quentin Le Roux, Marti Jimenez, Yannick Teglia, Philippe Loubet Moundi

原文摘要

The protection of mature, multi-stage Face Recognition Systems is crucial to system providers. This technical report targets the threat model most relevant to industry practitioners: although model training is performed in-house, training data is sourced from possibly-compromised third parties. Given this setting, we present three practical defense "tricks" against data poisoning-based backdoor attacks. The first operates at training-time, detecting poisoned identities during training or prior to a pipeline's deployment. The last two operate at inference-time, filtering suspicious inputs before an answer can be sent back to a potential attacker. Each method is presented with their motivation, algorithms and computational impact, and evaluated on realistic face recognition workloads. Our goal is to provide actionable hardening techniques to system providers.

cs.CV · cs.AI · cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06410

Polynomial $(2α+\varepsilon)$- and Quadratic $4$-Approximation Algorithms for the Biased Traveling Salesman Problem in Bipartitioned Networks

Jingyang Zhao, Trung Q. Duong, Een-Kee Hong, Hyundong Shin

原文摘要

The traveling salesman problem (TSP) is one of the fundamental problems in combinatorial optimization that asks for a minimum-cost Hamiltonian cycle in a complete undirected graph with $N$ vertices. For the metric TSP, where edge costs satisfy the triangle inequality, a long line of work has produced constant-factor approximation algorithms, culminating in the best-known approximation ratio $α<3/2-10^{-36}$. The biased TSP (BTSP) generalizes the metric TSP to bipartitioned networks: the vertex set is partitioned into two subsets, edge costs satisfy the triangle inequality within each subset, while edges crossing the partition may violate it by a certain bias factor. This model captures heterogeneous routing scenarios in which distances are metric only locally but may be distorted across different regions or vertex types. Previously, the only known result for the BTSP was a $7/2$-approximation algorithm with running time $O(N^3)$. In this paper, we present two new approximation algorithms that significantly improve the state of the art. The first achieves an approximation ratio of $2α+\varepsilon$ (strictly less than $3$) in polynomial time $N^{O(1)}$ for any constant $\varepsilon>0$, where the exponent grows at least linearly with $1/\varepsilon$. The second achieves a $4$-approximation in only $O(N^2)$ running time, reducing the previous cubic-time bound by a full polynomial factor. These advances directly support emerging networked systems---including multi-tier 6G architectures and hybrid quantum-classical networks---where cross-region transitions incur biased and non-metric overheads.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06409

Zero-Shot Coordination among LLM Agents

Adrian Hayler, Shashank Reddy Chirra, Andrei Lupu, Johannes Forkel, Bidipta Sarkar, Siheng Feng, Jakob Foerster

原文摘要

We study zero-shot coordination (ZSC), where independently developed agents must coordinate at test time. While ZSC has been well studied in the RL literature, far less is known about the performance of LLM agents despite their increasing deployment in such settings. Existing work on LLM coordination often relies on specialised scaffolding that independently developed agents are unlikely to share in practice. Moreover, evaluations on complex environments (e.g., Hanabi) make it difficult to pinpoint the sources of coordination failure. In contrast, we focus on simple, general-purpose scaffolds in minimal environments designed to isolate specific coordination challenges. Our results show that even in these controlled settings, frontier LLM agents struggle to coordinate, largely due to limited understanding of the coordination problem and weak reasoning about their partner's beliefs. While LLMs introduce semantic information as an additional axis for coordination, they nonetheless fail to exploit this structure effectively. Towards this, we propose Coordination-friendly definitions (CFDs) as a principled approach for enabling robust coordination among LLM agents. Finally, we show that CFDs can be discovered automatically, removing the need for manual engineering. Code is available at https://github.com/ahayler/zsc-llm-agents.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.11833

Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics

Sam Gijsen, Michał Łukomski, Marc-André Schulz, Kerstin Ritter

原文摘要

Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distribution contexts. Yet generative models of neural time series have largely remained restricted to categorical conditioning, precluding compositional and zero-shot generalization. In this work, we propose PINC-Flow, a per-timestep conditioned diffusion transformer for generating realistic fMRI brain dynamics during unseen cognitive tasks by injecting both compositional language and optional spatial priors in-context. Such zero-shot generation could enable counterfactual neuroscience by supporting in-silico design and evaluation of novel cognitive experiments before empirical validation. Leveraging this model, we evaluate across hundreds of held-out task conditions and characterize predictive performance in relation to the training manifold. From language alone, the model recovers region-specific recruitment across tasks and held-out spatial activation patterns. Spatial priors, when available, complement the text pathway by anchoring generation in regions of task space where language alone degrades, while retaining the compositional structure needed for counterfactual task specification. To our knowledge this is the first generative model of whole-cortex fMRI dynamics for unseen cognitive tasks, advancing counterfactual neuroscience and data-driven experimental design.

cs.LG · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30749

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance

Sungha Kim, Gawon Lee, Jusuk Lee, Jonghae Park, H. Jin Kim, Daesol Cho

原文摘要

Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians. While recent approaches incorporate expressive generative policies via importance-weighted supervised learning, they are prone to importance weight collapse, which limits their scalability in high-dimensional action spaces. Our key insight is to mitigate this limitation by localizing the sampling region, avoiding the weight degeneracy induced by importance sampling over the entire action space. To instantiate this insight, we introduce \textbf{FLAG} (\textbf{F}low policy with \textbf{L}atent-\textbf{A}ugmented \textbf{G}uidance). FLAG augments the state space with a flow latent variable and optimizes a provably consistent proxy MaxEnt-RL objective. We empirically demonstrate that FLAG enables expressive policy optimization with limited importance samples and scales to state-based high-dimensional control tasks. Furthermore, FLAG achieves state-of-the-art performance among expressive-policy MaxEnt online RL methods on state-based high-dimensional control benchmarks.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06403

Ruby-OPD: Enhancing Pronunciation Controllability and Accuracy for Flow-Matching Text-to-Speech via On-Policy Distillation

Rui Hu, Xiaolong Lin, Zhenpeng Zhan

原文摘要

Achieving both high pronunciation accuracy and fine-grained controllability remains a central challenge in Japanese text-to-speech (TTS), as Japanese is an unsegmented language mixing logographic Kanji and phonographic Kana with extensive polyphony. Traditional cascaded systems convert text into phoneme sequences via a front-end, ensuring pronunciation control but discarding lexical semantics and prosodic cues in surface orthography. Conversely, recent zero-shot TTS models directly consume raw orthographic text to improve naturalness, yet suffer from polyphone errors and lack explicit pronunciation control. To bridge this gap, we propose a two-stage framework for flow-matching TTS. First, we investigate Ruby text representations with orthography perturbation to jointly preserve surface forms and target pronunciations for reliable control. Second, we introduce On-Policy Distillation (OPD) on large-scale text-only corpora to enhance pronunciation accuracy on raw orthographic text without paired speech. On the Joyo-Kanji-Yomi benchmark, our model achieves 97.13% Accuracy, 2.02% Target PER, 0.70% Sentence PER, and 4.21% Sentence CER under raw text while retaining strong controllability.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06402

Interpretable Text Embeddings Based on Hierarchical Questions

Kohei Oda, Po-Min Chuang, Kiyoaki Shirai, Natthawut Kertkeidkachorn

原文摘要

QA-based text embeddings represent texts as vectors consisting of 1/0 answers to yes/no questions. Although these embeddings provide detailed information for interpretation and achieve high task performance, they often require humans to examine a large number of questions. Furthermore, the relationship between the number of questions and the appropriate level of question granularity has not been sufficiently studied. To address these challenges, we propose a method for constructing hierarchical questions for text embeddings. As the hierarchy deepens, questions become more specific and their number increases. During interpretation, we reduce the number of questions that humans need to examine by replacing questions at deeper levels with aligned questions at shallower levels. The question hierarchy is constructed through recursive clustering, contrastive prompting, and question alignment. Experimental results on general-purpose tasks show that our method improves interpretability while maintaining task performance. It is also found that, when only a limited number of questions are available, questions at shallower levels tend to achieve higher task performance than those at deeper levels, even with the same number of questions.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.16002

Decomposing one-class support vector machine into an ensemble of one-data support vector machines

Toshitaka Hayashi, Dalibor Cimr, Hamido Fujita, Richard Cimler

原文摘要

One-class Support Vector Machine(OCSVM) is a variant of support vector machine(SVM) for one-class classification (OCC). However, OCSVM has scalability issues with large datasets. This paper proposes an acceleration strategy for OCSVM. The idea is to decompose the dataset into samples and train OCSVM models for single data points. Subsequently, ensemble learning is applied to combine all models to compute the OCSVM model for the dataset. In addition, further acceleration is achieved through a support vector selection strategy with an OCSVM model trained on the average of the training samples. The experiment compared the proposal and traditional OCSVM using the Python package. The proposed strategy is faster than traditional OCSVM, while achieving similar classification results. Moreover, the proposed strategy can create a one-to-one correspondence between samples and models. Source code is uploaded at https://github.com/ToshiHayashi/ODSVM.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06967

Call-Level Revision Contracts for LLM-Authored Workflows

Chenyang Jiang, Benyang Pan, Puqu Wu

原文摘要

Durable execution engines replay a recorded history and do not compare activity payloads. When a model repairs a workflow that failed partway through, it must either pay again for calls that succeeded or accept a recorded result whose payload changed. We define a revision contract for workflows whose orchestration code is written by a model. Each capability call carries a structural identity built from its callsite, its fanout position, and its occurrence count, and the identity stays stable under rewrites that leave the call in place, so committed identities form a frozen prefix. The frozen unit is the call expression, and the surrounding code stays writable. A static gate rejects a rewrite that would change a committed call before a container starts. A runtime digest stops a changed payload at a committed identity, and an occurrence ledger names a repeated paid payload. Under three assumptions, a candidate the gate accepts replays every committed call it invokes, executes only new work, and reports the identities it skips. No local identity is both relocation-invariant and free of wrong reuse, so callsite identity turns a relocation into a pre-spend stop. On media workflows, 22 gate-passed repairs replay 258 committed identities with no duplicate, and a live six-way fanout makes seven paid calls instead of twelve. A 12-task customer-support study applies the same identity, replay, and boundary checks on two models.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06397

Where Should a KV-Cache Repair Budget Go? Distractor Structure and Contextual Compatibility in Non-Prefix Reuse

Yuxing Peng, Zhiqing Tang, Weijia Jia

原文摘要

Non-prefix KV-cache reuse encodes retrieved chunks independently and concatenates their caches. To find where a small repair budget should be spent, we vary the chunks around the answer-bearing one (the target) across three 7B-8B models and four datasets of dialogue memory, open-domain QA and API documentation. Reuse loses 19-100% of the context-dependent questions that full prefill answers, and it loses more when the other chunks are of the same kind as the target. Because the recoverable damage is spread over these other chunks, restoring a few of them recovers little, and the budget is better spent on the target. This works through contextual compatibility: recomputing the target against the reused cache beats inserting its full-prefill KV in all seven settings tested, although the recomputed KV stays far from the full-prefill KV. Question attention over reused caches, however, selects the target in at most 18.8% of development questions. A retriever finds it more often, and recomputing its top chunk after moving it next to the question significantly beats InfoFlow-style reordering at the same 5% budget in six of nine open-domain QA and API-documentation settings. On dialogue memory, though, recomputing chunks never significantly beats the token-level selector chosen for each setting.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06395

GIST: Gibbs-Targeted Hierarchical Data Selection for Offline RLVR

Xuliang Huang, Tianxiang Zhao, Chengwei Qin, Yao Shu

原文摘要

Offline reinforcement learning with verifiable rewards (RLVR) trains on a fixed pool of sampled responses and typically supervises every token of every response, although responses and tokens are not equally informative. We study which ones to supervise through the Gibbs-optimal policy of KL-regularized RLVR, which offline training targets, and measure the mismatch between a policy and this target with a bidirectional KL divergence. At the reference policy, this mismatch factorizes exactly and separates the two outcomes: correct responses contribute mainly through the forward term, concentrated on their low-probability tokens, and incorrect responses through the reverse term, concentrated on the responses the policy generates often and on their high-probability tokens. Based on this analysis, we propose GIST (Gibbs-Targeted Hierarchical Data Selection), a two-level selection method that approximates these principles with signals available before training. GIST uses the sampling temperature to select correct responses on-policy and incorrect responses near the policy's mode, and it uses the initial policy's token probabilities to supervise only the tokens where the mismatch lies. Applied to two offline training objectives, GIST raises the average accuracy over GSM8K, MATH-500, and MBPP for all three models under both objectives. In a controlled comparison on Qwen3-0.6B/GSM8K, it outperforms seven selection baselines that choose from the same candidates while supervising 66.6% fewer tokens than training on all candidates of the same prompts.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00892

Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs

Songming Yang, Hong-Tao Yu, Xiu-Shen Wei

原文摘要

Reinforcement learning (RL) post-training has become an important paradigm for improving multimodal large language models (MLLMs), especially with automatically verifiable rewards. Self-supervised visual pretext tasks provide such rewards without human annotations. However, existing methods mainly exploit within-instance structure, offering limited supervision for cross-instance discrimination and fine-grained comparison. We introduce Group-and-Order Self-Supervised Reinforcement Learning (GO-SSL), a cross-instance jigsaw framework for vision-centric MLLM post-training. Given two visual instances, GO-SSL mixes their local elements and trains the model to group them by instance of origin while recovering the order within each group, coupling instance-level comparison with spatial, temporal, or geometric structure recovery. This paired formulation turns the same unlabeled data into richer verifiable supervision through diverse pairings, shuffles, and a random-to-hard curriculum. We instantiate GO-SSL mainly on cross-image jigsaw tasks and further extend it to 3D depth and video temporal ordering. Across diverse benchmarks, GO-SSL consistently improves over the base MLLM and prior self-supervised post-training baselines, with clear gains in fine-grained perception and spatial understanding. Further evaluations across model scales and families support its generality. These results suggest that cross-instance comparison provides a useful self-supervised RL signal for improving transferable visual understanding in MLLMs. Code is available at https://github.com/SEU-VIPGroup/GO-SSL.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06394

KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data

Boyong Tang, Tao Wang, Lei Yang

原文摘要

Finding high-performing formulations is difficult when few have been measured and experimental budgets are limited. We propose KolTa, an active learning framework that selects batches to discover the top 5% of formulations at a target temperature under a fixed query budget. KolTa combines a three-stage predictor of component contributions, role-conditioned interactions, and anchored temperature response with task-specific soft physics constraints. Its Physics-Residual-Calibrated Upper Confidence Bound (PRC-UCB) acquisition rule combines predicted utility, ensemble disagreement, and a target-temperature physics residual, with nonnegative exploration weights fitted to out-of-fold signed errors. We evaluate the framework on three measured tasks and one simulated task covering binary-mixture viscosity, drug solubility, ionic-liquid viscosity, and electrolyte conductivity. KolTa ranks first or second in mean area under the learning curve (AULC) on every task and outperforms seven of the eight comparator strategies in paired tests, winning 75 of 78 paired comparisons across tasks and seeds against those seven strategies. Across the three measured tasks, its largest gap to the best mean AULC is 0.032, compared with at least 0.056 for every comparator. On Drug, reaching 80% average recovery of the remaining targets across drugs requires an estimated median of 348 additional formulation queries, about 18% fewer than the fastest comparator. Researchers can adapt the framework to diverse formulation problems through component roles and physical constraints.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.16031

Revisiting data-driven dynamic security assessment with a tabular foundation model

Olayiwola Arowolo, Maosheng Yang, Jochen Cremer

原文摘要

Data-driven pre-fault dynamic security assessment (DSA) rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning (ML). Existing approaches face two limitations. First, they require a large labelled database for training, with a separate model trained, tuned, and maintained for each contingency in a potentially long list of credible contingencies. Second, the trained models generalize poorly to unseen contingencies. This work addresses these limitations by using a tabular foundation model (TFM) that assesses stability through in-context learning, and requires no retraining or hyperparameter optimization. We use a single TFM to assess many contingencies at once, removing the need to train one classifier per contingency. We also characterize when using electrical distance coordinates (EDC) as continuous features enables the TFM to generalize to unseen contingencies and when it does not, showing how a few labelled samples can reliably improve generalization. Through comprehensive case studies on the IEEE 68-bus system, we show that a single TFM attains an average Macro F1 score of about 90\% with only 120 labelled samples per contingency, outperforming both classical ML and deep learning baselines, without any model retraining or hyperparameter tuning. For held-out contingencies, we show that using just 10 labelled samples of the new contingency with a modified EDC encoding matches the balanced accuracy of the best achievable transfer learning oracle model, which requires fully labelled data and is not deployable in practice. Overall, this initial study paves the way for developing and deploying foundation models for power system operations, with possible applications across multiple operational tasks.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06393

A Cracked Mirror: How People Perceive Gender Performance by Large Language Models

Faezeh Fadaei, Jenny Carla Moran, Taha Yasseri

原文摘要

How do large language models (LLMs) perform gender under zero-shot prompting, and how do people interpret those performances in conversation? Drawing on gender performativity, we examine how gendered meanings emerge through generated language, conversational context and human interpretation. In a preregistered randomised online experiment, 1,060 participants each had five short conversations with an LLM. We used minimal prompts to elicit performances from "very masculine" to "very feminine" and asked participants to rate their partner's perceived gender after each conversation. Mean ratings shifted in the direction of the prompts, but ratings at the extremes were closer to the midpoint than the prompt labels implied. When prompted to perform as "neither masculine nor feminine", the models were perceived as slightly masculine on average. Ratings varied across models and conversation topics. Women and men gave similar ratings at the extremes, but women rated the models as more masculine across the intermediate prompt levels. Participants' explanations illustrate how they drew on writing style, emotional expression and conversational interests, sometimes questioning the stereotypes behind their judgements. These findings suggest that conversational AI acts as a cracked mirror of gender norms. Models reproduce recognisable cues, and people interpret and sometimes challenge the meanings those cues carry.

physics.soc-ph · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06187

In-Context Black-Box Optimization with Unreliable Feedback

Nicolas Samuel Blumer, Julien Martinelli, Samuel Kaski

原文摘要

Black-box optimization in science and engineering often comes with side information: experts, simulators, pretrained predictors, or heuristics can suggest promising candidates. Such feedback can accelerate search, but can also be biased, input-dependent, or misleading. Feedback-aware Bayesian optimization methods typically handle tasks independently, limiting adaptation across feedback sources. In-context optimizers enable cross-task adaptation, but usually rely only on optimization history at test time. We study feedback-informed in-context black-box optimization (FICBO), where a pretrained optimizer conditions on both the observed history and cheap auxiliary feedback for the current candidate set. We introduce structured priors over how auxiliary feedback relates to the objective, and use them to pretrain a feedback-aware transformer across regimes ranging from highly informative to misleading. At test time, the model estimates source reliability in context by comparing observed objective values with auxiliary signals, improving query selection. On synthetic and real-world tasks, FICBO effectively exploits informative feedback while remaining robust to weak or misleading sources. Empirical investigations further illustrate how the model perceives test-time sources, offering insights into its interpretability and decision-making process.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06389

MA-Mesh: Resilient Multi-Agent Collaboration via Role-based Self-Healing

JunYong Lee, Woo Kyung Kim, Honguk Woo

原文摘要

Effective collaboration in multi-agent systems requires mechanisms for coordination and adaptability in dynamic and uncertain environments. However, existing multi-agent systems rarely model resilience explicitly, instead relying on ad-hoc output correction that limits systematic, runtime management of robustness. In this work, we propose Multi-Agent Mesh (MA-Mesh), a framework that constructs a role-based self-healing layer on top of a collaboration pattern. Specifically, MA-Mesh generates resilience-aware system specifications and synthesizes them into executable multi-agent policy code. To enhance resilience, we introduce two self-healing mechanisms: Cross-agent reflection, a mechanism that allows agents to evaluate not only their own outcomes but also the performance of their peers, enabling informed behavioral adjustments and collective policy refinement; Role-based failover, a strategy which dynamically reassigns roles and enables agents to substitute for one another when sub-tasks fail or agents underperform, ensuring continuity of task execution. Experimental results across diverse tasks (e.g., software development, tool use, scientific reasoning) demonstrate that MA-Mesh significantly outperforms existing multi-agent systems in both task performance and robustness under system uncertainty.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06387

Partially Dynamic Algorithms for Single-Source Temporal Paths

Davide Bilò, Bartłomiej Bosek, Jadwiga Czyżewska, Evangelos Kipouridis, Karol Węgrzycki, Anna Zych-Pawlewicz

原文摘要

We present efficient partially dynamic algorithms for maintaining earliest arrival times from a fixed source in temporal digraphs with $n$ vertices. For the incremental scenario where updates are arc insertions, our algorithm has a constant query time and requires a total update time of $O(n + m \log m)$, where $m$ is the total number of arcs added to the arc-less graph. For the decremental scenario where updates are arc removals, our algorithm has a constant query time and requires a total update time of $O(n + m \log m)$, where $m$ is the number of arcs in the graph upon its initialization. We also consider earliest-arrival queries with an arbitrary departure-time threshold and develop an incremental algorithm with $O(n+Δ_s m\log m)$ total update time, $O(\log m)$ query time, and $O(n+m)$ space, where $Δ_s$ is the number of distinct departure times of arcs leaving the source. All of our algorithms are also capable of reporting an earliest arrival path from the source to the queried vertex $v$ in constant time per edge once the earliest arrival time at $v$ is known. We complement our positive results with conditional lower bounds based on the Online Boolean Matrix-Vector Multiplication conjecture (a.k.a. OMv conjecture). For both the incremental and the decremental scenarios, we show the non-existence of an algorithm with $O(n^{1-\varepsilon})$ amortized update time and $O(n^{2-\varepsilon})$ amortized query time, even if the algorithm is randomized and latencies on the arcs are uniform. For arbitrary departure-time queries, we also establish an OMv-based conditional lower bound showing that our incremental algorithm is optimal up to logarithmic factors on dense temporal graphs. Thus, efficient total running time is essentially the best outcome we can get. Our conditional lower bounds hold also for the case of undirected temporal graphs.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06386

Shoot on (Core)Sight: Re-enabling Secure Debug on the RP2350 with Photon-Emission Microscopy and Laser Fault Injection

Antoine Plin

原文摘要

Fault-resistant policy storage does not guarantee fault-resistant enforcement. We demonstrated this distinction on the RP2350A4 using differential photon-emission microscopy (PEM) and laser fault injection (LFI). PEM narrowed the area for laser scanning, which found two sites where pulses set the DEBUGEN bits enabling core~1 Secure debug. An online attack sequence using only Serial Wire Debug (SWD) feedback restored sustained access. After rescue reset, the sequence recovered a 128-bit test secret. This reset reloads the secret's runtime page lock from a stored policy that permits Secure reads and prevents user firmware from tightening the lock.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06384

Presentation Sensitivity in Typed Decision Models for Subjective Text Evaluation

Jatin Agrawal, Radhika Mamidi

原文摘要

Typed decision models offer structured choices, scores, and probabilities for low-cost automated evaluation. We present a controlled audit of presentation sensitivity in Jev, Clef Flash, and Perplexity Decider across native choice and score interfaces. Across six datasets with 9,000 multiply annotated humor, helpfulness, and summarization items, we collect 702,000 judgments under interventions that vary positions, identifiers, authorship claims, endorsements, decision framing, and rating rubrics while preserving the evaluated texts. Jev's second-position probability advantage reaches 6.11 percentage points on summaries; reversing reader endorsements changes Perplexity's selected humor text on 40.40% of pairs; and rejection framing reduces Clef's summary agreement with human preferences by 23.36 points. Rating formats also shift score levels while often preserving rankings. Across these findings, repeatability, presentation robustness, and human alignment emerge as distinct properties of an evaluator. Reliable use therefore requires validating the decisions and score interpretations on which an evaluation pipeline depends.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06382

From hydrological laws to catchment models: A process-based model matches deep-learning accuracy on three continents

Xilin Xia

原文摘要

Dooge asked whether hydrology has laws at the catchment scale. We ask whether a low-dimensional system built under physical laws can match the accuracy of neural networks that outperform process-based models on the same inputs. Three laws constrain a lumped catchment model. Conservation makes it a flux-connected storage network, dissipation fixes the sign of every flux and aggregation determines how the unresolved composition enters the fluxes, through effective laws over threshold distributions and a memory of the forcing. These laws admit four kinds of refinement. A parsimonious model under them, CaRT (11 parameters per catchment), is refined in a loop assisted by AI agents. Each refinement addresses an observed deficit through a hypothesis from the literature. The result, CaRT+, has fourteen states, 35 parameters per catchment and no daily neural network. Most refinements follow from aggregation over thresholds or from variables that carry no water but modulate fluxes. On 602 British and 593 US gauged catchments, single CaRT+ models reach median Nash-Sutcliffe efficiencies of 0.863 and 0.765 in held-out years. A stateful LSTM reaches 0.869 and 0.751 and an entity-aware LSTM 0.862 and 0.754, while three-seed LSTM ensembles remain ahead of the CaRT+ ensemble by 0.003-0.012 in median paired NSE. On 505 drier Australian gauged catchments unused in development, single CaRT+ models reach 0.778 against 0.762 and 0.753 for the two LSTMs. The results suggest that catchment-scale laws exist as laws of form, with the constitutive families shared and only their parameters learned.

cs.LG · cs.AI · math.DS · physics.geo-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06381

LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution

Xinyu Yang, Jiejun Tan, Chenlong Deng, Chenghao Zhang, Tongyu Wen, Zhicheng Dou

原文摘要

As LLM-based agents develop, they have been increasingly applied in the legal domain. Legal Judgment Prediction~(LJP) requires models to conduct multi-step reasoning and external legal evidence retrieval. Existing legal search agents' performance is often constrained by the quality of retrieval queries. They often formulate queries directly from the initial user request, overlooking latent legal issues and legally salient details. To address this issue, we propose \emph{LegalEvolver}, a query optimization framework specifically designed to generate legally informative queries for LJP-oriented retrieval. Sampling high-quality optimized queries and their corresponding search trajectories is challenging, as relying solely on unguided high-temperature rollouts is both inefficient and constrained by the model's initial capabilities. We therefore heuristically optimize queries as seeds, improving the efficiency of trajectory generation. Furthermore, we summarize rollout experience into rubrics and use them to guide multi-round iterative self-evolution. Iteratively performing rubric optimization and rubric-guided RL enables the model to surpass its initial performance ceiling. End-to-end performance on extensive benchmarks demonstrates the effectiveness of query optimization on LJP. Comparisons with direct SFT followed by RL demonstrate the effectiveness of rubric guidance. Evolving rubrics further outperform fixed rubrics, confirming the benefits of self-evolution.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.01558

Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings

Pengfei Qu, Lei Ye, Wenyu Ouyang, Chi Zhang, Yikai Chai, Shuolong Xu, Yongri Piao, Miao Zhang 等 9 位作者

原文摘要

Accurate prediction in ungauged basins (PUB) requires effective transfer across hydrologically diverse regions. While deep learning has advanced large-sample hydrological modeling, its cross-regional generalization depends in part on the static basin descriptors used to guide model behavior. Earth Foundation Models (EFMs) provide a promising alternative by learning environmental representations from multi-modal satellite data. In this study, we evaluate the 64-dimensional AlphaEarth Foundations (AEF) embeddings as a new form of static basin representation and assess their value for streamflow prediction under both in-sample (IS) and out-of-sample (OOS) settings using the CAMELS dataset. Results show that AEF embeddings offer higher OOS robustness than CAMELS attributes, despite nearly identical IS performance. Mutual-information analysis reveals statistical associations between AEF embeddings and conventional catchment attributes related to terrain, vegetation, and rooting characteristics. We further investigate similarity-based donor-basin selection for PUB using CAMELS attributes and AEF embeddings. Across 100 target basins, AEF static inputs generally improved PUB performance. With AEF inputs, similarity-based donor selection outperformed random selection for smaller donor pools, but its advantage diminished as pool size increased. Adding more donor basins did not consistently improve performance. Leave-one-cluster-out experiments showed AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training. Overall, this study demonstrates that Earth Foundation Model embeddings provide a transferable representation for PUB prediction and underscores the importance of basin representation quality and donor pool design, motivating future research toward unified hydrological foundation models.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.28190

Connectivity Preservation and Graph Stretching in Range-Only Swarm Dispersion

Ariel Barel

原文摘要

We study connectivity-preserving finite-jump dispersion of anonymous, identical, and oblivious agents under an idealized range-only sensing model. Each agent measures only the distances to its visible neighbors, without bearings, identifiers, communication, memory, or a shared coordinate system. We derive the largest isotropic displacement certifiable as safe from these measurements alone. The resulting rule requires only the distance to the farthest visible neighbor: each agent selects a random direction and moves by half of its remaining visibility margin. The rule preserves every existing visibility edge under synchronous finite motion and therefore preserves connectivity. For two agents, we prove positive conditional drift in squared distance, almost-sure convergence to the visibility boundary, and finite expected time to reach any fixed neighborhood of that boundary. A one-million-run Monte Carlo experiment agrees with the exact first-round moments and estimates approximately 9.5 rounds to reach distance 0.97V from coincident initial positions; an independent Bellman-equation computation gives the same estimate. For general swarms, 1,000 runs across five initial-topology classes reproduce the deterministic safety guarantee at implementation level and reveal a consistent topology-dependent ordering of attainable diameter under the tested protocol. These results provide a theoretical foundation for connectivity-preserving multi-robot dispersion under minimal sensing, while isolating the guarantees achievable from anonymous range measurements alone.

cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06380

Does Context Compression Preserve Refusal Alignment?

Anthony Nguyen, Wenjun Lin

原文摘要

Context compression reduces inference cost by encoding inputs into compact representations while preserving semantic content. An open question is whether semantic preservation alone is sufficient to maintain downstream behaviours such as refusal alignment. We investigate this question and find that encoder-based compression systematically weakens refusal behaviour in instruction-tuned language models, despite high reconstruction fidelity. This effect persists across model families and compression architectures. Mechanistic analysis shows that compression attenuates activation along the decoder's learned refusal direction. We further explore Memory Steering, a lightweight inference-time intervention that restores refusal rates to near-baseline levels without retraining and operates entirely in compressed representation space. These results demonstrate that semantic preservation does not guarantee behavioural preservation under compression, highlighting the need to explicitly preserve alignment-relevant features in compression-aware systems.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06378

UniLoop: Unified Loop Closure Detection from Retrieval to Geometric Verification and Relative Pose Estimation

Jingwen Yu, Pengyu Wang, Jin Wu, Weinan Chen, Ping Tan, Hong Zhang

原文摘要

Loop closure detection conventionally cascades separate models for global retrieval, geometric verification, and relative pose estimation, leading to redundant computation and disconnected visual representations. We propose UniLoop, a unified framework that reuses the hierarchical representations of the pretrained geometric foundation model throughout this pipeline. A shared image encoder produces features for compact global descriptors; the same features are passed to the cross-view decoder for pairwise verification; and the original geometric predictions provide relative camera constraints for pose-graph optimization. Experiments on place recognition, loop verification, and relative pose estimation show that UniLoop improves loop-closure robustness and accuracy while reducing redundant backbone computation relative to modular pipelines. UniLoop achieves the best Recall@10 on MSLS (96.6) and Pitts30k (99.3) among the compared methods, while its verification branch reaches 95.63 AP and 96.29 ROC-AUC, surpassing the existing geometric verification baselines.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06377

NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation

Jiacheng Lu, Haoyi Zhu, Sipei Yi, Enze Xie, Cheng Zhuo, Yu Li

原文摘要

Autoregressive video models rely on historical key-value (KV) caches to preserve scene consistency over extended rollouts, making KV storage and repeated attention over history a growing memory and computational bottleneck. Aggressive compression can degrade generation quality, while reconstructing full-dimensional KV leaves attention computation largely unchanged. We introduce NanoKV, a frozen-backbone framework for generation-aware high-ratio KV compression. NanoKV exploits redundancy across tokens and attention heads by storing shared content in cluster centers and encoding joint head-channel residuals into low-bit coefficients. Crucially, NanoKV uses different fitting objectives for Keys and Values according to their distinct roles in attention: Key decoders are optimized to preserve downstream block outputs, whereas Value encoders and decoders are fitted for faithful reconstruction through the deployed quantization path. Building on the same compressed representation, the optional NanoKV-Fast variant reuses the stored coefficients for mixed-dimensional attention, reducing computation without modifying the video backbone. Across three autoregressive video backbones, NanoKV consistently improves the quality-storage trade-off. On HY-WorldPlay, NanoKV achieves $26.09\times$ effective KV compression, nearly twice that of KVTC, while improving PSNR by 1.0 dB. NanoKV-Fast retains $20.53\times$ effective compression and achieves an approximately $1.15\times$ end-to-end speedup over KVTC.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.19002

RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulation

Weronika Łajewska, Paul Missault, George Davidson, Saab Mansour

原文摘要

Simulating survey responses with LLMs offers a scalable alternative to costly human data collection, yet evaluation methods remain ad hoc and inconsistent. Current metrics, typically borrowed from adjacent domains, focus on accuracy or distributional similarity while overlooking ranking alignment-whether simulations preserve the relative preference orderings observed in human populations. A simulator may achieve low distributional divergence yet fail to identify the option humans most prefer, a critical gap for decision-making applications. We propose RADIUS, a two-dimensional alignment suite that evaluates survey simulation along complementary axes: 1) RA alignment and 2) DIstribUtion alignment, accompanied by statistical Significance testing. Experiments across multiple social surveys and persona sources demonstrate that RADIUS exposes limitations of single-metric evaluation and offers stronger discriminative power. On an independently reproduced simulator, we further show that distributional improvement often coincides with misidentifying the option humans most prefer - a decision-relevant error RADIUS surfaces but distributional metrics miss. We open-source RADIUS to support reproducible and comparable assessment of survey simulators.

cs.CL

查看论文
arXiv ↗PDF ↗