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

+2471新增论文
+2025其中 AI 相关
+163已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 19:33 · 全站最近入库：2026-11-10 15:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 20:27 — 2026-11-10 20:27（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：2026-11-10 19:33最近发现新增版本：2026-11-10 15:22库内论文最新更新时间：2026-11-10 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。

20,643 已收录论文17,531 AI 相关5,643 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 15,443 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 19:30（北京时间）
新论文 · v1arXiv:2611.08975

Beyond Truncation? Entailment-Licensed Elision and the Limits of Semantic Preservation in LLM Decoding

Mahmoud Alyosify, Mirna Imbabi, Eman Elkhamisi

原文摘要

Instruction-tuned large language models (LLMs) answer at greater length than a request needs. We ask whether a training-free controller inside the decoding loop can remove that surplus while preserving content, judged against the simplest possible baseline: truncating the model's own answer to the same length. An entropy-gated logits processor removes 25.5-34.9% of tokens on MT-Bench development questions and 19.9-34.2% on a sealed test split within pre-registered BERTScore non-inferiority margins, yet we prove and confirm by audit that its output is always a prefix of the unmodified answer: the saving is truncation. A survey of 23 training-free mechanism families finds none that selects content better than truncation without oracle labels. We therefore introduce Entailment-Licensed In-Decoding Elision (ELIDE), which, at each sentence boundary, withholds a span from the reader only when a natural-language inference model judges it entailed by the text already shown, while leaving the model's generation unchanged. ELIDE beats matched-length truncation on three model families, but reading 936 of its elisions on 670 public prompts shows that 59% harm the answer, a failure that no automatic measure detects. Scoping the licence to its discourse unit reduces the harmful share to about one elision in ten on two fresh tests.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.19119

Discretizing Continuous Time Series for Imputation with Masked Diffusion Training

Dongbin Kim, Seungyun Lee, Geonwoo Shin, Jaewook Lee

原文摘要

Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data. Existing approaches, however, exhibit two limitations: missing and observed values are embedded within the same representation space without explicit structural separation, and continuous diffusion-based methods recover the missing values only through many iterative denoising steps rather than by predicting them directly. To address these, we propose the Masked Diffusion Time-series Imputation Model (MDTIM), which leverages the training paradigm of masked diffusion model for imputation tasks. The [MASK] token is structurally orthogonal to valid observations, and because the corrupted state is the partially observed series itself, the model is trained to predict the missing values directly from the observed ones, naturally aligning both the representation and the learning objective with the imputation task. To bridge the gap between discrete masked diffusion and the continuous, ordinal nature of time series, we further introduce Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics. Our experiments on diverse benchmarks confirm that MDTIM achieves superior robustness and scalability, consistently outperforming state-of-the-art deterministic and generative baselines across various missing scenarios. Code and project page are available at https://dongbeank.github.io/MDTIM/.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05278

Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve

Shaanil Punglia, Dadhichi Telwadkar, Vaibhav Rathore, Siddharth Sureka, Neha Bhargava

原文摘要

Language-subspace interventions aim to improve multilingual reasoning by suppressing language-related components in mid-layer activations. Using MATH and MGSM across four open-weight LLMs, we ask three questions: do estimated language subspaces capture translation-associated variation? Does projecting them out remove language information? And do they improve accuracy without compromising response language? For the first question, we build subspaces using the existing Mean-SVD construction and our DiffPCA. Both capture substantial translation-associated variation and show similar patterns across model depth. For the second, we project out each subspace and train linear probes to classify language from the projected activations. The probes still identify language almost perfectly, showing that neither subspace exhaustively captures language information. For the third, we evaluate several intervention configurations on Qwen2.5-7B, by varying subspace creation methods and intervention operators. We find that the intervention that most improves MGSM accuracy sacrifices response-language fidelity, with only one intervention improving joint accuracy$\unicode{x2014}$answers that are correct and in the target language$\unicode{x2014}$slightly, by 1.60 points. Interestingly, subtle changes in the prompt alone can reproduce the accuracy gains albeit with significant damage to language fidelity. We argue that causal interventions must be judged on more than accuracy, to fully account for language substitution trade-offs.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08971

Phantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making

Disha Sheshanarayana, Rajat Subhra Pal, Manjira Sinha, Tirthankar Dasgupta

原文摘要

Multi-agent LLM systems increasingly aggregate judgments across model instances, but reasoning about other agents can itself introduce failure. We study a setting in which LLMs shift their public decisions after observing ambiguous social signals while reporting inaccurate estimates of what other agents privately judged, even when the group's recorded private judgments do not support the apparent consensus. We call this failure phantom consensus and study it as a pluralistic-ignorance-style pattern in controlled LLM collectives. To measure this phenomenon, we introduce PHANTOM-Bench, a benchmark that separates isolated private judgments, public decisions after ambiguous social signals, elicited estimates of the group's private judgment, transparency-based recovery, and controls for neutral public text and explicit vote-following. Across nine closed- and open-weight models, ambiguous public signals consistently degrade decision quality and can turn correct private group judgments into incorrect public collective outcomes. Public accuracy drops by as much as 47.8 percentage points, and collective rationality failures reach 47.3% in the most susceptible setting. We observe substantial errors in reported group-private beliefs alongside public-stage failures, while control conditions reveal model-dependent differences in susceptibility to ambiguous and explicit peer signals. Revealing the agents' recorded private decisions repairs many failures without revealing the gold label, although recovery varies across models. Our results show that evaluating multi-agent LLM systems requires measuring not only final agreement, but whether that agreement reflects independently measured private judgments or an apparent consensus.

cs.MA · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.08802

Improving Generalization Robustness of Multimodal RLVR

Pengfei Zhou, Zhiwei Tang, Chenrui Zhou, Lama Moukheiber, Yixing Ma, Bin Xu, Jiajun Song, Zhenglin Wan 等 13 位作者

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective. First, the binary verifier conflates format with content, so the reward signal cannot tell a wrong answer apart from a misformatted one. Second, the training distribution covers only a thin slice of the real-world prompts that the model might meet at deployment, so policies that perform well on the training distribution can behave differently under unseen prompts during test. Both failures call for a robust post-training method that helps the policy cover a broader distribution of semantically equivalent prompts, and we identify two measures that help achieve this objective: separating format from semantics in the reward, and applying policy invariance across perturbed prompts with equivalent semantics. We therefore propose Prompt-Invariant RLVR (PIRL), consisting of a dynamic trinary reward and a consistency regularizer based on an embedding-space adversary. Under stress testing, PIRL's average accuracy on benchmarks drops by only $\le 1\%$, where GRPO drops ~3%. On dynamic evaluation, PIRL also achieves the smallest performance drop.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08970

Adaptive Age of Information Optimization in Rateless Coding-Based Multicast-Enabled Sensor Networks

Hung-Chun Lin, Kuang-Hsun Lin, Hung-Yu Wei

原文摘要

As the demand for real-time information in Internet of Things (IoT) and Wireless Sensor Networks (WSN) scenarios grows with the evolution of bandwidth-intensive 5G applications, multicast transmission becomes increasingly vital. This paper delves into the significant role of multicast in WSN, exploring a novel perspective of using rateless codes over the traditionally employed Hybrid automatic repeat request (HARQ) for eliminating retransmissions in a wireless multicast system. We aim to optimize data freshness, quantified by the Age of Information (AoI), and analyze strategies to minimize time-average AoI in a multicast environment with diverse channel conditions. Specifically, our policy focuses on optimizing the time-average AoI based on sensor devices' feedback. We transform the problem into a Markov Decision Process (MDP) to locate optimal and low-complexity suboptimal policies. We present the first age-minimum scheme for rateless code-based wireless multicast systems. Our numerical simulations reveal that the proposed policies, developed considering unique system structural properties, consistently surpass baseline strategies. We are thus able to preempt updates at the most beneficial time, thereby addressing the issue of the bottleneck device's adverse impact on overall performance.

cs.NI · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08969

PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals

Yanlong Chen, Simone Benatti, Luca Benini, Cuntai Guan, Yawei Li

原文摘要

We present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J levels, C channels, and S temporal patches. Route-specific front ends and learned channel-name embeddings allow one Transformer per modality to handle diverse montages and sampling rates, while unseen setups reuse the backbone via lightweight adapters. We pre-train a 30M-parameter EEG model on over 15M windows (19--128 channels), alongside ECG (30M) and sEMG (12M) encoders. Across four EEG routes, scale folding cuts Transformer latency by 4.0--7.2x and peak memory by 6.8--12.7x over scale expansion without accuracy loss. Our EEG encoder leads 8 of 9 metrics against BENDR, BIOT, LaBraM, and EEGPT, and surpasses LUNA-L on wearable seizure detection with fewer parameters. Reliability-aware latent fusion (RALF) further integrates summary tokens from independently pre-trained encoders via sample-adaptive weights. On SeizeIT2, RALF raises event sensitivity at 11 false alarms/h from 61.4% to 74.4% and window AUPRC from 0.321 to 0.399 over the best unimodal baseline, outperforming weighted-logit and concatenation fusion across all variants. PhysioWave-T also achieves state-of-the-art sEMG accuracies and top macro-F1 on PTB-XL Super and Chapman-Shaoxing. Code and models: https://github.com/ForeverBlue816/PhysioWave.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08967

Using an LLM to Tackle Difficult Cases in NER for Nepali Tweets

Claire Wang

原文摘要

Named entity recognition (NER) is challenging for social media data in a low-resource language. LLMs often lag behind pretrained language models (PLMs) in NER performance, but they show promise in handling cases that PLMs struggle with. Using a dataset of Nepali tweets, we split the test set into "easy" and "hard" cases using token probabilities from a fine-tuned pretrained language model (PLM). We then evaluate an LLM on the hard test cases using 16 different prompt configurations. We find that selecting examples based on semantic similarity and increasing the number of examples improves F1 score by almost 10 points from the baseline configuration. Although the LLM underperforms the PLM on the full and easy test sets, it surpasses the PLM on the hard test set, resulting in an improved score when the two models are combined.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2605.13481

PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents

Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov, Alina Bogdanova, Mikhail Belkin, Ekaterina Lisitsyna, Artyom Sosedka, Victoria Dochkina 等 11 位作者

原文摘要

We introduce PersonalAI 2.0 (PAI-2), a novel framework designed to enhance LLM-based systems through integration of external knowledge graphs (KGs). The proposed approach addresses key limitations of existing Graph Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage pipeline. The central point of the PAI-2 design is its ability to perform adaptive, iterative information search, guided by extracted entities, matched graph vertices and generated clue-queries. Conducted evaluation on five benchmarks (Natural Questions, TriviaQA, HotpotQA, 2WikiMultihopQA and MuSiQue) demonstrates an improvement in the factual correctness of generated answers compared to baseline methods (LightRAG, RAPTOR, HippoRAG 2 and PAI-1). PAI-2 achieves a 9 percentage points (pp) average gain by LLM-as-a-Judge on 2WikiMultihopQA and MuSiQue benchmarks, and attains comparable accuracy to HippoRAG 2 on the TriviaQA and HotpotQA benchmarks with Qwen2.5 7B and multilingual-e5-large reflecting its effectiveness in reducing hallucination rates and increasing recall. We show that enabled search plan enhancement mechanism gain in average a 18 pp boost compared to disabled one by LLM-as-a-Judge across five benchmarks. In addition, an ablation study reveals that PAI-2 achieves superior result on the MINE-1 benchmark, obtaining an 89\% information-retention score with Qwen2.5 7B and multilingual-e5-large. Collectively, these findings underscore the potential of PAI-2 to serve as a reusable component for personalized AI applications, which require context-aware knowledge-representation and reasoning capabilities. The source code of PAI-2 is available at the following link: https://github.com/Dzigen/PersonalAI.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08966

Concordance-Optimal Continuous Music Emotion Estimation: Variance Decomposition, Dual-Branch Temporal Fusion, and Conformal Prediction Intervals

Mohammad Faraz Akhtar, Aditya Parashar, Ayush Jain, Madhur Gupta, Ritesh Kumar, Soubhik Chakraborty

原文摘要

Continuous music emotion recognition (MER) estimates how Arousal and Valence evolve within a song, yet the field's standard metric, pooled frame-level correlation, is dominated by between-song differences and cannot distinguish a model that tracks emotional dynamics from one that only ranks songs by their average level. We decompose annotation variance into between- and within-song components and show that mean squared error (MSE) targets the former, while windowed Lin's concordance correlation coefficient (CCC = $r \cdot C_b$) targets the latter by penalising the variance compression MSE induces. A single weight $λ$ controls the trade-off: on 1,764 DEAM songs, raising $λ$ from 0 to 1 lowers pooled Arousal $r$ from 0.843 to 0.810 while raising mean within-song $r$ from 0.204 to 0.368. Building on this objective, we present MMAS (Multimodal Music Analysis System), an open-source model that predicts Arousal and Valence every 0.5 s from raw audio. It fuses frozen MERT-v1-95M embeddings with ten symbolic features from automatic transcription through a dual-branch temporal convolutional network with cross-modal attention. Because both branches are audio-derived, one model trains jointly on DEAM and PMEmo without domain conditioning. Under song-grouped 5-fold cross-validation (2,531 songs), pooled $r$ reaches 0.801/0.685 (Arousal/Valence) on DEAM and 0.742/0.746 on PMEmo. Against a ridge baseline on identical features, within-song Arousal $r$ roughly triples (0.344 vs. 0.125; $n = 353$ songs, Wilcoxon $p = 1.7 \times 10^{-21}$, $d = 0.56$). Complete transcription failure costs at most 0.04 pooled $r$. Split-conformal intervals attain 93.7% (Arousal) and 90.0% (Valence) marginal coverage at a 95% target, with the shortfall traced to within-song dependence. MMAS is released as a pip-installable package.

cs.SD · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08963

Global Sinkhorn Convergence and Spectral Stability of Matrix Scaling

Kun He

原文摘要

We give a global spectral bound for the Sinkhorn--Knopp (SK) algorithm. Let $A$ be a row-stochastic nonnegative $n\times n$ matrix admitting a finite doubly stochastic scaling $B$. Define \[ g=1-s_2(B)^2>0, \qquad D=\min\left\{\|(u,v)\|_\infty: B=\operatorname{diag}(e^u)A\operatorname{diag}(e^{-v})\right\}. \] From the standard initialization, SK achieves total marginal $\ell_1$ error $\varepsilon$ in \[ O\!\left(\frac{D+\log n+\log(1/\varepsilon)}{g}\right) \] iterations. A scale-invariant potential contracts globally according to the spectrum of $B$. The linear dependence on $D$ is necessary in the fixed-gap regime: we construct strictly positive inputs with constant input and endpoint spectral gaps, $D=Θ(n)$, and an $Ω(n)$ iteration lower bound at error $n^{-2}$. Our upper bound gives $O(n)$ iterations on this family. We next give spectral certificates for scalability and short scaling distance. For a row-stochastic input $A$ with positive column sums $c_j$, set \[ K=\frac{\max_jc_j}{\min_jc_j},\qquad σ=s_2\!\left(A\operatorname{diag}(c)^{-1/2}\right). \] The input-only condition $\sqrt K\,σ<1$ certifies exact scalability and polynomial scaling distortion, with $D=O(\log n)$ for fixed $K$ and a fixed positive spectral margin. Given a finite scaling $B$, the weaker condition $\sqrt K\,σs_2(B)<1$ gives the same structural bounds. With a constant endpoint gap, these bounds imply logarithmic SK iteration complexity. Boundary constructions show that the strict spectral inequalities cannot uniformly be replaced by nonstrict ones.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.01365

The Greedy Superstring Conjecture Is False

Nikolai Chukhin, Rishikesh Gajjala, Juha Harviainen, Alexander S. Kulikov, Ivan Mihajlin, Hiroki Shibata, Alexander V. Smal

原文摘要

In the Shortest Common Superstring problem (SCS), one is given a finite set of strings and is asked to find a shortest string containing every input string as a substring. Since the problem is NP-hard, various approximation algorithms have been proposed for it. The currently best known approximation ratio is $2.466$ due to Englert, Matsakis, and Veselý; a better approximation ratio $2$ has been announced by OpenAI just recently. In 1988, Tarhio and Ukkonen introduced a simple greedy algorithm that iteratively takes two strings with the longest overlap and merges them together. They showed that the greedy algorithm may produce a superstring that is about two times longer than the optimal one and conjectured that this bound is tight. This has become known as the Greedy Superstring Conjecture and has remained open for almost four decades. The best known upper bound on the approximation ratio of the greedy algorithm is $3.396$ due to Englert, Matsakis, and Veselý. In this paper, we present a series of results tightening the bounds of the greedy algorithm, with the main contributions being as follows: 1. We refute the Greedy Conjecture by constructing a family of instances for which a lower bound on the approximation ratio tends to $2.4$. 2. We prove that the greedy algorithm is $3$-approximate. 3. For input strings of fixed length $k$, we prove that the approximation guarantee is exactly $9/5$ for $k=3$ and at least $2$ for all $k \ge 6$.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.01025

Fast and Accurate Probing of In-Training LLMs' Downstream Performances

Zhichen Liu, Tianle Lun, Yang Xu, Zhibin Wen, Hao An, Yulin Ou, Jianhui Xu, Hao Zhang 等 10 位作者

原文摘要

The paradigm of scaling Large Language Models (LLMs) in both parameter size and test time has pushed the boundaries of AI capabilities, but at the cost of making the traditional generative evaluation paradigm prohibitively expensive, therefore making the latency of LLM's in-training downstream performance evaluation unbearable. However, simple metrics like training loss (perplexity) are not always correlated with downstream performance, as sometimes their trends diverge from the actual task outcomes. This dilemma calls for a method that is computationally efficient and sufficiently accurate in measuring model capabilities. To address this challenge, we introduce a new in-training evaluation paradigm that uses a lightweight probe for monitoring downstream performance. The probes take the internal representations of LLM checkpoints (during training) as input and directly predict the checkpoint's performance on downstream tasks measured by success probability (i.e., pass@1). We design several probe architectures, validating their effectiveness using the OLMo3-7B's, OLMo3-32B's, and Apertus-8B's checkpoints across a diverse set of downstream tasks. The probes can accurately predict a checkpoint's performance (with avg. AUROC$>$0.75), have decent generalizability across checkpoints (earlier predicts later), and reduce the computation latency from $\sim$1 hr (using conventional generative evaluation method) to $\sim$3 min. In sum, this work presents a practical and scalable in-training downstream evaluation paradigm, enabling a more agile, informed, and efficient LLM development process.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08959

Accuracy Is Not Value: Choosing Weak Supervisors by What the Student Inherits

Romano Li, Xunfan Cai

原文摘要

Weak supervisors are usually judged by their own errors, but what matters is what a student learns from them. For squared loss and any linear learner shared by all supervisors, we show that a supervisor's value is determined by its errors after they pass through the student's learning operator. Consequently, the inner products of the supervisors' raw errors can be compatible with every feasible value of the student's risk, and weighting supervisors by them can be arbitrarily worse than the best weighting in relative excess risk. This student-relative value is not identifiable from unlabeled data, but what is missing is small: one finite-dimensional projection of the target decides whether training on a weak aggregate helps, another decides how to weight the supervisors. Known teacher training rules, or a label-model condition stated in student-relative form, shrink it further. Clean labels close the remaining gap at a cost set by the geometry of the unresolved directions rather than by the dimension of the student's representation, with matching worst-case lower bounds. In Gaussian designs we also quantify when exact teacher structure beats ordinary stacking and when weak supervisors, combined with clean labels, beat every procedure that uses the clean labels alone. The guarantees extend to fitted ridge students and finite unlabeled data.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.27239

Analytical Correction for Subsampling Bias in Drifting Models

Jiaru Zhang, Zeyun Deng, Juanwu Lu, Ziran Wang, Ruqi Zhang

原文摘要

Drifting models are capable one-step generative models trained to follow a drifting field. The field combines attractive and repulsive softmax-weighted centroids over the data and current-generator distributions. In practice, only a minibatch of $n$ samples from each distribution is available, and each centroid is approximated by an empirical estimate. In this paper, we begin by showing that the minibatch centroid is in general a biased estimator of the target centroid, with a pointwise $O(1/n)$ bias arising from softmax self-normalization. Correcting this bias requires the expectation over the full distribution, which is intractable. We instead approximate the leading bias term from in-batch statistics and propose Analytical Bias Correction (ABC), a closed-form plug-in adjustment. We prove that ABC reduces the bias from $O(1/n)$ to $O(1/n^2)$, introduces no first-order increase in total variance, and preserves convex-hull containment of the corrected centroid. In practice, ABC requires only two additional lines of code and has negligible wall-time overhead under compiled execution. Toy experiments confirm the theoretical $O(1/n)$ and $O(1/n^2)$ scaling. On CIFAR-10, ABC reduces FID and trains faster, with the largest gains at small $n$, where the bias is most significant.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2611.05942

Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning

Mengni Jia, Mengyu Zhou, Xiaoxi Jiang, Guanjun Jiang

原文摘要

RL for LLM reasoning often plateaus early as its policy sharpens. Policy entropy is studied as both a diagnostic and a control signal, but increasing it alone does not reliably change the eventual plateau in our experiments. We analyze RL's implicit target policy using a sharpness factor $κ$ and effective counterpart $κ_{\mathrm{eff}}$ that describe how reward or advantage gaps translate into probability-ratio gaps. We introduce reward budgeting, a plug-in advantage construction assigning a fixed total reward budget to each prompt. For binary rewards and independent on-policy rollouts, its expected unclipped score-function update is the exact gradient of a finite-$G$ concave objective with diminishing returns; its advantage gap decreases as more rollouts become correct. For general rewards, a shifted log-mean interpretation holds asymptotically under the stated regularity conditions. On Qwen3-8B and Llama3.2-3B-Instruct, reward budgeting consistently improves RL baselines, with gains up to +12.50 on AMC23 and +10.00 on AIME24 and AIME25. These results support an update-dynamics view of premature convergence and substantial gains without explicitly preserving entropy. Code is available at https://github.com/Qwen-Applications/RewardBudget.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06922

Towards Comprehensive Mobile Application Testing for User-centric Feature Coverage via Simulating Real-World Users with Personas

Ha Min Son, Huan Ren, Huan Song, Zhe Zhao, Xin Liu

原文摘要

LLM agents are increasingly used for black-box mobile application testing, where the ultimate goal is the comprehensive coverage of the features users rely on. However, most existing studies focus on Activity Coverage, which measures the proportion of distinct application screens visited during a test session but does not directly measure whether agents actually test the features users care about. To address this, we focus on (1) how to automatically measure whether a testing framework covers the features users care about, and (2) how to design a framework that achieves more comprehensive feature coverage. To answer (1), we introduce the User-Centric Feature Coverage benchmark, which consists of two components: a manually crafted dataset of 3,012 user-centric target features based on real reviews and app descriptions, and an automated evaluation pipeline that translates agent-generated test cases and target features into a shared semantic space, then uses an LLM-as-a-judge to compute coverage. To answer (2), we introduce ECS (Exploration, Critical User Journeys, and Synthetic Reviews). ECS is a framework that explores the application, then uses an LLM to convert exploration traces into Critical User Journeys (CUJs) to bring the semantic meaning of the trace closer to a distinct feature. Each CUJ consists of an LLM-inferred user intent paired with reproducible test steps. ECS then aggregates multiple CUJs using persona-augmented synthetic reviews to capture more complex features, simulating real users who build knowledge of an application across multiple screens before writing a review. ECS achieves 64.1% feature coverage, a 23.8% gain over the state-of-the-art baseline, and covers 72.5% of features in app descriptions, capturing the most prominent features. Our failure analysis shows statelessness and exploration discoverability as main reasons of failures, providing future directions.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30844

Fine-Tuned Language Models Exhibit Improved Information Conveyance

Yuwei Cheng, Weiyi Tian, Haifeng Xu

原文摘要

Fine-tuning is often believed to reduce uncertainty and diversity in large language models, but existing analyses overlook output length, a key confounder, and therefore fail to capture how uncertainty is distributed across an entire generation rollout. To address this, we propose Canopy Entropy ($\mathrm{CE}^\star$), a measure that views language generation from a tree perspective, where "canopy" represents the space of all possible rollouts, making $\mathrm{CE}^\star$ naturally quantify the effective size of the generation space. $\mathrm{CE}^\star$ jointly captures uncertainty in both the output length $N$ and the generated sequence $Y_{1:N}$ -- indeed, we show that it equals total Shannon entropy $H(N, Y_{1:N}\mid X)$, where $X$ denotes the prompt. This formulation yields interpretable metrics, including a length-entropy correlation term $ρ(N, r_N)$, where $r_N$ is the entropy rate, quantifying information conveyance efficiency by indicating whether longer outputs are more or less informative per token. Empirically, across tasks and model families, we find that fine-tuned models predominantly exhibit more positive correlation $ρ(N, r_N)$, even when total entropy decreases. Furthermore, after controlling for model family, task, prompt, and output-length effects, we find that fine-tuning nearly triples the correlation strength between entropy rate and semantic diversity, suggesting that aligned models convert token uncertainty into semantic diversity more efficiently. Overall, these results demonstrate that fine-tuning does not simply reduce uncertainty, but fundamentally reorganizes it into more informative and semantically meaningful generations. Our code is available at https://github.com/WeiyiTian/canopy-entropy.

cs.CL · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.06522

Anatomy of LLM Sycophancy: What a Flip Rate Hides

Haonan Huang, Tianlin Zhang

原文摘要

A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. SycoLens, a modular replay protocol, measures flip rates from replays of an item, a committed answer, and one scripted user line, each against a matched control with the line deleted. Pushback wording, committed text, answer format, boundary distance, and ground truth become factors of one instrument, where earlier instruments vary one to three, so the interactions between the factors become measurable. Across eleven frontier models and about 760,000 controlled replays, lines that assert the opposite verdict and lines that challenge without asserting one rank the models almost unrelatedly. Flip effects grow several-fold near a model's boundary, yet items the model is certain of still carry about half of the most-affected totals; planted prose anchors a commitment at rest more than it protects it. Under a yes/no readout the rankings come closer, entangled with a pressure-induced shift toward "no". Where a truth exists, one model re-derives and corrects itself while another abandons correct answers without written work. One score per model therefore compares different behaviours; we condense them into a reporting profile, and the records and analyses will be released upon publication.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08949

Age of Information for Power-Saving Devices with DRX Mechanism

Hung-Chun Lin, Kuang-Hsun Lin, Hung-Yu Wei

原文摘要

Reducing the power consumption of User Equipment (UE) has always been a crucial issue in communication systems. As a result, Discontinuous reception (DRX) is introduced in today's New Radio (NR) networks as a power-saving strategy. In addition, the variety of low latency applications in 6G makes the issue of maintaining data freshness increasingly important. This paper aims to study the relationship between freshness and power-saving. To capture the information freshness, we use Age of Information (AoI) as the performance metric. To our best knowledge, unlike previous studies focusing on power saving and delay trade-offs, this is the first study considering the impact of DRX on AoI. We solve the closed-form solution of the peak average AoI with the DRX mechanism. Moreover, we propose a parameters adjustment strategy. Based on the simulation validation, our proposed strategy can enable the UE to keep the AoI close to the theoretical lower bound AoI while achieving high power-saving efficiency.

cs.NI · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08947

More with Less: Efficient Parallel Scientific Code Translation via an Agent-Skill Workflow

Jianuo Shen, Pengyi Xu, Bo Zhang

原文摘要

Translating parallel scientific codes between HPC programming frameworks is a critical but labor-intensive task. Existing LLM-based approaches rely on fixed sequential pipelines with undifferentiated repair strategies and correctness criteria that do not match scientific computing practice. We present an agent-skill framework that separates translation, compilation diagnosis, and execution validation into three autonomous agents coordinated by a verdict-driven orchestrator, routing each failure to a targeted repair skill rather than retrying blindly. An automated output check drives the self-correction loop, complemented by an offline LLM-based verification that exposes false positives escaping compiler and runtime checks. We evaluate the framework on 30 HeCBench kernels translated bidirectionally among CUDA, OpenMP, and SYCL with three open-source LLMs. Our framework attains the higher verified correctness rate in all 18 model and direction combinations over a state-of-the-art baseline while consuming up to 52.4% fewer tokens, remaining consistent across models and directions without architectural modification.

cs.DC · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.15660

Sparse All-Layer Connector for Domain Generalised Semantic Segmentation

Ruoyu Guo, Xin Kun Lin, Maurice Pagnucco, Yang Song

原文摘要

Domain generalised semantic segmentation (DGSS) has recently benefited from combining multiple foundation models, such as vision-language and vision foundation models, to leverage their diverse representations for generalisation. Existing multi-model approaches share a common design choice: cross-model fusion is restricted to depth-aligned layers, implicitly assuming that mutually beneficial information resides at the same depth across models. However, foundation models pretrained under different objectives may develop distinct representation hierarchies, making the optimality of depth-aligned fusion questionable. Moreover, we observe that the foundation models exhibit different depth-wise domain sensitivity. Motivated by these observations, we propose a Sparse All-Layer Connector (SALC) that enables each layer to access information from preceding layers of another model. As the number of accessible layers grows with depth, dense aggregation may hurt generalisation. SALC therefore learns to adaptively select a sparse subset of informative layers. We further introduce a candidate dropout regularisation that strengthens sparsity and encourages SALC to explore diverse layers, leading to more robust selection. Across four foundation model combinations and three DGSS evaluation settings, the proposed design demonstrates stronger generalisation than conventional depth-aligned fusion. The code is available at https://github.com/RuoyuGuo/SALC.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.05552

Decomposing Yes-No Bias in LLM Moral Judgment: Stance, Position, Word, and Verdict

Haonan Huang

原文摘要

Large language models (LLMs) increasingly issue binary verdicts - safety gates, judge decisions, value probes - and the answer is read as the model's judgment. A settled judgment should be coherent across paired phrasings of the same question: yes to "do you approve?" should mirror no to "do you oppose?". LLMs often violate this coherence, and in a yes/no question the verdict, the answer word, and the printed position coincide, so a conventional flipped-question audit yields one contrast that cannot say what moved. We introduce a crossed psychometric battery that extends the flip to full 2x2 and 2x2x2 crossings of question polarity, printed order, and answer label, separating stance from position, word, label, and verdict-role effects; an independent graded instrument estimates each model's stance $θ$ with no binary format; and a two-parameter fit (framing susceptibility $m$, decisiveness $s$) separates robustness from saturation that hides susceptibility. Applying the battery to twenty moral dilemmas - 1.35 million trials over ten frontier models from the Claude, GPT, and Gemini families in 23 reasoning configurations - we find response-form bias widespread but never uniform. The largest apparent yes-no biases are almost purely surface (word and position), while several of the newest models show the reverse: near-zero flip contrasts concealing verdict attachment up to +0.42, a component no surface counterbalance can expose, replicated across label alphabets. Requested reasoning reshapes these channels rather than removing them. When subjects state decisions in free text and a separate model transcribes them, two judge families agree on 99.3% of jointly scored transcriptions with zero opposing committed labels, and the transcribed stance converges with the graded ruler (median $r=0.87$): response form is part of the instrument, and the judgment can be measured apart from it.

cs.CL · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08946

Flex-RSI: Benchmarking Recursive Self-Improvement of Frontier Agents

Jingdong Zhang, Jionghao Wang, Zhengming Yu, Yancheng Cai, Wei Chow, Chris Choy, Zhiyang Dou, Hang Hua 等 22 位作者

原文摘要

Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only on its model but also on its harness: the prompts, tools, memory, and control loop through which the model acts. When an agent is applied to a new problem, a natural question is whether it can use the feedback of the task to improve the way it works, and not merely its answer. Most existing benchmarks keep the agent's harness fixed and score the solution it produces, or target large-scale model training. We introduce Flex-RSI, a benchmark for the recursive self-improvement of agents on vision and robotics tasks under a fixed budget. In each round, an executor improves the task solution, which is kept only if it scores higher on held-out validation data, and an improver then revises the harness, including the executor and itself. Every run starts from the same general-purpose harness, and the final solution is scored on hidden test data. Evaluating closed-source and open-weight models on tasks spanning perception, reasoning, robot action, 3D reconstruction, visual creation, and infrastructure, we find that self-improvement helps most when the agent builds its own solution, that feedback recording only success or failure holds back open-weight models, and that open-weight models fall furthest behind where outputs must pass strict checks of physical stability or exact correctness. Paired runs further show that editing the harness itself contributes to the gains.

cs.AI · cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08945

The Schur products of some nonbinary narrow-sense antiprimitive BCH codes

Haojie Xu, Xia Wu, Wei Lu, Xiwang Cao

原文摘要

In recent years, the Schur products of linear codes have been extensively studied due to their favorable applications in cryptography. In this paper, we aim to study the parameters of the Schur products of some nonbinary narrow-sense antiprimitive BCH codes. Let $\mathcal{C}_1$ and $\mathcal{C}_2$ be two narrow-sense antiprimitive BCH codes with designed distances $δ_{1}$ and $δ_{2}$, respectively, where $2\le δ_{1},δ_{2}\le n$. Let $\mathcal{C}_1\star\mathcal{C}_2$ be the Schur product of $\mathcal{C}_1$ and $\mathcal{C}_2$. We present some necessary and sufficient conditions for $\mathcal{C}_1\star\mathcal{C}_2\ne\mathbb{F}_q^n$ by applying some constraints to $δ_{1}$ and $δ_{2}$. Furthermore, we determine the dimensions of these products and lower bounds on their minimum distance. Several linear codes with best known parameters are found.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2412.12737

PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model

Yuqing Wang, Zhongling Huang, Shuxin Yang, Hao Tang, Xiaolan Qiu, Junwei Han, Dingwen Zhang

原文摘要

PolSAR data presents unique challenges due to its rich and complex characteristics. Existing data representations, such as complex-valued data, polarimetric features, and amplitude images, are widely used. However, these formats often face issues related to usability, interpretability, and data integrity. Most feature extraction networks for PolSAR are small, limiting their ability to capture features effectively. To address these issues, We propose the Polarimetric Scattering Mechanism-Informed SAM (PolSAM), an enhanced Segment Anything Model (SAM) that integrates domain-specific scattering characteristics and a novel prompt generation strategy. PolSAM introduces Microwave Vision Data (MVD), a lightweight and interpretable data representation derived from polarimetric decomposition and semantic correlations. We propose two key components: the Feature-Level Fusion Prompt (FFP), which fuses visual tokens from pseudo-colored SAR images and MVD to address modality incompatibility in the frozen SAM encoder, and the Semantic-Level Fusion Prompt (SFP), which refines sparse and dense segmentation prompts using semantic information. Experimental results on the PhySAR-Seg datasets demonstrate that PolSAM significantly outperforms existing SAM-based and multimodal fusion models, improving segmentation accuracy, reducing data storage, and accelerating inference time. The source code and datasets will be made publicly available at https://github.com/XAI4SAR/PolSAM.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.39701

DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence

Kiljoon Han, Kyumin Hwang, Wonhyeok Choi, Jeonghoon Kim, Sunghoom Im

原文摘要

Iterative refinement models have significantly improved stereo matching accuracy, but their rigid, fixed update schedules incur heavy computational costs and a strict trade-off between speed and accuracy. This challenge is magnified in video streams, where traditional online methods resort to reducing feature channels or relying on expensive temporal warping. To address this, we propose DEQ-Stereo, a novel video stereo matching framework based on the Deep Equilibrium (DEQ) paradigm. Instead of unrolling a fixed number of iterations, DEQ-Stereo reformulates the refinement as an implicit fixed-point problem, adaptively terminating once convergence is met. To ensure fast and stable intra-frame convergence, we introduce the Convolutional Simplified Gated Unit (ConvSGU), which eliminates unnecessary non-linearities by modeling the latent state as a gated, element-wise sum of inputs. Furthermore, to exploit cross-frame temporal coherence, we propose Temporal State Transfer (TST), a warm-start strategy that propagates the converged hidden state to the next frame without requiring explicit pose or warping priors. Extensive evaluations demonstrate that DEQ-Stereo delivers state-of-the-art performance with a superior accuracy-to-latency trade-off.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08943

MESAM: Enhancing SAM2 for Few-Shot Segmentation through Semantic-Visual Memory Generation and Refinement

Tianyu Zou, Shengwu Xiong, Rui Wu, Ruilin Yao, Yi Rong

原文摘要

This paper investigates how to leverage the powerful capabilities of the Segment Anything Model 2 (SAM2) to tackle few-shot segmentation (FSS) tasks. One major challenge lies in the substantial appearance differences between the support and query images, which may diminish the effectiveness of the memory-matching process in SAM2. Through systematic analysis, we find that the memory generated based on the categorical semantic information is robust to this appearance divergence and is more compatible with SAM2. Based on these observations, we propose a new Memory-Enhanced SAM2 (MESAM) method, which first introduces a Semantic-Visual Memory Generation (SVMG) module to separately construct a query semantic memory, a query foreground visual memory, and a support adaptive visual memory. Then, in our designed Interactive Semantic Memory Refinement (ISMR) module, we further enrich the obtained semantic memory with fine-grained visual details, and suppress its misatcivated background responses. Extensive experiments on the PASCAL-$5^i$, COCO-$20^i$, and LVIS-$92^i$ datasets demonstrate that MESAM consistently outperforms existing FSS methods, achieving new state-of-the-art segmentation performance. Our source code is available at: \href{https://github.com/tianyu-zou/MESAM}{https://github.com/tianyu-zou/MESAM}.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08936

Ordered Policy Optimization

Dongkyu Derek Cho, Pan Xu

原文摘要

Proximal Policy Optimization (PPO) stabilizes policy updates by clipping the importance ratio between the new policy and the data-collecting policy. The standard rule uses one fixed clipping range for all samples. While this choice offers simplicity and effectiveness, it fails to distinguish statistically harmful extreme ratio values from large, yet tolerable changes. We study how to adapt the clipping radius to the reliability of the induced importance ratio distribution. Our case study demonstrates that reliable updates require controlling these extreme ratios, rather than merely verifying that individual ratios fall within a fixed interval. Motivated by this observation, we propose Ordered Policy Optimization (\textsc{OPO}). In each minibatch, \textsc{OPO} sorts the importance ratios, selects the extreme ratios that potentially have the largest effect on the update, and assigns them adaptive sample-wise radii instead of using the fixed clipping radius. These radii are derived from a prescribed tail profile, which specifies desired target values for the selected extreme ratios. The resulting objective remains first-order and requires only minibatch sorting and a modified policy loss. Experiments conducted on MuJoCo and Atari benchmarks demonstrate that this simple modification achieves strong performance relative to established baselines.

cs.LG · cs.AI · cs.RO · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08935

SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing for Reliable Dermatology AI

Jing Hao, Weinan Zhou, Zhihong Lu, Yaling Shen, Yiming Xu, Yefeng Liu, Siyuan Yan, Shuaibo Li 等 14 位作者

原文摘要

Reliable dermatology AI requires access to verifiable evidence distributed across heterogeneous textual and visual sources. However, conventional retrieval-augmented generation (RAG) typically relies on one-shot retrieval from flat corpora, limiting its ability to adapt retrieval granularity, explore multi-hop relations, and integrate multimodal clinical evidence. We introduce SkinMind, a multimodal agentic RAG framework that equips policy models with human-inspired graph probing for autonomous evidence seeking. SkinMind organizes retrieval as an iterative interaction between an orchestrator and a graph environment. Through eight hierarchical graph-probing tools, the orchestrator progressively identifies relevant entities, inspects node-level information, traverses relations and paths, and retrieves source-text and visual evidence. This progressive-disclosure design allows the model to adaptively determine the retrieval modality, exploration direction, and evidence granularity while constructing a query-specific evidence subgraph. To support autonomous graph probing, we construct SkinMind-KG from a 62M-token corpus of dermatology guidelines and textbooks and 423K images, guided by a dermatologist-informed schema and a conflict-resolution mechanism. The resulting graph contains over 1.0M nodes and 2.0M edges, unifying textual, relational, and visual evidence for retrieval. Across six dermatology VQA benchmarks and two policy-model settings, SkinMind improves the average score over direct answering by 8.70 and 8.89 points with GPT-5.4-mini and Gemini-2.5-Flash, respectively, while consistently outperforming competing RAG methods. Together, SkinMind and SkinMind-KG provide an effective foundation for evidence-grounded multimodal reasoning in dermatology.

cs.IR

查看论文
arXiv ↗PDF ↗