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
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 07:12 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 07:22 — 2026-11-09 07:22（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：2026-11-09 07:12最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 3,292 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 07:10（北京时间）
新论文 · v1arXiv:2610.39305

Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference

Akshay Vyas, Hailiang Dong, Shivvrat Arya, Brij Malhotra, Tahrima Rahman, Vibhav Gogate, Nicholas Ruozzi

原文摘要

Probabilistic graphical models (PGMs) compactly encode structured joint distributions, but Most Probable Explanation (MPE), which finds the highest-probability assignment to unobserved variables, remains computationally intractable in large, densely structured models. Anytime systematic search, such as branch-and-bound (B&B), is a popular approach, but its efficiency depends on tight admissible upper bounds that are often prohibitively expensive to compute using classical methods like Mini-Bucket Elimination (MBE). We introduce Learning to Bound (L2B), a data-driven framework that amortizes bound computation cost by training a neural predictor. L2B targets two key properties required for effective search bounds: admissibility, which is achieved via statistical calibration techniques, and progressive tightening as evidence accumulates, which is enforced through structural architectural constraints that ensure monotonicity by construction. Across challenging benchmarks, L2B delivers tighter, monotonic bounds at orders-of-magnitude lower cost on every PGM family, and yields measurable improvements when integrated with branch-and-bound on high-treewidth instances.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39302HF 社区推荐

Proving and Improving the Platonic Representation Hypothesis with JEPAs

Randall Balestriero, Yann LeCun

原文摘要

Whether models trained on different modalities converge to the same representation of the world is central to AI. The Platonic Representation Hypothesis (PRH) conjectures that they do as they scale, but without a proof it offers neither a guarantee nor a recipe. We turn the hypothesis into a theorem. First, we prove a \emph{Platonic Representation Theorem}: Joint-Embedding Predictive Architectures (JEPAs) trained separately on any number of modalities learn the same representation up to one rotation whenever their positive pairs are two observations of one scene--\emph{good views}--and their misalignment is bounded otherwise. Second, we show that next-token prediction is a JEPA with \emph{bad views}, parts of a single document, which explains why language models align with vision only through scale. Third, we validate the theory from 145k captions to the texts of 940M web images, and uncover a scaling law of alignment that predicts unseen runs within seed noise. Good views need 42 times fewer training samples than next-token prediction on the same corpus to reach the same alignment, and a 109M-parameter text JEPA aligns with DINOv2 and CLIP's image encoders better than every language model we evaluated, up to 72B parameters, and than CLIP's text encoder: next-token prediction is a remarkably inefficient route to platonic representations. As a showcase, one rotation turns separately trained encoders into an image captioner (CIDEr .838 on COCO). Even that rotation needs no pair: on the latest pair-free benchmark, our text JEPA beats every zero-shot accuracy reported with language models up to 8B parameters, e.g., 64\% against at most 56\% top-5 on ImageNet-100. Positive views, and not scale alone, are thus the lever to build platonic representations.

cs.AI · cs.CV · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.29532

GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing

Xiaoyi Chen, Yifei Gao, Yang Xu, Zhenlong Wang, Jian Yan, Jiming An, Xingxing Song, Liqun Deng 等 12 位作者

原文摘要

Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an application and discover defects through its own interaction. However, current evaluation falls short on two fronts. First, existing benchmarks focus almost exclusively on interaction defects, leaving display defects outside the evaluation frame. Second, evaluation protocols are bound to predefined defect annotations, collapsing the testing process into a single end-state judgment that conflates qualitatively distinct failure modes. To address these challenges, we present GUITestScape, an interactive benchmark covering 61 real-world Android applications and 508 preset defects spanning interaction and display types, and introduce GUIJudge, an open-set evaluator that decomposes an agent's testing trajectory into independently diagnosable capabilities. Experimental results demonstrate that GUIJudge achieves reliable process-aware evaluation beyond predefined annotations, substantially outperforming all baselines. Benchmarking on GUITestScape further reveals that detection remains the critical bottleneck for existing models across both defect types, and that integrating GUIJudge's verifiers into existing agents significantly boosts their detection performance without retraining.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39295

There Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price

Yinuo Liu

原文摘要

Reinforcement learning with verifiable rewards (RLVR) makes a language model solve more problems on the first try and fewer when given many tries: it raises pass@1 while the base model overtakes it at large sampling budget k. Is this a failure of RL to add reasoning, or a transient that more training removes? We settle the question with a theorem. The reversal is a price, and we compute its exact rate. Modeling RLVR as an exponential tilt of a base policy over strategies shared across prompts, we prove that under exclusive specialization every update that raises pass@1 strictly lowers the success of some prompt; a strictly positive price on prompts (Stiemke duality) is the exact condition, and being merely the best strategy on a prompt is provably not enough. When the loss reaches the hardest prompts, it forces a pass@k crossover, and the number of crossings is at most the sign variation of the shift in per-prompt success, a totally positive bound that is tight and that recovers the known single-crossover result as its order-preserving case. The crossover is not a bug to patch: a constrained update traces the exact pass@1 versus pass@k frontier, and removing the crossover entirely costs the entire pass@1 gain. The same tilt identity yields entropy collapse and the entropy-performance law with an identifiable exponent, unifying two literatures under one mechanism. Reinforcement cannot widen the reasoning frontier; it can only move along it, at a price we make measurable by a diagnostic that reads the bound, the order-preserving test, and the price from any evaluation log. There is no free lunch, only a price.

cs.LG · cs.AI · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39282

What Does "Now" Mean to Your Computer-Use Agent? Stale Screenshots, Page Loads, and Which Check to Run Before a Click

Vasundra Srinivasan

原文摘要

Computer-use agents plan on a screenshot for several seconds and then click at a position on the screen; if the page has changed in the meantime, the click lands on an unintended element. Prior work treats the planning interval as the source of this risk. Measuring planned clicks on 31 public web pages, we find that the risk lies in page loading: 0.4% of clicks planned on fully loaded pages became stale within 30 seconds, against 17% of clicks planned in the first second after a page opened. On these pages, waiting about one second for network activity to stop removes most of this risk, yet the wait rules of eight of ten widely used open-source agents leave more than 1% of clicks stale. Commercial pages keep loading for longer: in the HTTP Archive's public crawl, 15% of 65 desktop booking and buying home pages went 500 ms without network requests within 3 seconds of their HTML being parsed, against 63% of 3,028 .gov pages, and 52% shifted their layout within 6.5 seconds of a network-idle wait capped at 3 seconds, against 8% (61% against 26% among pages recorded in full). Where a check before the click is needed, as before irreversible actions and on pages that are still loading, a pixel comparison verifies the target's position as accurately as a frontier vision-language model at one eighth of the latency, and a 4B model matches the frontier model in verifying whether the previous action succeeded. We release a benchmark generator, a break-even formula for when a check pays, and three rules for agent developers: https://github.com/multimodal-ai-engineering/preflight-bench

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.22488

Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints

Nelly Elsayed

原文摘要

Distributed denial of service (DDoS) attacks threaten the availability of Internet of Things (IoT) infrastructures, particularly under resource-constrained deployment conditions. Although transfer learning models have shown promising detection accuracy, their reliability, computational feasibility, and interpretability in operational environments remain insufficiently explored. This study presents an explainability aware empirical evaluation of seven pre-trained convolutional neural network architectures for multi-class IoT DDoS detection using the CICDDoS2019 dataset and an image-based traffic representation. The analysis integrates performance metrics, reliability-oriented statistics (MCC, Youden Index, confidence intervals), latency and training cost assessment, and interpretability evaluation using Grad-CAM and SHAP. Results indicate that DenseNet and MobileNet based architectures achieve strong detection performance while demonstrating superior reliability and compact, class-consistent attribution patterns. DenseNet169 offers the strongest reliability and interpretability alignment, whereas MobileNetV3 provides an effective latency-accuracy trade-off for fog-level deployment. The findings emphasize the importance of combining performance, reliability, and explainability criteria when selecting deep learning models for IoT DDoS detection.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39278

WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining

Yuhao Lu, Jiongxu Chen, Hexiang Wei, Jiajin Wu, Juelin Li, Mingjian Liang, Fan Yang, Zhuowei Liang 等 12 位作者

原文摘要

Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulations remain tied to specific robot configurations, and 3D motion prediction models use flow-only supervision, providing a limited learning signal for physical dynamics. To circumvent these limitations, we introduce \method{}, a generative world model that jointly predicts future video and query-based 3D trajectories. By parameterizing 3D motion as continuous displacement tokens aligned with the video grid, a unified Mixture-of-Transformers (MoT) backbone jointly denoises both modalities under a rectified-flow objective. This formulation couples explicit geometric dynamics with visual evolution, effectively unlocking the physical commonsense embedded within pretrained video models. To empirically scale and validate this unified architecture, we train \method{} on a heterogeneous mixture of 1.44 million object-level samples spanning simulated and real-world domains. We further introduce WorldFlowBench, comprising 1,678 evaluation samples from 11 data sources across simulated and real-world interactions, including spatial reasoning tasks. Across all three evaluation sets, WorldFlow achieves the lowest average displacement error (ADE) and final displacement error (FDE) among the evaluated learning-based methods. Notably, on the challenging SpatialCog set, WorldFlow achieves an ADE of 0.060 m, a 54.2\% reduction compared with the strongest external baseline. It also reduces ADE and FDE by 55.9\% and 68.5\%, respectively, compared with its flow-only variant. Project page: https://worldflow-rbs.github.io/.

cs.CV · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39276

MemSteer: Turning User Histories into Supervision for Agent Memory Optimization

Jie Huang, Cuiling Lan, Qize Yu, Xiulian Peng, Yan Lu

原文摘要

An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for evaluating and improving memory designs. Yet suitable labels are rarely available for new user histories, and manually constructing QA pairs and supporting evidence is costly. We introduce MemSteer, which turns unlabeled user histories into question-answer (QA) supervision with supporting evidence for memory-design optimization. MemSteer constructs an evidence-grounded answer plan that specifies how facts across related records jointly support a reference answer. The plan guides question generation, while source-grounded auditing and blind answer recovery check the resulting annotations. To study the utility of this supervision, we develop MemSteer-Opt, which combines QA-based design evaluation with evidence-guided failure diagnosis to revise memory store, retrieval, and context construction without updating model parameters. Experiments on ATM-Bench and RHELM show that this supervision is competitive with official-QA-guided optimization. Relative to Base-BM25, MemSteer-Opt improves ATM-Bench Question Score by 13.4 points and RHELM accuracy by 4.1 and 6.6 points without and with external data, respectively. The supervision also benefits two existing optimizers on ATM-Bench, while new-user experiments demonstrate continued design optimization using supervision generated from the target histories.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39275

LLM-Assisted Optimization for Simulation-Based Redesign

Chan-Eui Song, Jeremy J. Michalek, Christopher McComb

原文摘要

Engineering design frequently involves redesigning a prior solution to adapt to changes in context, such as material prices or system requirements. Redesign often leverages simulators too complex and/or computationally intensive for traditional numerical solvers, which lack engineering knowledge and context, to ensure global solution quality. Large language models (LLMs) can interpret semantic information, including engineering knowledge about the system and changes in context, to help guide search, and recent studies have shown that incorporating this knowledge into optimization can improve search performance. However, how best to combine LLMs with numerical solvers in redesign remains unclear. We develop and test an integrated LLM-optimization approach for redesign and compare three methods for leveraging LLMs (warm start, variable fixing and ReAct) and four black-box solvers (Bayesian optimization, genetic algorithms, mesh adaptive direct search and random search) on an electric vehicle battery pack cost minimization case study across four types of redesign scenarios. We find that the integrated approach can match feasible design discovery of the numerical-solver baselines with 80% fewer simulator evaluations while tripling the fraction of runs that find near-optimal solutions. We find that the best LLM-solver integration approach and the way the prior solution is leveraged depend on the structure of the design requirement change, and that the benefit of increasing LLM model size grows with the extent to which the LLM controls the search. These results show clear potential for LLMs in redesign tasks for guiding or replacing numerical solvers.

cs.AI · cs.CE · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39265

DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition

Zhiqiang Wu, Shuang Sun, Jiale Zhang, Jing Li, Yibo Chen, Xu Tang, Yao Hu

原文摘要

Multi-image composition (MICo) is a critical yet challenging capability for large-scale image editing models, where consistency degrades rapidly as the number of reference images increases. While supervised fine-tuning (SFT) can equip models with basic MICo ability, it provides only implicit supervision on the composed image and often fails to learn reliable object-level correspondence across multiple references. We propose DeCoRL, a reinforcement-learning (RL) framework that improves MICo consistency by decomposing holistic MICo consistency into object-level consistency. DeCoRL first establishes instruction-relevant object correspondences across reference images and localizes the corresponding regions in the generated image. It then uses a VLM-based reward model trained on single-object consistency annotations to produce fine-grained, object-wise feedback, which is aggregated into a multi-object consistency reward to guide RL post-training. We further introduce DeCo-Bench, a benchmark covering compositions from 2 to 6 reference images. Experiments on DeCo-Bench and the public MICo-Bench demonstrate consistent improvements in MICo consistency.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39264HF 社区推荐

Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps

Peitong Duan, Khashayar Gatmiry, Jeffrey Nichols, Samy Bengio, Emmanuel Abbe

原文摘要

While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via supervised fine-tuning (SFT) or offline reinforcement learning often memorize static trajectories, leading to brittle execution and an inability to recover from errors. To address these limitations, we propose a novel online reinforcement learning framework that trains UI navigation agents directly on live iOS applications. Our framework decouples the agent into two specialized components: a Planning agent and a UI Grounding model. We rely on an LLM-as-a-Judge to provide comprehensive reward signals, combining dense, step-level feedback to evaluate intermediate progress with a terminal reward for overall task completion. To effectively leverage this dual reward structure, we optimize the agent using Proximal Policy Optimization (PPO) with step-level advantage estimation. Furthermore, we introduce GiGPPO, a novel neighbor-conditioned value estimation method that improves critic stability by leveraging reward signals from visually similar states across concurrent trajectories. To support this online training paradigm at scale, we introduce an efficient infrastructure that orchestrates hundreds of concurrent virtual iOS devices. Evaluations on rigorous benchmarks, including UINavBench, iOSWorld, and AndroidWorld, demonstrate that our online RL trained agents substantially outperform both SFT and terminal-only RL baselines while accelerating training convergence. Notably, our 8B RL agents achieve nearly a sevenfold improvement over the SFT baseline in out-of-distribution generalization to Android environments, while outperforming Gemini-3.5-Flash and tying with Gemini-3.1-Pro on real iOS applications.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.17474

Iterative Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback

Haichen Hu, Yuheng Zhang, David Simchi-Levi

原文摘要

Large language model (LLM) distillation can propagate teacher bias under covariate shift when target reward feedback is unavailable. We propose Iterative Calibration and Learning (IterCaL), which alternates source-reward teacher calibration through token-level branching with student learning on target prompts. We prove polynomial convergence in expected average KL to the oracle student, the reference-regularized target-reward maximizer within a potentially misspecified student class; a quantified source-to-target calibration discrepancy gives an explicit additive true-return term. Our separation shows that regularized direct teacher matching retains positive oracle-KL error at its population optimum for every shared reference penalty, even when the teacher is stronger than every student. On the same instance, IterCaL converges to the oracle using source rewards alone.

cs.LG · cs.AI · math.ST · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39251

Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents

Yuxiang Chai, Quyu Kong, Panrong Tong, Steven Hoi, Yue Wang

原文摘要

Trajectory-level GRPO is a common approach for training multi-step GUI agents, but repeatedly rolling out complete trajectories from the task root can be inefficient: task-level rewards provide coarse supervision over which intermediate decisions require improvement, while already-mastered prefixes are repeatedly re-executed before reaching difficult states. We introduce a two-stage adaptive training framework that jointly addresses where to learn and how far to roll out. We first construct reusable intermediate checkpoints from successful expert trajectories and select informative pivots using action disagreement, which measures uncertainty directly from sampled GUI actions. Stage I performs one-step RL at these pivots to improve uncertain local decisions. Stage II then progressively expands policy responsibility through adaptive Local, Suffix, and Root training according to task progress. Recoverable checkpoints enable repeated training from intermediate states without replaying the preceding trajectory. Across MobileGym and CUA-Gym-Hub, our method reduces environment interaction by 56-61% relative to Vanilla GRPO while improving task performance, demonstrating that jointly allocating training across states and rollout ranges can substantially improve GUI-agent RL efficiency.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39247

SocialArena: Evaluating Social Intelligence in Large Language Models

Zongqi Wang, Rui Wang, Yuchuan Wu, Hua Yang, Bingxue Qiu, Tianle Gu, Bing Zhao, Yujiu Yang 等 10 位作者

原文摘要

We introduce SocialArena, a benchmark for systematically defining and evaluating the social intelligence of large language models (LLMs). Although LLMs are increasingly deployed in socially interactive applications such as mental health counseling, companionship chatbots, and educational tutoring, existing evaluations remain fragmented focusing on isolated capabilities or single scenarios and evaluation reliability is largely unverified. This work makes three main contributions to address these limitations. (1) We first propose a unified three-tier framework that defines social intelligence along three capability dimensions: role-playing ability, mental state reasoning, and behavioral reasoning. To operationalize this definition, we design a role-playing dialogue paradigm with explicit character thinking for evaluation, enabling simultaneous assessment of these capabilities in a manner that mirrors realistic human interactions. (2) To ensure diversity across social scenarios and thereby prevent evaluation conclusions from being confined to specific scenarios, we introduce the U-TRIMF framework, which guides us in synthesizing social contexts with broad coverage. (3) To obtain reliable evaluation, we invest $132.4K to recruit and train human annotators and adopt a human-annotated arena-style protocol, where annotators compare model responses and provide preference labels along with natural-language critiques. We hope that SocialArena can provide valuable insights and guidance for future LLM improvements.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39230

Beyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI

Pradeep Kumar GS, Ravi Tanniru

原文摘要

Financial AI systems must support decision-bearing questions involving payments, collections, cash flow, and compliance while ensuring numerical accuracy, traceability, and auditability. Large language models (LLMs) enable natural language interaction but cannot independently guarantee reproducible calculations or evidence-grounded recommendations. We present a production-grounded architecture integrating three components: a financial knowledge graph for enterprise relationships, temporal context, and provenance; a deterministic optimization engine for financial calculations and decisions; and a multi-agent LLM layer for intent interpretation, task orchestration, explanation, and claim validation. A coordination layer, termed context engineering, selects, ranks, composes, and validates query-specific context across ERP systems, tools, and tenants. Based on observations from 15 deployments over approximately 11 months, single-agent pipelines exhibited hallucination rates of about 7-9% (5-10% across query types), including invented invoices and unsupported financial claims. Graph-backed multi-agent validation reduced observed rates to below 1%, although these findings are observational rather than causal. ERP data quality and tenant-specific schemas remained major implementation challenges. Reusable mappings, graph templates, and validation policies coincided with a reduction in deployment time from roughly six to two weeks. We argue that financial context engineering extends beyond text-centric retrieval-augmented generation by requiring structured relationships, temporal validity, exact numerical evidence, access controls, and validation against source records and solver outputs. We outline research challenges in evaluation, reproducibility, privacy, context quality, and cross-tenant generalization.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.00058

GenoBERT: A Language Model for Accurate Genotype Imputation

Lei Huang, Chuan Qiu, Kuan-Jui Su, Anqi Liu, Yun Gong, Weiqiang Lin, Lindong Jiang, Chen Zhao 等 16 位作者

原文摘要

Genotype imputation enables dense variant coverage for genome-wide association and risk-prediction studies, yet conventional reference-panel methods remain limited by ancestry bias and reduced rare-variant accuracy. We present Genotype Bidirectional Encoder Representations from Transformers (GenoBERT), a transformer-based, reference-free framework that tokenizes phased genotypes and uses a self-attention mechanism to capture both short- and long-range linkage disequilibrium (LD) dependencies. Benchmarking on two independent datasets including the Louisiana Osteoporosis Study (LOS) and the 1000 Genomes Project (1KGP) across ancestry groups and multiple genotype missingness levels (5-50%) shows that GenoBERT achieves the highest overall accuracy compared to four baseline methods (Beagle5.4, SCDA, BiU-Net, and STICI). At practical sparsity levels (up to 25% missing), GenoBERT attains high overall imputation accuracy ($r^2 approx 0.98$) across datasets, and maintains robust performance ($r^2 > 0.90$) even at 50% missingness. Experimental results across different ancestries confirm consistent gains across datasets, with resilience to small sample sizes and weak LD. A 128-SNP (single-nucleotide polymorphism) context window (approximately 100 Kb) is validated through LD-decay analyses as sufficient to capture local correlation structures. By eliminating reference-panel dependence while preserving high accuracy, GenoBERT provides a scalable and robust solution for genotype imputation and a foundation for downstream genomic modeling.

q-bio.GN · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39223

Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers

Zhiwei Liu, Boao Kong, Bing Liu

原文摘要

Rotary Position Embedding (RoPE) typically uses uniform coverage across Transformer layers despite heterogeneous positional requirements. Phase-off interventions reveal non-uniform, model-specific rotary-phase dependence, while coverage interventions relate it to coverage-upgrade benefits. We propose profiling-guided layer-wise RoPE allocation, assigning high/low coverage under a fixed budget using early coverage-benefit profiles. The framework supports fixed-width query/key representations and physical rotary-dimension allocation in Multi-head Latent Attention (MLA). Normalized-depth mapping transfers profiles within model families, enabling small-model measurements to guide larger-model allocations before pretraining. A brief analysis relates selection and transfer to score calibration and inter-layer interactions. From-scratch experiments demonstrate validation-loss improvements over available budget-matched baselines, while analytical resource accounting identifies favorable quality--storage--compute trade-offs for physical MLA. These results connect positional demand to transferable, efficient architecture design.

cs.LG · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2509.11080

Membership Inference Attacks on Recommender System: A Survey

Jiajie He, Xintong Chen, Xinyang Fang, Min-Chun Chen, Yuechun Gu, Wenjin Liu, Keke Chen

原文摘要

Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping user behavior and decision-making, highlighting their growing impact in various domains. However, recent studies have shown that RecSys are vulnerable to membership inference attacks (MIAs), which aim to infer whether user interaction record was used to train a target model or not. MIAs on RecSys models can directly lead to a privacy breach. For example, via identifying the fact that a purchase record that has been used to train a RecSys associated with a specific user, an attacker can infer that user's special quirks. In recent years, MIAs have been shown to be effective on other ML tasks, e.g., classification models and natural language processing. However, traditional MIAs are ill-suited for RecSys due to the unseen posterior probability. Although MIAs on RecSys form a newly emerging and rapidly growing research area, there has been no systematic survey on this topic yet. In this article, we conduct the first comprehensive survey on RecSys MIAs. This survey offers a comprehensive review of the latest advancements in RecSys MIAs, exploring the design principles, challenges, attack and defense associated with this emerging field. We provide a unified taxonomy that categorizes different RecSys MIAs based on their characterizations and discuss their pros and cons. Based on the limitations and gaps identified in this survey, we point out several promising future research directions to inspire the researchers who wish to follow this area. This survey not only serves as a reference for the research community but also provides a clear description for researchers outside this research domain.

cs.IR · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39193

Goal-Aware Dynamic Multi-Agent Collaboration for Long-Horizon Tasks

Xu Shen, Lingyong Yan, Shuaiqiang Wang, Jianmin Wu, Zhikai Chen, Jiliang Tang, Jie Ren

原文摘要

LLM-based agents are increasingly used to complete complex, long-horizon tasks without human intervention. To make progress toward the task goal, agents need to perform different duties, such as planning and verification, when needed. To understand how single agents manage these duties during long-horizon execution, we conduct a preliminary study. Our analysis shows that verification has the strongest association with task success, but often occurs late, leaving limited opportunities for correction. We also find that the proportion of duty-relevant information decreases as records from different duties accumulate in a shared context. These findings lead us to examine whether multi-agent systems (MAS) can address these problems by assigning duties to agents with separate contexts. Our analysis shows that this separation alone is insufficient. Agents can lose track of the overall goal and repeat prior investigations. They may also lack necessary background while receiving irrelevant information from others. To maintain goal awareness and coordinate collaboration as task needs change, we propose Goal-Aware Dynamic Multi-Agent Collaboration (GAD). It uses a growing execution graph to organize subtasks and their dependencies. To keep agents focused on their goals, each context retains the original instruction and the assigned task's goal and acceptance conditions. To adapt collaboration and information sharing during execution, agents can divide tasks into subtasks and specify dependencies based on execution evidence. These dependencies guide when agents work and which results they receive. Verification and recovery check subtask results and full task completion against their goals, providing feedback for repair when checks fail.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39182

Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models

Aishik Nagar, Cheston Tan

原文摘要

Large language models (LLMs) are increasingly described as acquiring "reasoning" skills after reinforcement learning with verifiable rewards. However, whether these gains reflect genuine reasoning or more superficial adaptations remains underexplored. In this work, we probe LLMs trained in a finite and exhaustively analyzable logical domain, namely Tic-Tac-Toe, and trace how internal representations evolve across reinforcement learning (RL) with Group Relative Policy Optimization (GRPO). Quantitatively, RL yields high accuracy and robustness across prompt variations, suggesting the emergence of game reasoning. Mechanistic interpretability, however, paints a different picture: features extracted with sparse autoencoders (SAEs) reveal that models primarily adapt to rely more heavily on information already explicit in the prompt, such as whose turn it is, game progression and board occupancy. In comparison, high-level concepts like board symmetries and strategic forks remain weakly represented, raising concerns that reasoning benchmarks overestimate model abilities. This suggests that RL-driven "reasoning" may conflate task-specific adaptations to input information with reasoning ability. We provide, for the first time: (i) a systematic interpretability pipeline tracing representation dynamics across RL training in small-scale LLMs; (ii) an extension of SAE-based feature discovery to hypothesis-driven testing in a finite logical domain; and (iii) an interpretability-based demonstration that RL post-training neither adds nor removes concept information but reorganizes which features dominate the representation, with causal interventions locating the decision downstream of it, in the late-layer state.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39180

EmbodiExp: Compositional Experience Transfer for Embodied Agents

Zhifeng Gu, Ying Chen, Rui Jiang, Lei Yi, Bing Wang

原文摘要

Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may be inapplicable to the current state or fail to produce their intended outcomes. We present EmbodiExp, a framework for constructing transferable experiences and composing them online during embodied task execution. Our key observation is that tasks often share subgoals whose completion can be assessed independently of overall task success. We therefore introduce an outcome-grounded subgoal experience that specifies a subgoal, applicability conditions, an adaptable policy, and a verifiable outcome. During execution, applicable experiences guide action generation, while verified outcomes can establish the conditions required by subsequent experiences, enabling online composition. Subgoal-level outcome attribution further enables failure utilization: failed trajectories can still contribute verified local successes and condition-specific guidance on actions to avoid. Experiments on multiple embodied benchmarks under a fold-based protocol with frozen experience banks demonstrate the effectiveness of EmbodiExp.

cs.RO · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39175

PRISM: Personalized Item Representations in User History

Renzhi Wu, Zikun Cui, Junjie Yang, Li Sheng, Yongjun Xie, Jerry Fu, Nipun Mathur, Sri Reddy 等 9 位作者

原文摘要

Sequential recommenders typically construct history inputs from item identifiers or content features using an embedding map shared across users. The same item therefore yields the same initial embedding representation, even when users have different relationships to the item. We propose personalized item representations in user history, where each item's embedding expresses its relationship to the user. Personalization becomes a property of the history inputs themselves, supplying richer evidence for later sequence modeling. We instantiate this idea with PRISM, which reuses upstream ranking computation to generate personalized item embeddings. An autoencoder jointly compresses all layer states from a user tower, a user--item tower, and same-request candidate mixing into one embedding per scored pair for downstream replay. Offline evaluation on Surface 1, a major recommendation surface at billion scale, reports an average downstream normalized entropy (NE) change of $-0.15\%$, compared with $-0.07\%$ for VISTA at similar history lengths. We further identify an empirical sequence-length scaling law: over history lengths of 26--240 events, NE gain follows a fitted power law with exponent 0.468, increasing from 0.06\% to 0.17\%. Therefore, personalized item representations in user history provide a new scaling dimension for improving recommendation quality.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36660

The View from Nowhere: Population-Centered Agent Evolution

Shuo Yan, Ningning Hou, Haoyu He, Haochen Pei, Shang Gao

原文摘要

Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches center improvement on selected parent agents and their evolutionary experience, leaving the broader population largely underused. We identify a substantial gap between population coverage (i.e., the tasks solved by at least one evolved variant) and the performance of the best individual agent. This gap shows that useful capabilities and diagnostic evidence emerge across the population without being consolidated into its leading agents. These observations motivate the view from nowhere, a principle for agent evolution: an agent should be improved by interpreting its behavior through population-wide patterns of success, failure, and prior self-modification. We instantiate this principle as Population-Centered Evolution (PCE). PCE distils task records and modification histories from the population into a population block, which captures recurring failures, complementary successes, and the effects of previously attempted modifications to guide improvements to a selected parent's harness. Under matched models, initial harnesses, and evolution schedules, PCE achieves 72.1% success on SWE-bench Verified and 96.7% on Polyglot, improving over a strong group-evolution baseline by 3.2 and 5.9 percentage points. In our evaluation, PCE reduces the gap between population coverage and best-agent performance by one-third on SWE-bench and closes it on Polyglot. These results suggest that treating the population as evidence, not merely as candidates for selection, provides a complementary principle for agent evolution.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.28959

Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization

Mohammadsina Almasi, Andrea Carbonati, Hadis Anahideh

原文摘要

The exploration-exploitation trade-off is central to sequential decision-making and black-box optimization, yet how Large Language Models (LLMs) reason about and manage this trade-off remains poorly understood. Unlike Bayesian Optimization, where exploration and exploitation are explicitly encoded through acquisition functions, LLM-based optimization relies on implicit, prompt-based reasoning over historical evaluations, making search behavior difficult to analyze or control. In this work, we present a metric-level study of LLM-mediated search policy learning, studying how LLMs construct and adapt exploration-exploitation strategies under multiple operational definitions of exploration, including informativeness, diversity, and representativeness. We show that single-agent LLM approaches, which jointly perform strategy selection and candidate generation within a single prompt, suffer from cognitive overload, leading to unstable search dynamics and premature convergence. To address this limitation, we propose a multi-agent framework that decomposes exploration-exploitation control into strategic policy mediation and tactical candidate generation. A strategy agent assigns interpretable weights to multiple search criteria, while a generation agent produces candidates conditioned on the resulting search policy defined as weights. This decomposition renders exploration-exploitation decisions explicit, observable, and adjustable. Empirical results across various continuous optimization benchmarks indicate that separating strategic control from candidate generation substantially improves the effectiveness of LLM-mediated search.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33478

MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding

Quang-Trung Truong, Thanh-Nghia Nguyen, Phu-Phong Vo, Jaeyeon Kim, Cheng Chen, Jie Zhang, Binh-Son Hua, Duc Thanh Nguyen 等 10 位作者

原文摘要

Marine video understanding is crucial for a wide range of real-world applications. However, existing marine video datasets suffer from limitations, including the limited number of data samples, fine-grained text descriptions, and detailed visual attributes. To address these limitations, we introduce a large-scale, video-text dataset featuring rich, in-the-wild visual attributes tailored for complex marine environments. Our dataset comprises 2,000 video-text pairs annotated with 13 attributes covering up to four objects per scene, object visual/geometric properties, behaviors, environmental context, and camera motion, spanning diverse lighting conditions, times of day, and 7 countries. From these annotations, we generate 16,080 video-question pairs (12,080 multiple-choice, 4,000 open-ended). Furthermore, we benchmark both proprietary and open-source video-LLM models on video question answering and video captioning tasks. We find that (i) proprietary models often achieves superior performances; (ii) VLMs handle object motion well but struggle with complex camera motion; (iii) closed-source models struggle to perceive camera motion; and (iv) VLMs struggle to reason in static cameras.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.23616

Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Reveal

Parker Fawcett

原文摘要

An AI agent's rebuild is only as good as the process that produced it. Prior work found that once a model is strong enough, a multi-agent rebuild pipeline loses to the simplest approach: giving the model the original code and one instruction (AgentModernize). We present rebuild-dossier, an open-source tool that locks an application's real interface - its exact inputs and outputs - before any code is written, then enforces one-test-at-a-time building through automated checks, not written instructions alone. Three results shape this evaluation, with differing amounts of evidence. First, in a small comparison, the compliant agent failed a held-back test while the rule-breaking agent passed everything - proof that a passing suite doesn't certify correctness when tests can be gamed. Second, we tested whether this beats simply giving the weaker model the source and one instruction: tied on a small app, but lost outright on a larger one where the automated check wasn't even running - pointing to the check mechanism, not interface-locking, which held up separately. Third, every claim here is checked at three levels - the agent's own report, an automated log, and the actual files produced - catching real errors, including a bug in our own logging code, that a single level would have missed. These risks reproduce on a different model and toolchain: a stronger model followed our process three times running, something the weaker model never managed. The tool is public, MIT licensed, and reproduces end to end against our own applications.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.38866

When Context Changes: Understanding Update Failures in LLMs

Junyu Guo, Yuchen Fang, Shangding Gu, Costas Spanos, James Demmel, Javad Lavaei

原文摘要

As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old value of the same variable, a failure that we call stale binding. To study when models use outdated information and why, we introduce Controlled In-Context Memory (CICM), a benchmark for tracking and using updated information in conversations and agent logs. We observe that even frontier reasoning models can fail to recover the current state. We find that in open-source models probes can still recover the updated value when the model answers with an old one, pointing to a failure to select information that remains available. Component tests in Qwen and Pythia identify a mechanism for this selection failure: attention drift, where attention favors old values over the current one when producing an answer. We study a one-layer transformer to mathematically understand how this phenomenon happens: when attention scores are similar, several old values can together receive more attention than the current value. Guided by this explanation, we redirect attention toward the current value without further training. When the current value is requested directly, adjusting this intervention for each input corrects most old-value errors across various model families while preserving nearly all initially correct answers. Reliable context management therefore requires more than remembering updated information: models must use it to guide their answers.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39155

REALM: Identifying Minimal Task Assets for LLM Agents

Zihou Ren, Byungchul Tak, Long Wang

原文摘要

Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution toward unrelated resources. Applying least privilege therefore requires identifying the assets needed by a task, including assets whose identities emerge only during execution. We present REALM (Required Execution Assets Linked to a Mission), an approach to identifying and maintaining a task's required assets and their permitted uses. The approach represents required assets as Dependency Graph nodes, resolves prerequisite relationships, and admits newly discovered assets through source-scoped selection. It separates discovering an asset from authorizing its use, while preserving the agent's freedom to choose its computation. The REALM Builder maintains the selected grants and projects Asset Files; the Partial API Manager exposes resource-bound Partial APIs to the Agent inside a Task Container. Across 60 clean tasks and 560 injected cases in AgentDyn, it completes 40.0% and 36.4% of tasks and decreases ASR from 16.6% to 0.2% with qwen3.5-flash as the base model.

cs.CR · cs.AI · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28629

Mechanistic discovery in grain boundary structure and deformation driven by agentic AI

Yazhuo Liu, Kunqing Ding, Xiaoguo Gong, Zifeng Wang, Yichen Yang, Yifeng Che, Wen Chen, Josh Kacher 等 11 位作者

原文摘要

Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending these capabilities to domain-intensive mechanistic studies remains challenging. General grain boundaries (GBs) exemplify this challenge, as their structural complexity complicates experimental characterization and atomistic modeling. Here, we present GBClaw, an agentic AI framework for investigating the structure and deformation of general GBs, which are common in real polycrystals yet remain understudied. By integrating large language models into a modular architecture, GBClaw effectively combines systematic simulations with targeted mechanistic analysis through iterative workflow refinement and dynamic replanning. Applied to 14 general asymmetric tilt GBs in nickel, the framework characterized interfacial defect structures and deformation modes across these incommensurate boundaries. It established a general approach to identify previously unobserved, widely spaced secondary GB misfit dislocations (SGBMDs) alongside closely spaced primary GB misfit dislocations (PGBMDs) in simulated atomic configurations and experimental images. Comparisons of GB sliding with and without SGBMDs revealed substantial differences in shear strength, underscoring the critical role of misfit-dislocation hierarchies in sliding resistance. Researcher-guided follow-up calculations further elucidated the structural origins of shear asymmetry and an anomalous shear response. This work demonstrates that combining agentic AI with domain expertise bridges high-throughput computational screening and deep mechanistic discovery at complex material interfaces.

cond-mat.mtrl-sci · cond-mat.mes-hall · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.22016

ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention

Xinyan Wang, Xiaogeng Liu, Ming Pei, Chaowei Xiao

原文摘要

Large reasoning models (LRMs) often suffer from overthinking, continuing with redundant verification and repeated attempts even after reaching a correct solution. This wastes computation and can overturn an initially correct answer. We show that the transition from productive to redundant reasoning is decodable from late-layer hidden states. These representations separate the two phases around first-correct-solution boundaries beyond what position and lexical controls explain, and distinguish correct from incorrect solution endings. Building on this finding, we propose ROM (Real-time Overthinking Mitigation), which uses a lightweight streaming detector (0.07--0.25\% of backbone parameters) to monitor a frozen LRM and intervene at well-formed reasoning boundaries without answer extraction or probe decoding. Counterfactual Self-Correction (CSC) augments detector training with wrong$\rightarrow$correct trajectories to preserve useful self-correction. Heads are trained separately for each backbone using shared MATH500 supervision and transfer zero-shot to four unseen benchmarks. Evaluated against ten baselines across five backbones from three families and five benchmarks, ROM$_{\text{CSC}}$ reduces response length by 28--77\% (45\% on average), with significant reductions in all 25 settings and accuracy matching or exceeding vanilla decoding in 22. Measurements on two backbones further show 20--70\% lower end-to-end latency with less than 0.5\% detector overhead per decoding step. Code is available at https://github.com/SaFo-Lab/ROM.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗