跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描：2026-11-09 02:00 · 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 02:39 — 2026-11-09 02:39（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 02:00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 14,661 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 01:58（北京时间）
版本更新 · v2arXiv:2610.21450

X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation

Ruibin Ju, Ruifeng Cai, Min Xu, Zhuojie Chen, Lin Wang

原文摘要

Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chunk before replanning amortizes this cost, reducing model inference from 195 to 42 ms per executed waypoint for our policy. It also moves the states at which the policy is queried away from expert demonstrations, which supervise neither recovery from these states nor termination at the learner's own arrival. On OpenFly test-seen, no-stop failures account for 47.78% of full-chunk behavior cloning (BC) outcomes. We present X-Fly, a staged training framework for full-chunk aerial VLN. Recovery DAgger labels learner-visited decision states with smooth chunks that reconnect to future expert segments and with STOP at the first in-region state. Flow-GRPO then jointly refines the chunked flow controller and a Bernoulli STOP policy from same-task closed-loop outcomes, supplemented by outcome-verified stopping supervision. With eight controls per decision, X-Fly reaches 74.18% SR on test-seen and 51.73% on test-unseen, compared with 16.45% and 18.43% for full-chunk BC and 32.04% and 29.46% for DreamFly.

cs.RO · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05890

CellCanon: An Agentic Cellular World Model for Prediction, Explanation, and Observation-Driven Updating

Zhaokang Liang, Shuyang Zhuang, Xiaoran Jiao, Hao Chen

原文摘要

Biological discovery requires using molecular knowledge and new measurements to infer responses beyond the conditions already observed. We introduce CellCanon, the first agentic cellular world model to unify single-cell expression prediction, evidence-grounded explanation, and observation-driven updating. Its predictive core reuses condition-level biological evidence across gene-specific numerical readouts to guide single-cell expression generation. A shared world state links predictions, acquired measurements, and source-linked claims, supporting explanation and revision. On 339 held-out SciPlex3 conditions across three cell lines, CellCanon improves differential-expression AUPRC and Macro-F1 over the best baseline for each metric by 63.3% and 17.3%, respectively, and direction Macro-F1 by 7.2%. Relative to gene-wise reasoning on matched drug-cell cohorts, measured language-model token use falls by 99.77% for Predict and 98.41% for Explain. On the source-grounded benchmark, Explain correctly answers all answerable questions with supporting proofs and identifies all insufficient-evidence cases. In simulated experimental feedback, Update uses one measured source context per drug to exceed the best fine-tuned baselines in differential-expression AUPRC and Macro-F1 without changing model weights. Together, these capabilities support a cumulative account of cellular responses, with predictions and biological judgments that can be revised as evidence accumulates.

q-bio.QM · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04813

AgenticFinBench: Benchmarking Financial Agents on Diverse Tasks from Real-World Requests

Shu Zhou, Ziyang He, Yuxin Rao, Yudong Fang, Jiali Qian, Dongyuan Chen, Juntao Zhang, Yong Hu

原文摘要

Financial agents are becoming an important class of real-world AI systems. Financial tasks vary widely in type and difficulty, and many are open-ended with no ground-truth answers. However, existing benchmarks neither capture this breadth and open-endedness nor separate grounding from correctness. To bridge this gap, we introduce $\textbf{AgenticFinBench}$, a benchmark of 230 real-world financial tasks spanning 8 categories, 2 languages, and 4 complexity levels. We also propose a reference-free evaluation framework that combines question-specific rubrics with a two-stage claim audit that detects hallucinations, defined as claims absent from the agent's trace and refuted by external evidence. This framework better matches how financial work is assessed in practice. Experiments across 18 agent configurations reveal three key findings: (1) Ignoring hallucinations can overstate agent performance: hallucination auditing lowers the baseline leader's score by 7.58 points and moves it to fourth place. (2) Harness differences explain more variation in evidence grounding than model differences (28.6% vs 8.8%). (3) Quality scores fall from 89.44 on direct retrieval to 79.18 on the most complex tasks. Case studies show that agents struggle to explain how events affect company profits or stock prices, compare financial data on a consistent basis, and justify their conclusions. By releasing AgenticFinBench, we aim to advance financial reasoning, factual verification, and agent design for more reliable responses to diverse real-world financial requests.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30809

Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems

Tak Shing Au Yeung, Ka Chun Cheung, Hannah Potgieter, Steven J. Ruuth, Simon See

原文摘要

We investigate the use of neural network solvers for infinity and $p$-Laplace problems, which are fundamental in nonlinear analysis and have practical applications. Our approach employs Physics-Informed Neural Networks (PINNs) and Deep Operator Networks (DeepONets) to address computational challenges associated with large $p$ values, ranging from $2$ to $1000$, on various 2D and 3D domains. Our method offers advantages over traditional physics-based solvers, especially in three dimensions where mesh-based solvers become very costly for these problems. We also establish conditional convergence results for PINN approximations of both problems and a universal approximation result for DeepONet on the parametric $p$-Poisson problem. We demonstrate the effectiveness of these neural network solvers through numerical experiments and compare their performance with conventional methods.

math.NA · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.13686

Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation

Hao Qin, Chicheng Zhang

原文摘要

We study the contextual combinatorial semi-bandit (CCSB) problem, where at each round, the learner observes a context, selects a combinatorial action consisting of a subset of basic arms, and receives the reward of each selected arm; its goal is to maximize its cumulative reward over time. While many previous works focus on CCSB problems with linear reward function approximation, the design of efficient algorithms for the CCSB problem with general reward function approximation is limited. In this work, we study the realizable setting where the learner has access to a reward function class $\mathcal{F}$ that contains the true reward function, and propose the $\mathrm{SquareCB{.}Comb}$ algorithm. We prove that $\mathrm{SquareCB{.}Comb}$ achieves a minimax optimal regret bound of $O(\sqrt{m A T \log |\mathcal{F}|})$, where $A$ is the number of arms, $m$ is the maximum number of arms in a combinatorial action, and $T$ is the time horizon. In addition, $\mathrm{SquareCB{.}Comb}$ is computationally efficient when we have an online regression oracle that can efficiently predict rewards of all arms given contexts, and the combinatorial action set admits either efficient linear optimization or efficient sampling given any target marginal probability on arms. We empirically verify the effectiveness of our algorithm in webpage recommendation and contextual shortest path problems.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.08892

Diffuse AI Control on Fuzzy Tasks

Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar, Joe Benton

原文摘要

AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment. Diffuse AI Control is a subfield of AI safety concerned with mitigating risks from AI sabotage distributed over long deployment horizons (diffuse threats). These risks are particularly pernicious on fuzzy tasks, i.e. tasks which are hard to grade or require intuition. To understand diffuse threats on fuzzy tasks, we introduce a framework that considers AI control as an adversarial game between a blue team and a red team. The blue team uses a weak trusted model to construct a weak score against which they would train a strong, potentially subversive model to remove the subversion propensity if it were present. The red team then tries to find model behaviors that are rated highly by the weak score, and thus might not be trained out, but actually correspond to poor performance. We test our framework on the task of writing experimental proposals for research questions from recent ML papers. We use a language model with access to the original paper as a proxy "ground-truth" scorer. Our red team discovers subversive behaviors using multi-objective evolutionary prompt optimization. We show that Opus~4.6 can write proposals that are worse according to the ground truth proxy than those of GPT-OSS-20B, while the weak scorer rates them as highly as the best proposals from Opus 4.6. We then propose an adversarial optimization algorithm for the blue team that discovers more robust prompts for the weak model. This algorithm produces a blue team prompt that our red team optimization fails to exploit. Code is available at https://github.com/MikhailTerekhov/diffuse_control.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04279

Bidirectional Centered Score Matching for Discrete Diffusion Distillation

Peng Tu, Baoyou Chen, Haoyuan Xia, Zilong Dong, Weihao Yuan, Siyu Zhu

原文摘要

Discrete diffusion models with parallel decoding are often distilled using token-wise KL objectives. Although token-wise KL exactly matches the corresponding product-form block distributions, its probability-space optimization geometry and teacher-only candidate truncation may provide insufficient supervision under aggressive few-step distillation. Concrete Score Matching (CSM) provides an alternative within-position objective by aligning relative logit geometry, but its complete pairwise form incurs \mathcal{O}(|\mathcal{V}|^2) complexity. We propose Bidirectional Centered Score Matching (BCSM), an efficient within-position distillation objective that constructs an \mathcal{O}(K) bidirectional active set, reduces pairwise comparisons to \mathcal{O}(K^2), and factorizes them into an \mathcal{O}(K) objective. We further introduce cross-timestep transition alignment. Experiments demonstrate strong quality--efficiency trade-offs, including up to 6\times NFE reduction with a 16.9\% relative HumanEval gain and a 15.1\% relative MMMU gain at single-step inference.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2509.23003

Discovering Phase Space Structure in Learned Hamiltonian Systems

Yulong Yang, Jiayin Liu, Vineet Bansal, Christine Allen-Blanchette

原文摘要

Mechanics-inspired neural networks provide physically structured models of dynamical systems, but typically assume access to the coordinates in which the underlying dynamics are expressed. While recent generative approaches relax this assumption, they remain limited in their ability to jointly model different dynamical regimes and discover interpretable latent structure. We introduce Structured Phase Space GAN (SPS-GAN), a conditional generative framework that learns mechanical dynamics and discovers latent phase-space structure from Cartesian trajectories or video observations. We achieve this by combining adversarial generation with port-Hamiltonian latent dynamics and extending cyclic-coordinate regularization to account for dissipation and forcing. This formulation supports conservative, dissipative, and forced systems while encouraging compact latent representations from which active degrees of freedom can be identified. Experiments on simulated and real-world systems demonstrate improved trajectory accuracy and video generation quality over competitive baselines, while identifying active latent dimensions consistent with the expected effective degrees of freedom and recovering physically interpretable coordinates across observation modalities and dynamical regimes.

cs.LG · cs.AI · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05885

Does RRT* Work on Uneven Terrain Meshes?

Otobong Jerome, Tiago Nascimento

原文摘要

The optimal rapidly exploring random tree (RRT*) is proven asymptotically optimal on open subsets of Euclidean space with straight-line local planning. We ask whether it works on a triangle-mesh terrain, a two-dimensional surface in R^3. First, the original RRT* cannot run on a mesh: the surface has zero volume, so uniform sampling never hits it, no clearance ball fits in it, and chords across a fold leave it. Second, the surface reformulation we call Mesh RRT*, with its naive edge, the chord costed by its length, solved every run on heightfields with slopes up to 75 degrees but minimises the wrong objective: its cost, the straight-line length of a polyline whose vertices lie on the surface while its segments may leave it by a tolerance tau, is the length of no route on the surface and lies strictly below the geodesic length on any curved mesh. In numeric simulation and after 30,000 iterations the reported cost is on average up to 2.7% below the exact geodesic, a cost no path attains, and the returned route on average 0.1-0.5% longer than it. Rewiring keeps the biased edges, the bias decays only linearly with the step on polyhedral surfaces, and shrinking tau trades bias for connectivity. Third, replacing each chord by a path on the surface above it, built from projected points joined across the mesh edges they straddle and costed by its own length, makes every edge cost the exact length of a feasible path; with no other change the exact length of the returned routes is on average within 0.07-0.16% of the geodesic at every roughness tested, two to 3.4 times closer than with chords on the rougher terrains. The planner is in MeshNav3D 0.2.0 (release pending).

cs.RO · cs.CG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03775

FlowRig: Unified Skeleton Generation for 3D and 4D Meshes via Flow Matching

Fengzhi Guo, Nate Morrill, Shiqi Li, Cheng Zhang

原文摘要

Automatic rigging is a fundamental task for both static 3D and dynamic 4D mesh animation, yet existing methods do not provide a unified feedforward solution for these two settings. While static 3D riggers achieve strong quality, they often provide limited control over bone count and become temporally unstable when applied frame by frame to dynamic meshes. Existing 4D methods, in contrast, typically rely on expensive per-sequence optimization. We propose FlowRig, a template-free, data-efficient framework for unified 3D and 4D skeleton generation. Built on flow matching, FlowRig generates temporally aligned skeletons for an entire sequence in a single feedforward pass, while naturally handling single-mesh 3D rigging. The model further supports explicit skeleton-count control, uncertainty estimation for candidate selection, and masking-based interpolation, forecasting, and backcasting. To address limited paired 4D rigging data, we adopt a curriculum that initializes from large-scale 3D rigging data and adapts to mid-scale 4D mesh-skeleton data. Experiments show that FlowRig achieves strong static 3D rigging performance with controllable bone complexity, as well as high-quality and temporally consistent 4D reconstruction and prediction results.

cs.CV · cs.GR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2507.07359

Goal-Oriented Sequential Bayesian Experimental Design for Causal Learning

Zheyu Zhang, Jiayuan Dong, Jie Liu, Xun Huan

原文摘要

We present GO-CBED, a goal-oriented Bayesian framework for sequential causal experimental design. Unlike conventional approaches that select interventions aimed at inferring the full causal model, GO-CBED directly maximizes the expected information gain (EIG) on user-specified causal quantities of interest, enabling more targeted and efficient experimentation. The framework is both non-myopic, optimizing over entire intervention sequences, and goal-oriented, targeting only model aspects relevant to the causal query. To address the intractability of exact EIG computation, we introduce a variational lower bound estimator, optimized jointly through a transformer-based policy network and normalizing flow-based variational posteriors. The resulting policy enables real-time decision-making via an amortized network. We demonstrate that GO-CBED consistently outperforms existing baselines across various causal reasoning and discovery tasks-including synthetic structural causal models and semi-synthetic gene regulatory networks-particularly in settings with limited experimental budgets and complex causal mechanisms. Our results highlight the benefits of aligning experimental design objectives with specific research goals and of forward-looking sequential planning.

cs.LG · cs.AI · stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05877

When Does Better Confidence Improve a Knowledge-Graph Audit?

Zehao Lin, Kai Chen, Xixuan Hao, Erenkai Zhu, Chunyu Li, Helan Hu

原文摘要

Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit. We study this gap through repairability, selection headroom and label validity. Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass $Δ^{\mathrm{cl}}$. We simulate ideal repair against benchmark-aligned labels for five extraction configurations and two cross-document graphs on Re-DocRED, followed by frozen confirmation on test and replication on 500 hash-selected training documents. On the held-out cross-document graphs, an error-rate $\times$ fan-out queue leaves 3.98-4.74 percentage points more errors than a joint model with the same actions. By comparison, opening shared actions for that joint planner reduces residual errors by 0.89-1.43 points relative to its own fact-only plans, in point estimates. Equivalence between joint and independent-block models remains inconclusive. Generic LLM verification improves three of four model-budget configurations on each held-out set. LLM adjudication identifies possible benchmark omissions.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05876

MIGONet: a multiple-input graph neural operator with solver-free discrete manufactured-solution training

Muhammad Hasnain, N. K. Anand, Arun Srinivasa

原文摘要

Surrogate modeling of transport requires operators that capture the combined influence of spatially distributed sources and Dirichlet and Neumann boundary conditions, together with training datasets that can be generated at low computational cost. This work presents MIGONet, a multiple-input graph neural operator, and a discrete method of manufactured solutions (MMS) that trains it without solving a partial differential equation, using steady heat conduction as the model problem. In the discrete MMS procedure, temperature fields are prescribed a priori, and the source terms and Dirichlet or Neumann boundary data are evaluated with the same discrete operators as the reference finite-difference method (FDM), so every training sample satisfies the discrete governing equations by construction. Because the boundary data are derived from each field, a Dirichlet or Neumann condition can be assigned to every boundary segment of every sample, and the boundary specification becomes an operator input. MIGONet supplies representations of the complete source field and boundary data to every node before local message passing. On the rectangular domain, it is compared with a version without the complete-source encoder (MIGONet-local) and with the multiple-input operator network MIONet, using the same training data. MIGONet achieves mean relative temperature errors of 10.31% and 10.64% for curved-wire and Gaussian-spot heating, compared with 45.97% and 48.34% for MIONet and 72.25% and 67.82% for MIGONet-local. For 10,000 samples, discrete MMS reduces data-generation time from 486.65 s to 3.15 s relative to matched iterative FDM labeling. Separately trained MIGONet models are also evaluated on L-shaped, disc-shaped, and ring-shaped domains.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2503.22771

Unraveling Groundwater Stress: A Model Generalizable Across Space and Time Reveals Co-Declining Water Tables and Recharge Across Bangladesh

Saleh Sakib Ahmed, Rashed Uz Zzaman, Saifur Rahman Jony, Faizur Rahman Himel, Afroza Sharmin, A. H. M. Khalequr Rahman, M. Sohel Rahman, Sara Nowreen

原文摘要

Is Bangladesh replenishing the groundwater it depends on? Answering this question remains difficult in Bangladesh and worldwide because sparse in-situ measurements limit observational capabilities, while existing machine-learning approaches struggle to generalize across time and space. To address this bottleneck, we develop a Teacher-Student framework in which a Teacher accurately learns from sparse annual in-situ minimum (R2 = 0.86) and maximum (R2 = 0.96) depth observations to generate dense spatial patterns, and a Student transfers these patterns from time-varying 25-km GLDAS groundwater storage to high-resolution (2-km) depth maps using location-specific features. The Student achieves R2 = 0.93 over 2003-2022 and generalizes across unseen years (Leave-One-Year-Out R2 = 0.93) and locations (Leave-One-District-Out R2 = 0.70), enabling reconstruction without contemporary in-situ measurements. The reconstruction reveals widespread water-table deepening and a national decline in groundwater recharge of 1.10 mm/yr (p < 0.001). Autocorrelation-corrected analysis identifies statistically significant recharge declines across 55.6% of Bangladesh, compared with significant increases across only 4.9%. This imbalance suggests that pumping-induced recharge enhancement, as proposed by the Bengal Water Machine hypothesis, remains localized rather than widespread across Bangladesh. Together, these findings reveal widespread weakening of groundwater replenishment and provide a scalable framework for monitoring groundwater dynamics in data-sparse aquifers globally.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05874

Feature Puzzles: Single-Image Supervision for Multi-View 3D-Aware Segmentation

Jiahao Ma, Qiang Zhang, Miaomiao Liu, David Ahmedt-Aristizabal, Chuong Nguyen

原文摘要

Humans can easily recognize the same objects across different viewpoints of a 3D scene, whereas teaching models such multi-view-consistent perception typically requires videos or calibrated multi-view captures, which are considerably more expensive and less diverse than large-scale monocular data.~In this paper, we introduce Feature Puzzles, a novel framework for learning multi-view-consistent segmentation using only single-image semantic segmentation supervision. Specifically, we propose a simple yet effective pipeline that constructs multi-view-consistent segmentation pseudo-labels through image cropping and geometric transformations. We further introduce a lightweight, plug-and-play network that leverages the multi-view-consistent image features learned by existing pretrained 3D foundation models and the generated pseudo-labels to perform multi-view-consistent segmentation. Importantly, our flexible framework supports various types of prompts provided from one or multiple views and can be readily extended to open-vocabulary 3D segmentation. Under this single-image supervision, our feed-forward model achieves the best mIoU on NVOS, remains competitive on SPIn-NeRF and ScanNet++ against baselines using per-scene optimization or in-domain multi-view training, and demonstrates zero-shot transfer to open-vocabulary 3D segmentation. Visual comparisons are available on our project page: https://featurepuzzles.github.io/

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05870

AI-Assisted Classification under Correlation Neglect and Trust

Dingwen Kong, Liang Lyu, Saurabh Amin, Amine Bennouna, Daniel Huttenlocher, Asuman Ozdaglar

原文摘要

When does an AI assistant improve human decision-making, and when does it hurt? We argue that the answer depends not just on AI accuracy but also on how much its evidence overlaps with the human's and how the human combines the two. A worker makes a binary decision by observing her own signal and receiving a recommendation from an AI. We develop a human behavioral model with two primitives: her awareness of the overlap and her trust in the AI. Our analysis gives a closed-form phase diagram over AI capability and overlap, with regions of complementarity, impairment, and automation. A worker who neglects the overlap (correlation neglect) can be made less accurate by a more capable AI, double-counting the shared evidence. Trust reshapes the regions - undertrust may compensate for correlation neglect, so that the trust level maximizing accuracy depends on the deployment parameters. Empirically, we identify the two model parameters by pairing the same workers with different AIs, and break the accuracy loss into a correlation-neglect cost and an undertrust cost, one tied to reducing overlap on the AI side, the other to calibrating trust on the human side. On ChatBench, AI assistance raises accuracy by 21 points, yet workers apply only about a quarter of the Bayes-rational weight to AI information; GPT-4o falls in the automation region and Llama-3.1-8b stays at the complementarity boundary; and calibrating trust recovers about 2.6 points for GPT-4o but almost nothing for Llama-3.1-8b.

cs.GT · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05869

On Convergence of Gradient Temporal-Difference Learning with Regularized Corrections and Eligibility Traces

Jingyi Jin, Martha White, Hao Wang

原文摘要

Temporal-difference (TD) learning underlies many prediction and control algorithms, but can diverge when combined with off-policy learning, bootstrapping, and function approximation. TD with Regularized Corrections (TDRC) is theoretically sound and practically simple, but existing convergence theory covers only the one-step case under i.i.d. sampling, while the Huber Bellman-error formulation has not been extended to TDRC or eligibility traces. In this work, we establish convergence of constrained TDRC($λ$) with diminishing stepsizes and non-i.i.d. off-policy data, for state-dependent and history-dependent $λ$-parameters. We also propose TDRC($λ$)-Huber, which preserves the TDRC($λ$) fixed point while reducing sensitivity to large Bellman errors. For both algorithms, we apply an ODE-based weak-convergence method from stochastic approximation theory. For the nonlinear mean dynamics of TDRC($λ$)-Huber, we give an integral small-gain condition that guarantees uniqueness and global asymptotic stability of the target equilibrium. We then establish convergence of the constrained algorithm, derive computable sufficient conditions for convergence, and identify a regularization-based convergence mechanism shared by linear TDRC($λ$) and TDRC($λ$)-Huber. When the mean TD matrix is positive stable, both constrained algorithms converge under sufficiently strong regularization without requiring positive definiteness.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.33767

Local Entropy Fluctuations for Black-Box LLM-Generated Text Detection

Xinpeng Wang, Bruce Rushing, Zhizhen Chen, Zhe Zeng

原文摘要

Zero-shot detection of machine-generated text is vital for mitigating the risks of large language models (LLMs) misuse. While the state-of-the-art dual-model detectors and resampling-based detectors outperform single-model statistical detectors on unprompted continuations, they suffer a catastrophic breakdown on instruction-conditioned text in the black-box setting, where the source model is unknown. We analyze this failure and trace it to poor prompt conditioning for resampling-based methods and diminished cross-model discrepancy for dual-model detectors. Motivated by recent studies that human writing maintains a steady, uniform information flow, whereas machine-generated text exhibits sharp, localized entropy fluctuations, we propose a new metric, the Relative Peak Prominence Rate (RelPPR) to capture this structural contrast along the entropy trajectory and further leverage it as a signal for LLM-generated text detection. Extensive evaluations across diverse model families and datasets demonstrate that RelPPR achieves state-of-the-art black-box detection performance and remains the most reliable detector under various practical situations. Our code is available at https://github.com/brushing-git/entropy-llm-detector.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34158

Last-Iterate Stationarity of Muon with Finitely Many Newton-Schulz Iterations

Ping Li, Vincent Y. F. Tan

原文摘要

Muon has demonstrated strong empirical performance in large-scale language-model training, motivating a deeper theoretical understanding of its practical implementation. Unlike the idealized polar-factor update, practical Muon employs a fixed number of quintic Newton-Schulz iterations. Existing analyses primarily establish average- or best-iterate stationarity guarantees, while last-iterate convergence remains less understood. In this work, we investigate last-iterate gradient convergence of practical finite-step Muon on smooth, lower-bounded nonconvex objectives. In the deterministic setting, we show that Muon without input stabilization can exhibit cyclic behavior even on a smooth convex quadratic. In contrast, with positive stabilization, we establish last-iterate gradient convergence and square-summability of gradients for any fixed momentum coefficient below one and a sufficiently small constant learning rate. In the stochastic setting, we first demonstrate that persistent bounded, unbiased noise can prevent convergence under fixed learning rates and momentum, even with positive stabilization. We then establish almost-sure and mean-square last-iterate gradient convergence under bounded-variance stochastic gradients by combining diminishing learning rates with increasing momentum. Finally, we construct a smooth counterexample demonstrating that neither convergence theorem implies a pointwise polynomial convergence rate. Nevertheless, we establish density-one convergence rates, guaranteeing polynomial gradient decay for all but an asymptotically vanishing fraction of iterations.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.09252

LLM Agents Already Know When to Call Tools -- Even Without Reasoning

Chung-En Sun, Linbo Liu, Ge Yan, Zimo Wang, Tsui-Wei Weng

原文摘要

Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed. We propose When2Tool, a benchmark of 18 environments (15 single-hop, 3 multi-hop) spanning three categories of tool necessity -- computational scale, knowledge boundaries, and execution reliability -- each with controlled difficulty levels that create a clear decision boundary between tool-necessary and tool-unnecessary tasks. We evaluate two families of training-free baselines: Prompt-only (varying the prompt to discourage unnecessary calls) and Reason-then-Act (requiring the model to reason about tool necessity before acting). Both provide limited control: Prompt-only suppresses necessary calls alongside unnecessary ones, and Reason-then-Act still incurs a disproportionate accuracy cost on hard tasks. To understand why these baselines fail, we probe the models' hidden states and find that tool necessity is linearly decodable from the pre-generation representation with AUROC 0.89--0.96 across six models, substantially exceeding the model's own verbalized reasoning. This reveals that models already know when tools are needed, but fail to act on this knowledge during generation. Building on this finding, we propose Probe&Prefill, which uses a lightweight linear probe to read the hidden-state signal and prefills the model's response with a steering sentence. Across all models tested, Probe&Prefill reduces tool calls by 38\% with only 1.7\% accuracy loss, while the best baseline at comparable accuracy only reduces 6% of tool calls, or achieves a similar tool call reduction but incurs a 5$\times$ higher accuracy loss. Our code is available at https://github.com/Trustworthy-ML-Lab/when2tool

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05866

Auditable Unlearning for LLMs

Piyush Tiwary, Anushka Srivastava, Prathosh A. P

原文摘要

Machine unlearning aims to remove a user's data from a trained model after a deletion request. Existing methods are majorly evaluated on three axes - how well they forget, how much capability they retain, and how robust they are to membership inference attacks, but not on whether the provider can offer the user any evidence that the deletion occurred. To fill this gap, we introduce auditability as a fourth axis, defined as the separation between requested (forget set) and retained (retain set) data under a statistic the provider computes. We show that across eleven unlearning methods on TOFU, MUSE and RWKU no method satisfies all four axes, with different methods falling short on different axes. To address this, we propose a two stage method that can be used on top of any unlearning method, in the the first stage we propose ${GapWiden}$ which uses a hinge loss to increase the difference between audit statistics of forget set and retain set. In the second stage we propose ${GapVeil}$, an inference time rejection-sampler which uses the base model as the drafter and re-samples based on the audit statistics of the drafted response. We observe that using our method, auditability and leakage reach oracle parity for every unlearning method, and forget performance converges to the oracle; retain performance improves for nine of eleven methods but remains short of parity. Our results show that evidence of deletion or auditability can be constructed by design, and that treating it as an explicit requirement changes the viability of existing unlearning methods.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.01470

Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence

Payel Mukhopadhyay, Stefan S. Nixon, Romain Watteaux, Michael McCabe, Alberto Bietti, Kyunghyun Cho, Cristiana Diaconu, Irina Espejo Morales 等 23 位作者

原文摘要

Whether physics foundation models can be usefully deployed on laboratory experiments remains an open question for scientific machine learning (ML). We test this question on the Rayleigh-Taylor instability (RTI), a ubiquitous and demanding fluid instability seen from tabletop flows to supernova explosions, in which small perturbations at a density interface grow into chaotic, multiscale mixing as a lighter fluid accelerates into a heavier one. Standard ML models struggle with RTI, and despite over a century of theoretical, numerical, and experimental work, it carries an unresolved discrepancy between simulation and experiment: the late-time mixing growth rate, $α$, measured in most laboratory experiments ($\sim$ 0.06-0.07), is roughly three times the value from idealized direct numerical simulations (DNS, $\sim$ 0.02). The gap's origin remains debated. These properties make RTI a stringent test for a question that matters well beyond RTI: can foundation models trained only on simulations generalise to sparse, messy, and noisy laboratory settings? We finetune Walrus, a foundation model for continuum dynamics, on three or fewer DNS realizations and recover key RTI physics over long rollouts. Applied zero-shot to sliding-barrier laboratory data, the finetuned model leaves the DNS-like regime and enters the observed growth band, having never seen a single experimental sample. These results provide independent, data-driven evidence that initial conditions play a crucial role in the longstanding sim-experiment gap in $α$. The model also generalises zero-shot to stable stratification, a buoyancy regime absent from training, correctly slowing mixing-layer growth. Together, our results show that foundation models can generalise well beyond their training data, predicting laboratory behavior and unseen physical regimes, opening new ways to probe longstanding simulation-experiment gaps.

physics.flu-dyn · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05862

CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines

Yuqin Dai, Zhanwei Zhang, Honghui Yang, Zhouheng Yao, Yueqi Zhang, Jingyu He, Chaoyang Shi, Fanding Wei 等 12 位作者

原文摘要

Large language model (LLM) shopping assistants now recommend products in multi-turn conversations. However, reliable evaluation faces Data scarcity and Difficulty Standardizing Criteria. To address these obstacles, we introduce CARTBench for CART (Complex and Ambiguous Requests with Timelines). For Data scarcity, we curate cases from real commercial shopping needs across 17 retail domains, pairing timestamped dialogue with 1,603 product records. For Difficulty Standardizing Criteria, we develop case-specific rubrics guided by Ideal Response Principles, distilled from excellent replies manually selected from successfully completed orders. These principles also guide Principle-Guided CART Prompting, our structured recommendation strategy. The experimental benchmark contains 1,328 expert-annotated criteria across Core, Excellence, and Safety. To answer the CART question, we evaluate 7 flagship commercial API models, including GPT-6.1-Sol and Claude-Opus-5, and 35B+ parameters open-weight models. In the first full-suite evaluation under the frozen rubrics, 3 of 10 models exceed 90% on Core, while none exceeds 45% on Excellence. Therefore, we identify an understanding-to-execution gap between required behavior and high-quality purchase advice. To examine these limitations, we diagnose shared failures in product evidence and unresolved needs, linked to changing requirements and decisive unknowns. Code and data are available at https://github.com/Da1yuqin/CARTBench.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05859

Generative AI for urban planning: synthesizing land-use maps with satellite imagery via DualControlNet

Qingqi Song, Yuzhou Chen, Lingqian Hu, Shenhao Wang

原文摘要

Various land-use models characterize land-use patterns and facilitate scenario planning. However, existing models are largely predictive, forecasting transitions based on numeric data without synthesizing new land-use maps from simple text prompts. Meanwhile, generative AI in urban systems remains unimodal, weakly controllable, and evaluated mostly by generic image quality rather than domain-specific metrics. To address these gaps, we introduce DualControlNet, a generative land-use model that jointly synthesizes high-resolution land-use maps and satellite imagery, addressing multimodality, controllability, and verification challenges. Trained on over 40,000 paired tiles from Orlando and Chicago, DualControlNet is evaluated using land-use, spatial consistency, and image quality metrics. Relative to unimodal baselines, DualControlNet improves land-use diversity consistency by 62.8% and building coverage ratio consistency by 16.3%, more than doubles cross-modal spatial consistency, and triples visual quality. Scenario-based experiments demonstrate that DualControlNet supports sustainable development through multidimensional controls, increasing density and diversity, and responding to text prompts like "high-density development." Overall, this work advances land-use modeling via a multimodal, controllable, and verifiable generative framework, lowering technical barriers and enabling intuitive exploration of urban futures.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.35456

AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain-Computer Interfaces

Muyun Jiang, Yi Ding, Wei Zhang, Jinbo Chen, Chenyu Liu, Zhenjie Yang, Yuxin Li, Jingyuan Chen 等 12 位作者

原文摘要

EEG-based brain-computer interfaces support a broad range of applications, yet designing decoding architectures that perform well across diverse tasks remains challenging. We introduce AutoBCI, an agentic framework in which a Designer Agent and a Forecaster Agent support the discovery and selection of EEG decoding architectures across tasks. The Designer Agent performs Pool-Guided Architecture Discovery (PGAD), generating and refining architectures through training and validation across multiple EEG tasks, such as emotion recognition, motor imagery, and sleep staging. The Forecaster Agent performs Performance Estimation from Early Knowledge (PEEK), using architecture code, the training protocol, and early learning curves to predict full-budget validation performance and select promising candidates for continued training. Across 14 EEG datasets spanning motor imagery, emotion recognition, and sleep staging, we evaluate AutoBCI with six LLMs, including Opus 5.5 and GPT 5.6 Sol, and compare the architectures selected by the search procedure against ten baselines: six conventional EEG models and four foundation models. The architecture discovered by AutoBCI with Claude Opus 5.5 achieves 64.16% average test balanced accuracy (bAcc), compared with 63.87% for REVE, the strongest baseline on this metric. Using ten observed epochs, PEEK reduces mean absolute error in predicting average validation bAcc from 2.20 to 1.36 percentage points, a 38.1% reduction relative to the best-observed-score baseline. Code is available at https://github.com/Jiang-Muyun/AutoBCI

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.08567

Multi-User Large Language Model Agents

Shu Yang, Shenzhe Zhu, Hao Zhu, José Ramón Enríquez, Di Wang, Alex Pentland, Michiel A. Bakker, Jiaxin Pei

原文摘要

Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is designed to satisfy the objectives of one dominant user whose instructions are treated as the sole source of authority and utility. However, as they are integrated into team workflows and organizational tools, they are increasingly required to serve multiple users simultaneously, each with distinct roles, preferences, and authority levels, leading to multi-user, multi-principal settings with unavoidable conflicts, information asymmetry, and privacy constraints. In this work, we present the first systematic study of multi-user LLM agents. We begin by formalizing multi-user interaction with LLM agents as a multi-principal decision problem, where a single agent must account for multiple users with potentially conflicting interests and associated challenges. We then introduce a unified multi-user interaction protocol and design three targeted stress-testing scenarios to evaluate current LLMs' capabilities in instruction following, privacy preservation, and coordination. Our results reveal systematic gaps: frontier LLMs frequently fail to maintain stable prioritization under conflicting user objectives, exhibit increasing privacy violations over multi-turn interactions, and suffer from efficiency bottlenecks when coordination requires iterative information gathering.

cs.CL · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.13168

Who Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory

Junkai Zhou, Shiting Guan, Zhaoyi Zhang

原文摘要

As large language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationships has become a pressing issue. However, existing assessments primarily characterize general personality traits, providing limited insight into model behavior within intimate and emotionally sensitive contexts. Therefore, we introduce adult attachment theory into LLM evaluation and use the Experiences in Close Relationships-Revised (ECR-R) scale to characterize attachment anxiety and avoidance. To evaluate emotional companionship capabilities of LLMs in realistic interaction scenarios, we present an emotional companionship benchmark, ECBench, spanning four scenarios including emotional support, collaborative tasks, conflict resolution, and social guidance, across friendship and romantic relationships. ECBench is utilized to assess model behavior using 11 dialogue-quality metrics and three evaluation methods. We evaluate the attachment tendencies of 32 LLMs and select representative models to investigate how these tendencies manifest in contextualized multi-turn interactions and whether they can be shaped through prompting. Our study provides a theoretical lens from psychology, along with practical tools to understand and select LLMs for emotional companionship.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.27955

Reinforcement Learning in GUI Agents: A Survey Toward Digital Inhabitants

Junan Hu, Jian Liu, Jingxiang Lai, Jiarui Hu, Yiwei Sheng, Shuang Chen, Jian Li, Dazhao Du 等 9 位作者

原文摘要

Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces visually. Yet supervised fine-tuning alone cannot handle long-horizon credit assignment, distribution shifts, and safe exploration in irreversible environments, making Reinforcement Learning (RL) a central methodology for advancing automation. In this work, we present the first comprehensive overview of the intersection between RL and GUI agents, and examine how this research direction may evolve toward digital inhabitants. We propose a principled taxonomy that organizes existing methods into Offline RL, Online RL, and Hybrid Strategies, and complement it with analyses of reward engineering, data efficiency, and key technical innovations. Our analysis reveals several emerging trends: the tension between reliability and scalability is motivating the adoption of composite, multi-tier reward architectures; GUI I/O latency bottlenecks are accelerating the shift toward world-model-based training, which can yield substantial performance gains; and the spontaneous emergence of System-2-style deliberation suggests that explicit reasoning supervision may not be necessary when sufficiently rich reward signals are available. We distill these findings into a roadmap covering process rewards, continual RL, cognitive architectures, and safe deployment, aiming to guide the next generation of robust GUI automation and its agent-native infrastructure.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05851

Risk Control Certifies Rates, Not Magnitudes: An Audit of Selective Fetal Biometry

Zhengshuai Yang, Linna Jiang, Changyun Li, Guihu Zhao

原文摘要

Prenatal ultrasound biometry must return a head circumference (HC) and refuse when the image cannot support one. Selective prediction trades coverage against error, but its finite-sample guarantees bound the rate of gross errors, not their magnitude. We audit a tool-grounded biometry pipeline on two separately pre-registered four-way splits of the 999 labelled HC18 images, retraining the segmenter three times on each. Calibrating the contour-completeness threshold by exact Clopper-Pearson risk control returns a certificate indistinguishable from a hand-set floor, yet the pipeline still emits a 271.3 mm error: a small, geometrically complete ring fitted to an image whose true HC is 324.6 mm. The accepted candidate scores 0.94 completeness, so the score cannot see the failure, and one outlier among $\approx 150$ answers leaves the certified risk bound ($α= 0.10$) intact. A second, untouched split reproduces the mechanism on a different image (233.3 mm). Constraining the admissibility region---the anatomical range in which the measurand is defined---removes the family instead: raising the lower bound from 50 to 55 mm costs 0.4 coverage points and cuts the worst-case error on both splits to 11.4 and 11.1 mm, whereas suppressing it through the completeness threshold costs 19.0 and 12.1 points. At an anatomically defined 70 mm the frozen tests give 1.91 and 1.81 mm MAE.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05849

A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction

Zheyu Zhang, Yuanhao Huang, Fan Feng, Jie Liu

原文摘要

Foundation-model predictors of perturbation response are evaluated primarily by aggregate accuracy. Using their predictions to prioritize experiments requires assessing each prediction's reliability. We audit the state-transition (ST) decoder used in STATE across three encoders (SE-600M, scGPT, and Tahoe-x1) and four cell lines under CRISPRi. The decoder's first attention layer has a low-rank output. Projecting this output onto 4-32 fixed directions estimated from training activations preserves mean per-perturbation Pearson delta correlation (PDC). This low-rank attention bottleneck bounds the decoder's reliability by distance to training responses: PDC declines as the cosine distance from a perturbation's observed response to its nearest training response increases. We propose predicted-NN-distance, the cosine distance from a predicted response to its nearest training response, as a per-prediction confidence score. The score has a mean absolute Spearman correlation of 0.81 with PDC, close to the 0.88 obtained with the observed response. Thresholds calibrated on this score transfer across encoders and cell lines, and the score remains predictive of PDC for drug perturbations.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗