跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+918新增论文
+729其中 AI 相关
+73已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 12:06各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 12:43 — 2026-11-17 12:43(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:2026-11-17 04:58最近发现新增版本:2026-11-17 12:06库内论文最新更新时间:2026-11-16 04:06

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。

24,672 已收录论文20,615 AI 相关7,189 有修订112 HF 社区发现

浏览论文库

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 24,672 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v2arXiv:2607.05427

Entering the Elite, But Remaining Outside Its Core? The Temporal Structure of Gender Inequality in the Global Citation

Marek Kwiek

原文摘要

This study analyzed the gender dynamics of the global citation elite using the annual Top 2% Stanford/Elsevier lists for 2019-2024. While previous analyses have discussed women s representation (inclusion), I discuss what happens once male and female scientists are within the elite (position and persistence). The database used included 1.22 million person-year observations (N = 1,216,089) and 465,707 unique scientists and scholars from more than 150 countries. I studied entry, exit, and permanent membership in the elite. The share of women in the top 2% increased from 18.35% in 2019 to 20.85% in 2024. However, women were more strongly represented among first-observed entrants than among continuing members, and their share decreased from 21.58% among single-year members to 17.69% among scientists present in all six annual lists. Women were located closer to the lower boundary of the elite in terms of citation index deciles (the lowest decile included 26.88% of women). Men, in contrast, were closer to its upper boundary (the highest decile included only 15.23% of women). Logistic regression models estimated a lower probability of women s membership in the durable core of the elite (odds ratio estimate [OR] = 0.886). Consequently, increasing the inclusion of women in the elite does not mean their equal position within or equal persistence of membership in it. I draw conclusions about temporal gender dynamics within the global citation elite and gender inequalities in science more generally.

cs.DL

新论文 · v1arXiv:2611.07055

Expanding the Quality-Coverage Frontier with Competitive Flow Matching

Wenxuan Peng, Richard Zhang, Haitian Zheng, Jaskirat Singh, Tsai-Shien Chen, Eli Shechtman, Bharath Hariharan, Hadar Averbuch-Elor 等 9 位作者

原文摘要

Flow matching (FM) generators often face a quality-coverage tradeoff. Inference-time techniques such as classifier-free guidance raise quality, but at the cost of coverage. We hypothesize this limitation stems from a basic property of the objective: an intermediate noisy image could correspond to many clean images, yet the model can only predict a single velocity, at best averaging over the multiple possibilities. To mitigate this, we introduce competition among predictions during training. We achieve this by augmenting the predictor with a randomly drawn low-dimensional conditioning code $z$. For each training example, we sample $K$ values of $z$ to produce $K$ candidate velocities that compete to explain the target, and apply the loss only to the best-matching candidate. This winner-take-all objective allows different modes to shape different predictions, rather than being averaged into a single compromise. Furthermore, this term naturally enables a new form of guidance, auxiliary conditioning scaling, which complements traditional guidance methods. Together, these two guidance mechanisms show that our method substantially improves the quality-coverage frontier. We validate on ImageNet-256, using two different testbeds, SiT and RAEv2. Given less than 3% of the original SiT pretraining compute for post-training, at the 67% Recall point, our method reduces $\mathrm{FD}_{r,6}$ from 19.22 to 5.91. On RAEv2, at the 70% Recall point, it reduces $\mathrm{FD}_{r,6}$ from 16.83 to 3.18.

cs.CV

版本更新 · v2arXiv:2609.00700

Value Over Language Model: Detecting Original Contribution in Writing

Vibhhu Sharma, Thorsten Joachims, Sarah Dean

原文摘要

LLMs have been rapidly adopted across writing tasks, prompting the development of tools for detecting LLM-generated text. Yet, these tools largely measure how much of a document's surface text was written by an LLM and aren't fundamentally designed to measure how much of the information content or ideas originated from the LLM itself rather than being supplied by the user in the prompt. In this work, we design a framework that measures how much value a person adds on top of what a language model could have easily produced by itself. The method requires no training or labeled data and never scores the document's surface text, insulating it from stylistic confounders. Instead, it extracts the document's content at increasing levels of granularity, uses an LLM to reconstruct the document from each partial representation, and compares these reconstructions with those produced from the task description alone. We call this framework Value Over Language Model (VOLM), which measures a document's contribution relative to a replacement-level document that an LLM could produce from the task description alone. We evaluate VOLM with a specific instantiation of this framework across three domains: news articles, ICLR peer reviews, and argumentative essays. VOLM separates human-authored documents from matched LLM-generated documents produced from generic task descriptions, while remaining substantially invariant to content-preserving transformations, including LLM-based reconstruction and round-trip translation. We further find that increasingly constrained content extractors reduce residual differences between LLM-generated and humanized text, demonstrating the importance of disentangling informational content from stylistic variation. We hope these results encourage further work on specialized instantiations of the framework and on assessing human contributions in LLM-assisted writing more generally.

cs.AI · cs.CL

新论文 · v1arXiv:2611.07054

Reclassification Is All You Missed: Surfacing Variant Reinterpretation Need in Online Health Communities at Population Scale

Kamalakkannan Ravi, Mengshu Nie, Annapurna Poduri, Cong Liu

原文摘要

Genetic variants are routinely reclassified in ClinVar after a patient is tested, sometimes from uncertain to pathogenic, yet patient recontact is inconsistent, with no clear duty and responsibility diffused among labs, providers, and patients. Many affected people discuss their results in public online health communities that clinical recontact often does not reach. We built PRISM, an agentic large-language-model pipeline that screens these posts, checks whether the variant was later reclassified, and drafts a disclaimer-bearing outreach message, in a no-contact dry run. Across 3.9 million posts from 32 communities, agent-predicted reinterpretation-relevant discussion is rare (0.288%) but concentrated in specialist genetics communities (6.30% versus 0.10% in general medical-advice communities) and growing fivefold since 2014; PRISM surfaces 123 candidate classification differences, 5 of them from an uncertain submission to pathogenic or likely pathogenic. On a held-out set of 30 real-post drafts, a clinician judged 27 factually grounded and 15 fit to send: factual accuracy is necessary but not sufficient for clinically acceptable outreach. PRISM contributes a population-scale reinterpretation-need map with code and data to be released upon publication.

cs.CL · cs.AI · cs.CY · q-bio.GN

版本更新 · v2arXiv:2610.27041

Robustness of Internal Signals for Hallucination Detection in Vision-Language Models

Allison Chen, William Yang, Salma Abdel Magid, Jonathan Williams, Olga Russakovsky, Esin Tureci

原文摘要

When given an image and a text prompt, vision-language models (VLMs) can produce seemingly sophisticated text responses. However, they are also prone to hallucinate objects in their output, which can have detrimental consequences in safety-critical applications. To detect these hallucinations, certain methods interestingly leverage internal signals from the VLM as it generates the text response; potentially, these methods use the same signals that led to a hallucination to detect it. We conduct an in-depth analysis to understand the robustness of these detection methods. First, we show that a naive baseline of a generated word's token position in the VLM text response achieves competitive performance. Further, we reveal how some detection methods rely on token position and use this heuristic as a shortcut. Second, we explore detection methods' sensitivity to language and vision modalities. Our experiments suggest that strong detection performance is often driven by detecting language-based hallucinations, and when methods rely on token position, they tend to be less visually grounded and exhibit reduced robustness when hallucinations occur earlier in a text response. Lastly, we demonstrate that different detection methods can carry complementary signals; when ensembling methods together, adding weaker methods to an ensemble of higher performing ones still offers performance improvements. Altogether, while there may be useful internal VLM signals to detect hallucinations, our investigation reveals important limitations of the current methods that try to leverage them.

cs.CV · cs.AI

新论文 · v1arXiv:2611.07051

Closed-Loop Agent Evaluation: Layered Measurement and Self-Calibration

Ruifeng Ren, Gun Ahn

原文摘要

Once an agent is live, teams want to know whether it is doing its job, not just whether it throws errors. Yet most evaluation is one-off: a benchmark run, a look at traces, a single score. Its conclusions neither check themselves nor reach the agent. We propose closed-loop evaluation, an evaluation method for deployed agents. It models evaluation as performance estimation under biased raters and censored outcomes, and it requires every level's conclusion to trace back to atomic data and to be computed by versioned rules. The method covers four levels of analysis (span, trace, conversation and engagement), measures along a spine of Execution, Substance, Trajectory and Results, treats Conduct as a constraint throughout, and uses Provenance and Adjudication components to certify the evidence and the evaluators. Evaluator agents generated by an Agent Factory carry these components, each with a domain knowledge pack and an adapter harness. Two loops close the evaluation: an inner loop audits the evidence, rules and metrics themselves, and an outer loop uses per-component regression checks to drive agent improvement. We also give a pipeline that runs this process automatically. Using the business-analysis agent SharpInsight as a case and porting the method to public conversation data, we show how problems differ across levels and how evidence-and-rule judgment is more reliable than holistic scoring (ICC 0.86 vs. 0.81; kappa 0.81 vs. 0.63).

cs.AI · cs.CL

新论文 · v1arXiv:2611.07050

Authorization Propagation in Agent2Agent Systems: An Experimental Security Evaluation of Multi-Hop Delegation

Gabriele Donno, Kashif Mehmood, Katina Kralevska

原文摘要

Delegated Agent2Agent (A2A) workflows create a security problem when the agent sending a request is different from the principal from which the authority originated. This paper evaluates a layered downstream-verification design in a synthetic four-party healthcare reimbursement workflow. The prototype separates current-caller context, transitive authorization evidence, per-hop Ed25519 request authentication, and independent replay state for requests and authorization artifacts. Of 15 adversarial conditions, 14 are rejected; an isolated delegation-path test exposes the absence of semantic authority attenuation. A separate authorized-intermediary experiment shows that a holder of the shared authorization-evidence HMAC key can modify the represented authority and generate valid evidence. In the fixed-depth local benchmark, the full configuration has a median security-processing latency of 5.11 ms and a 3.87 kB serialized payload. The results show the value of separating request authentication from inherited authority while identifying origin-verifiable delegation and semantic attenuation as requirements for stronger A2A authorization propagation.

cs.MA

新论文 · v1arXiv:2611.07049

Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering

Yiyan Wang, Haohan Liu, Tetsuo Shibuya

原文摘要

Hybrid Mesh-Gaussian rendering combines compact textured surfaces with flexible 3D Gaussian primitives, offering an efficient alternative to purely Gaussian scene representations for structured environments. Existing scene-reconstruction hybrids commonly follow an additive formulation, where Gaussian residuals compensate for errors left by the mesh. However, not every Mesh-Gaussian conflict is caused by missing content: residual geometry errors, occlusion mismatch, texture-projection artifacts, and view-dependent appearance can make the same mesh content consistent in one view but inconsistent in another. We therefore formulate hybrid rendering as a multi-view inconsistency problem and present Gaussolve, a subtract-and-refill framework that selectively dissolves inconsistent mesh content before residual Gaussians refill the revealed regions. We introduce a lightweight Neural Dissolve Field, parameterized by scalar spherical-harmonic Gaussians, to learn where and from which viewing directions mesh content should be dissolved. A continuous transmittance fusion rule progressively exposes residual Gaussians behind the dissolved mesh, preserving their reconstruction gradients and avoiding hard visibility discontinuities. Experiments on structured and semi-structured scenes demonstrate higher visual fidelity with fewer Gaussian primitives and faster rendering. Project page: https://ooosn.github.io/gaussians-can-subtract/

cs.CV

新论文 · v1arXiv:2611.07048

Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI

Andrew W. Lo, Chaoyi Zhao

原文摘要

Evolution has shaped intelligence for billions of years. Artificial intelligence (AI) now raises a striking possibility: intelligence may begin to direct its own evolution. As AI agents become capable of modifying and evaluating their own behavior, how quickly could they improve, and how can that improvement remain safe? We develop a theoretical framework comparing Darwinian, Lamarckian, and agent-directed evolution following environmental change. Darwinian evolution relies on natural selection, Lamarckian evolution adds inherited learning, and agent-directed evolution allows agents to generate and evaluate behavioral variants and choose how extensively to search. When learning is sufficiently effective, these mechanisms exhibit progressively faster adaptation. Generating more variants accelerates adaptation, while optimal search effort depends on learning ability, problem difficulty, and experimentation costs. However, an agent's ability to direct its improvement does not ensure that improvements are evaluated against the intended objective. When the evaluation target is misspecified, additional search accelerates convergence toward the wrong behavior, even as measured performance improves. In recursive self-improvement, such errors may persist across generations, posing challenges for AI safety. Independent evaluation and oversight must keep pace with autonomous AI development. The central challenge is not simply to accelerate the evolution of intelligence, but to preserve humanity's ability to guide its direction, limit its speed, and intervene when necessary.

cs.AI

新论文 · v1arXiv:2611.07043

Polynomial Lower Bounds for Steiner Shortcuts via Test Functions

Aaron Bernstein, Henry Fleischmann, Bernhard Haeupler, Gary Hoppenworth, Thatchaphol Saranurak

原文摘要

The Steiner shortcut problem asks whether every directed graph $G=(V,E)$ with $n$ vertices and $m$ edges admits an augmentation $G_{+}=(V\cup V_{+},E\cup E_{+})$ with $m^{1+o(1)}$ edges such that $G_+$ has the same reachability structure as $G$ (i.e. for all $s,t\in V$, $s$ reaches $t$ in $G$ iff $s$ reaches $t$ in $G_+$), and the diameter of $G_{+}$ is $m^{o(1)}$. This is a core combinatorial question underlying many reachability algorithms in the dynamic, streaming, and CONGEST models, and all parallel algorithms with almost-linear work and sublinear depth. A sequence of works ruled out such a shortcut $G_{+}$ in the non-Steiner setting where $V_{+}=\emptyset$. However, as recently shown by Bernstein et al. [STOC '26], all known non-Steiner lower-bound constructions fail once Steiner vertices $V_{+}$ are allowed. This paper rules out almost-optimal Steiner shortcuts: we show an infinite family of graphs $G=(V,E)$ with the property that, for any $\varepsilon>0$, a Steiner shortcut $G_{+}=(V\cup V_{+},E\cup E_{+})$ with $m^{1+\varepsilon}$ edges must have diameter at least $n^{1/56-O(\varepsilon)}$. Our construction strengthens the standard non-Steiner lower-bound framework via an additional structure that allows Steiner vertices to be replaced by original vertices; we can then reduce back to the standard arguments without Steiner vertices. This new structure is achieved via a new general strategy based on test functions, which is quite flexible and can potentially be extended to applications beyond our work. We also generalize our lower bound to exact Steiner hopsets in undirected graphs and to depth reduction for monotone circuits. The latter significantly strengthens the classical lower bound based on Sylvester matrices.

cs.DS

新论文 · v1arXiv:2611.07042

Follow the Policy, Fail the Benchmark: Auditing and Revising Policy-Based Decision Benchmarks

Yanru Xiao, Yifei Cai

原文摘要

Policy-based decision benchmarks evaluate whether systems apply written rules to financial and operational cases. Yet a rule-following response can be marked wrong when the benchmark misstates the required decision. We audit nine public policy-based decision benchmarks through source tracing, program execution, and controlled checks. We find unsupported targets, reference errors that survive replay or propagate as solved steps, and evaluators that reject acceptable answers or credit incomplete decisions. To measure the scoring impact, we rescore unchanged model responses. On the 96 LegalBench SARA numeric cases, correcting the scorer raises acceptance by more than 80 percentage points for each of three models, without changing references or responses. In RuleArena Tax, restoring a required zero floor changes 27 of 300 references and narrows an observed model gap. A controlled federal-exemption task with explicit ownership and eligibility assumptions also shows that errors in supplied intermediate answers can affect final decisions. We present BAR (Benchmark Audit and Revision), a versioned collection of audit evidence and revisions for reevaluation.

cs.CL · cs.SE

新论文 · v1arXiv:2611.07040

An LLM-Orchestrated Neuro-Symbolic Framework for Verifying Diagnostic Signal Reachability in Electronic Systems

Heba Jaradat, Mohammed-Khalil Ghali, Saurabh Kulkarni, Rohan Kulkarni, Sangwon Yoon

原文摘要

Diagnostic Signal Reachability (DSR) captures whether board-level health signals are observable by management controllers, including baseboard management controllers (BMCs), complex programmable logic devices (CPLDs), and other smart controllers. Verifying DSR is essential for field diagnosability in datacenter fleets, where one design is deployed at massive scale, yet it remains largely manual, since each signal is traced by hand across schematic sheets, renamed nets, series components, and monitoring devices. Large language models (LLMs) are attractive but unreliable at structural connectivity reasoning, where over-claiming can silently hide a rare coverage gap. We present NetFlow-DSR, a neuro-symbolic framework in which an LLM orchestrates the DSR pipeline and resolves device roles mainly from part-name families and library pin names, consulting specifications only for ambiguous parts. Pin directionality is read from the design library, and deterministic graph engines verify connectivity over the authoritative netlist. The pipeline detects diagnostic nets, canonicalizes renamed net fragments, and performs controller-seeded, power-aware breadth-first search over an admissibility graph that credits device-mediated monitoring. Each verdict carries an auditable trace card whose proof path is the witness. Across five production boards from an AI platform, covering 421 expert-graded signals, a three-stage ablation improves pooled F1 from 0.578 to 0.944. Because a monitored verdict is emitted only with a proof path, the verifier is sound by construction, and precision and specificity were 100% in the evaluated data. In a cross-model study on the system-controller module, precision remained 100% across three LLMs while recall tracked each model's device-semantic extraction. Precision therefore depends on the netlist-grounded verifier and correct device semantics rather than on any single LLM.

cs.SE

版本更新 · v2arXiv:2610.14070

What Does the Effective Dimension of a Hybrid Quantum Neural Network Actually Measure?

Md Masum Mia, Amith Khandakar, Mohamed Arselene Ayari

原文摘要

Hybrid quantum neural networks (QNNs) pass features from a classical backbone into a variational quantum circuit, and many studies log a scalar called the effective dimension as a sign of capacity or model quality. The effective dimension is usually defined as the participation ratio (PR) of the quantum Fisher information matrix (QFIM), but studies in practice log a PR of cheap parameter sensitivities instead, and the meaning of that scalar is rarely tested. We show that the logged scalar equals the PR of Pauli-Z output sensitivities, that each sensitivity is at most n times its QFIM diagonal entry on n qubits, and that a PR of the QFIM diagonal overstates the full-matrix PR by an exact factor set by the off-diagonal mass. We then test the scalar on CIFAR-10 and EuroSAT with four frozen backbones, one of them a random projection, over 4 to 16 qubits, 1 to 4 layers, three entangling patterns, and three seeds. At a fixed circuit, CIFAR-10 accuracy spans 23.14% to 86.44% while the scalar stays between 6.63 and 9.13, and its correlation with accuracy changes sign across seeds in 7 of the 14 configurations. Depth raises the share of active parameters from 0.39 to 0.91, near a ceiling we derive, and initial gradient variance falls by a factor of 34.5 from 4 to 16 qubits. Removing entanglement raises accuracy by 5.3 to 8.2 points at the same parameter count. The effective dimension therefore describes circuit geometry rather than model quality, so capacity, trainability, and accuracy each need their own diagnostic.

quant-ph · cs.AI

版本更新 · v2arXiv:2602.00192

AI-Generated Image Detectors Exploit Global Artifacts: Evidence from Inpainting Exchange

Elif Nebioglu, Emirhan Bilgiç, Adrian Popescu

原文摘要

Modern diffusion-based inpainting enables realistic, localized image manipulation, raising critical challenges for reliable detection. We show that state-of-the-art AI-generated image detectors largely fail to identify \emph{what} was synthesized and instead exploit a \emph{global} artifact introduced as a side effect of the generation pipeline: latent-diffusion inpainting passes the entire image through a VAE encoder--decoder, inducing a subtle but pervasive spectral shift even in unedited regions. We turn this observation into a simple, model-free diagnostic, \emph{Inpainting Exchange} (INP-X), that restores the original pixels outside the edited region while preserving all synthesized content. To study the effect at scale, we build a benchmark of $30$K matched real, standard-inpainted, and exchanged triplets ($90$K images) spanning four datasets and three inpainters. INP-X requires no model access and is a single compositing step, yet it collapses pretrained detectors, commercial APIs, and bias-aware methods toward chance (commercial APIs: $>$$90\%\!\to\!\sim$$55\%$; the bias-aware DDA: $97.6\%\!\to\!58.4\%$). We give formal propositions linking the effect to high-frequency attenuation from the VAE information bottleneck, and we causally isolate it with a factorial battery and a variance decomposition that attributes $97\%$ of the background spectral shift to the autoencoder round-trip alone. A perceptual study ($n{=}153$) shows the shift is also perceptible to humans, whose accuracy falls from $63.8\%$ to $56.2\%$ ($p{=}0.002$): significantly reduced, though not eliminated. Finally, we show that mechanism-driven mitigations (mixed-distribution and localization-supervised training) improve robustness, but detecting INP-X edits remains an open problem. Our benchmark and code are available at: https://github.com/emirhanbilgic/INP-X

cs.CV · cs.AI

新论文 · v1arXiv:2611.07025

LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time

Teresa Delgado, Hugo Hazard, Martin Benfeghoul, Jun Wang, Zafeirios Fountas

原文摘要

Autoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length and caps batch size and throughput. Existing post-training methods exploit redundancy across tokens, layers, and feature dimensions, or lower numerical precision. We identify a complementary axis: within each attention head, values are largely predictable from their corresponding keys. We exploit this with value cache amortisation, which fits a lightweight per-head predictor at test time and stores residuals only for the tokens it reconstructs worst, giving $4\times$ near-lossless value compression. The predictor can be initialised by meta-learning for substantially reduced prefill overhead, or fitted from scratch in settings that allow a one-off cost, such as multi-query inference. We pair value amortisation with cross-layer low-rank key compression to produce LowRAM, an asymmetric compression pipeline that stays close to lossless across three model families. By reconstructing only a selected subset of KV pairs at each decoding step, LowRAM can keep decoding overhead minimal and achieve up to $5\times$ higher peak decode throughput at $4\times$ compression. LowRAM further composes with quantisation and eviction, reaching $26.9\times$ compression at $94.5\%$ of baseline performance on long contexts. These results show that treating keys and values as structurally distinct enables efficient, aggressive, and composable KV cache compression.

cs.LG · cs.CL

新论文 · v1arXiv:2611.06914

面向LLM社会智能体的上下文丰富与选择性鲁棒性框架

A Framework for Context Enrichment and Selective Robustness in LLM Social Agents

Mattia Greiche, Reihaneh Rabbany, Maximilian Puelma Touzel

AI 速读 基于摘要

提出受控上下文丰富方法与“选择性鲁棒性”验证标准,并在类囚徒困境游戏中比较不同上下文丰富形式对LLM智能体行为的影响。

cs.MA · cs.CL · cs.LG

查看原文摘要

Researchers use large language models as agents in social simulations, where agents are prompted with observations and background information intended to shape their actions. Yet LLM agents have been shown to substantially change their behavior under meaning-preserving prompt variations, creating a validation problem for social simulation. One plausible hypothesis is that this brittleness reflects a lack of grounding and can be reduced by enriching the context provided to the agents. Whether richer context improves robustness remains unclear, in part because context richness and robustness are rarely defined in ways that support controlled comparisons. We address the first need with controlled context enrichment, a set of prompt substitution rules that systematically enriches distinct types of context: neutral padding, generic social background, descriptive decision grounding, and normative decision grounding. We address the second by introducing selective robustness as a validation criterion: insensitivity to meaning-preserving prompt variation combined with a directional response to decision-relevant changes in the social world. We demonstrate the framework in a Prisoner's Dilemma-like game, showing how it can be used to identify which forms of context enrichment produce more desirable and robust agent behavior. We find that these forms of enrichment produce distinct behavioral patterns that vary between the two models tested.

新论文 · v1arXiv:2611.06912

FlowReconBench:稀疏传感器下学习型与经典流场重建的精度、校准与成本基准

FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors

Nicolas Tricard, Linzheng Wang, Jason Chen, Sili Deng

AI 速读 基于摘要

该基准在三种流态下统一比较十种学习型与五种经典稀疏传感器流场重建方法,考察逐通道误差、集合离散度、校准、频谱与计算成本。

physics.flu-dyn · cs.LG

查看原文摘要

Reconstructing full flow fields from sparse sensors requires prior assumptions about unmeasured regions and physical variables. Yet it remains unclear when learned models outperform classical estimators and which aspects of their predictions can be trusted. FlowReconBench evaluates ten learned and five classical methods on three regimes: a laminar cylinder wake across Reynolds numbers, two-dimensional Kolmogorov turbulence and a large-scale three-dimensional (3D) isotropic turbulence. Methods share leakage-controlled splits and sensor draws and are scored on per-channel error, ensemble spread, calibration, spectra and cost. The leading method changes for each regime. Classical methods perform strongly in low-order and dense-sensing regimes. On the cylinder wake, linear stochastic estimation and gappy proper orthogonal decomposition lead, including for unobserved pressure. In 3D, inverse-distance weighting matches the best learned methods on observed channels. Data-driven methods become superior at decreasing sensor density or poor sensor observability. On Kolmogorov flow, continuous ranked probability score and error yield different method rankings: generative models offer broader but underdispersed ensembles, while deterministic models prioritize pointwise error. Generative models balance this tradeoff through their sampler budget, with a larger budget improving ensemble quality at higher computational cost. In 3D, scaling tests demonstrate that queryable methods are flat in memory, while full-grid construction methods run out of memory. Observing only 2 of 4 fields leaves the problem kinematically underconstrained, yet a latent model can reproduce structural similarities to the ground truth.

新论文 · v1arXiv:2611.06911

BEAKER:面向自驱动化学实验室具身大脑的专家精选基准

BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories

Fei Lin, Tengchao Zhang, Ziyang Gong, Xiaotong Yu, Bohan Zhang, Yifan Zhou, Qihao Yang, Ji Dai 等 18 位作者

AI 速读 基于摘要

作者提出并构建了专家人工标注的 BEAKER 基准,用于评测多模态大模型在自驱动化学实验室中的执行导向具身能力。

cs.AI

查看原文摘要

Self-Driving Chemical Laboratories (SDCLs) are moving chemical experimentation toward embodied automation, where machines must perceive laboratory scenes, reason about experimental states, and act under physical, procedural, and safety constraints. Although Multimodal Large Language Models (MLLMs) are increasingly considered as embodied brains for such systems, existing laboratory benchmarks mainly focus on safety, anomaly detection, or general scientific understanding, leaving their execution-oriented embodied capabilities underexplored. To fill this gap, we introduce BEAKER, a Benchmark for evaluating Embodied Actionability, Knowledge, Experimentation, and Reasoning in SDCLs. BEAKER contains 1,000 expert-curated question-answer samples across 11 image and video task types, covering key judgments required for chemical laboratory execution, including affordance grounding, trajectory planning, equipment, state, and safety recognition, apparatus setup, operation and step reasoning, and temporal procedure reasoning. All questions and annotations are manually created and reviewed by chemistry and embodied Artificial Intelligence (AI) experts, without AI-assisted generation or annotation. We evaluate 28 general-purpose, science-oriented, chemistry-specialized, and embodied MLLMs in an offline, single-turn setting. Results show that current models can follow coarse experimental procedures in videos, but still struggle to ground actions into operable regions and feasible trajectories, to recognize fine-grained laboratory apparatus, states, and safety norms, and to order steps in mid-length procedures. BEAKER thus reveals a clear gap between coarse procedural understanding and the precise, action-grounded perception required for laboratory execution, providing a diagnostic benchmark for future MLLMs in SDCLs.

新论文 · v1arXiv:2611.06910

FrontierPhysics:评估面向端到端物理研究的智能体

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

Bingran You, Wenjun Ke, Ria Rosenauer, Bo Liu, Wenbo Chen, Min Chen, Shuqi Xu, Yue Ma 等 72 位作者

AI 速读 基于摘要

作者提出包含56个由物理学家基于自身研究设计的端到端物理研究基准,用确定性验证器与专家评分量表同时考察智能体研究的正确性与可发表性。

cs.AI

查看原文摘要

AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality alongside correctness. We introduce FrontierPhysics, an end-to-end benchmark with 56 tasks made by 42 physicists based on their own research, covering nine domains across theoretical, computational, and experimental physics. Each task requires agents to review the literature, develop a research plan, conduct research and experiments, and produce structured outputs and scientific manuscripts. Combining deterministic verifiers with expert-authored rubrics, FrontierPhysics evaluates whether agents' research is correct and publishable. Across 22 models in 26 configurations, no configuration passes more than 46 of its 168 rollouts. Manual review of agent trajectories shows that frontier agents' main weaknesses are insufficiently rigorous reasoning and limited expert intuition, rather than gaps in physics knowledge or execution errors.

新论文 · v1arXiv:2611.06908

从仿真中学习感知型人形机器人运动

Perceptive Humanoid Motion from Simulation

Siyuan Hu, Abulikemu Abuduweili, Yue Meng, Shipeng Liu, Quentin Leboutet, Chen Chen, Matthias Müller, Vladlen Koltun

AI 速读 基于摘要

提出 HALO 系统,用程序化生成的千套虚拟住宅合成视觉-语言-运动数据,训练人形机器人技能并零样本迁移到真实世界。

cs.RO · cs.AI · cs.CV · cs.LG

查看原文摘要

Humanoid robots have the potential to automate a wide range of physical tasks. Progress toward generalist humanoid autonomy, however, remains constrained by a data bottleneck: mapping pixels and free-form language to low-level joint commands requires paired supervision, and no corpus of such data exists at sufficiently large scale. Some approaches rely on human teleoperation and wearable capture devices, which require at least an hour of human time to produce an hour of data. We present HALO, a humanoid autonomy system powered by a pipeline that synthesizes vision-language-motion data across a thousand procedurally generated homes. The corpus scales with compute rather than human labor. HALO acquires a repertoire of physical skills, including sitting on chairs, navigating to named objects, stepping sideways through half-open doors, crouching and crawling beneath tables, and pushing boxes. It orchestrates these skills to solve composite, long-horizon tasks. Without ever seeing a real home during training, HALO transfers zero-shot to the physical world, achieving a 91% success rate across 360 trials in six unmapped real-world environments. See https://apple-aiml-research.github.io/ml-halo/ for code and videos.

新论文 · v1arXiv:2611.06906

一个有向可达性的简单次二次割查询协议

A Simple Subquadratic Cut Query Protocol for Directed Reachability

Henry Fleischmann, Sagnik Mukhopadhyay, Swagato Sanyal

AI 速读 基于摘要

作者提出一个简单的随机化算法蓝图,通过有向割查询在真正次二次查询复杂度内判定有向图 s–t 可达性,给出两种实现分别达到 Õ(n^{9/5}) 与 Õ(n^{5/3}) 查询上界。

cs.DS

查看原文摘要

We study $s$--$t$ reachability in an unweighted directed graph on $n$ vertices, accessed through a directed cut oracle: given $S\subseteq V$, the oracle returns the number of edges directed from $S$ to $V\setminus S$. Directed cut functions are submodular, and reachability asks whether the minimum $s$--$t$ cut has positive value. This connects the problem to the query complexity of submodular function minimisation. Whether or not reachability can be solved in truly subquadratic query complexity has been an outstanding open question for a decade. We give a simple algorithmic blueprint with two randomised implementations. The first uses $\widetilde O(n^{9/5})$ outgoing-cut queries; the second improves this bound to $\widetilde O(n^{5/3})$. The common idea is to construct an alternative orientation with the same underlying undirected graph and vertex-wise degree imbalances, thereby preserving reachability. We first approximate the target imbalances using an averaging and rounding procedure, then correct the remaining error with a flow. An earlier manuscript, made available in August 2026 in an online AI repository, reports an $\widetilde O(n^{3/2})$ query bound. Our contribution is a simple and comprehensible alternative approach that already achieves a polynomial saving over quadratic query complexity.

新论文 · v1arXiv:2611.06905

强化学习实现通用机器人策略的规模化改进

Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement

Michal Korniak, Marco Bagatella, Ralf Römer, Michal Nauman, Yarden As, Pranav Vignesh, Manan Agarwal, Leander Diaz-Bone 等 24 位作者

AI 速读 基于摘要

作者系统评估通用机器人策略能否在部署阶段通过在线强化学习实现多任务同时改进,并探索使该改进泛化到未训练任务的关键算法配方。

cs.LG · cs.RO

查看原文摘要

The introduction of generalist robot policies has enabled a single, large model to learn to perform a variety of tasks from a vast pre-training corpus. While these models often exhibit powerful zero-shot generalization capabilities, they typically require an adaptation phase to achieve sufficient performance in deployment. Iterated self-improvement via reinforcement learning (RL) has demonstrated promise in enabling this adaptation, yet such approaches have been largely explored in single-task settings - where the goal is to simply improve on a narrow deployment task - which lies in stark contrast to the multi-task capabilities of the base policy. In this work we ask whether generalist robot policies are capable of multi-task, generalist improvement in deployment - targeting many diverse tasks simultaneously - and what algorithmic recipe enables this. To answer this question, we first develop a set of structured evaluations to test generalist improvement capabilities, and systematically evaluate algorithmic and practical design choices regarding value estimation, policy extraction and resource allocation. We show that not only can generalist policies be improved online across diverse tasks, but that the right recipe can enable generalization and increase performance on tasks not considered during online training. We characterize when this generalization occurs and show that both the training task distribution and the use of value-based RL are critical. To the best of our knowledge, this is among the first evidence for online generalist improvement for robot foundation models.

版本更新 · v3arXiv:2606.11552

教扩散模型从左到右推测

Teaching Diffusion to Speculate Left-to-Right

Lexington Whalen, Yuki Ito, Ryo Sakamoto

AI 速读 基于摘要

通过三种训练期干预,缩小扩散草稿模型的双向生成与自回归目标模型从左到右验证之间的目标错位,从而提升推测解码的接受长度。

cs.CL · cs.LG

查看原文摘要

Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation. Speculative decoding addresses this bottleneck by employing a lightweight draft model to propose multiple future tokens that are subsequently verified in parallel by a larger target model. Recent work has demonstrated that diffusion language models are well suited for this setting, as they can generate entire blocks of draft tokens in parallel and thereby alleviate the sequential constraints of autoregressive drafting. A subtlety of this regime is that block-diffusion drafters generate tokens bidirectionally within a block, whereas verification is performed by an autoregressive target model that evaluates tokens in a strictly left-to-right manner, leaving a gap between the symmetric training-time objective and the asymmetric verification-time reward. In this work, we offer an empirical analysis of three training-time interventions that narrow this gap: token positional weighting, a first-error focal loss that targets the position that breaks the accepted prefix within each block, and a chain loss term that substitutes a differentiable surrogate for the expected accepted length. The three interventions act along orthogonal axes (position, block-conditional first error, joint prefix) and compose additively; they are likewise orthogonal to test-time alignment mechanisms such as multi-draft self-selection, with which they can in principle be combined. Across four target models and six reasoning, code, and dialogue benchmarks, the three interventions raise accepted draft length by 21-76% per benchmark over a position-uniform baseline, without adding additional forward passes and without changing the inference pipeline or the rejection-sampling exactness contract.

新论文 · v1arXiv:2611.06901

运动引导的对比正则化用于潜在世界模型

Motion-guided Contrastive Regularization For Latent World Models

Yiwen Chen, Qiqi Hou, Jisoo Jeong, Yinhao Zhu, Huaizu Jiang, Amir Said

AI 速读 基于摘要

针对JEPA式世界模型中的静态坍缩问题,提出用光流相似度构造软对比目标的运动引导对比正则化,以提升控制相关表征。

cs.CV

查看原文摘要

JEPA-style world models learn action-conditioned latent dynamics without reconstructing observations, but distributional regularization alone does not ensure that their representations preserve information needed for control. We identify static collapse, a failure mode in which the encoder preserves episode-specific static content while suppressing manipulation-relevant state changes. Because static content is temporally predictable yet diverse across episodes, this failure can persist despite regularizers such as SIGReg. A controlled study on OGBench-Cube shows that introducing randomized backgrounds substantially degrades planning performance while leaving the underlying manipulation task unchanged. To address this problem, we propose motion-guided contrastive regularization. Our approach compares predicted latent transitions with transitions to candidate observations from the same episode, reducing the usefulness of static background identity for distinguishing action outcomes. Optical-flow similarities provide soft contrastive targets, allowing candidates with similar motion to receive similar supervision. Combined with latent prediction and SIGReg, our objective encourages representations to preserve within-episode state distinctions and similarities between related transitions. Our method improves planning success over LeWorldModel (LeWM) from 52% to 78% on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while maintaining comparable performance on four other visual-control benchmarks.

新论文 · v1arXiv:2611.06899

免费遮挡检测:利用两种单目距离线索的分歧检测遮挡

Occlusion for Free: Detecting Occlusion from the Disagreement Between Two Monocular Distance Cues

Chibueze Praise Onyenweaku, Toyibat Adele, Sikirulahi Opeyemi Abdulkareem, Obed Honour Eje

AI 速读 基于摘要

作者提出一种无需训练、无需遮挡标注的遮挡检测分数,仅依赖相机管线已有的表观高度与单目度量深度两种距离估计的排序关系。

cs.CV · cs.AI

查看原文摘要

Knowing that a pedestrian is occluded is useful to a robot even when the detector cannot recover the hidden pixels, but occlusion estimators are normally trained on occlusion annotations that deployment settings rarely have. We show that occlusion can be read off two distance estimates a camera-only pipeline already computes. Apparent height is largely unchanged by occlusion, because the detected box still spans the whole person; monocular metric depth is pulled toward the occluder, because the nearest surface inside the box is what a depth map reports. Only their ordering matters, so no focal length, stature, or depth scale is needed, provided the depth model's error is close to a pure gain, a condition that can be checked without labels. The score detects heavy occlusion on KITTI with AUC 0.909 (0.888 over all annotated pedestrians, including those the detector misses), requires no training and no occlusion labels, and is not a proxy for range: within fixed distance bands it holds AUC 0.894-0.925 while true distance alone sits near chance. On synthetic CARLA scenes with measured visibility it reaches 0.819, against 0.644 for distance alone. We arrived here after measuring three standard architectural responses to occlusion, depth fusion, occlusion-simulating augmentation, and attention, none of which improved detection outside its training distribution in the configurations we tested, and after finding that a detector trained on German roads loses half its accuracy on self-annotated street scenes in Lagos, Nigeria. Signals that need no local annotation are worth more in settings that benchmarks do not represent.

新论文 · v1arXiv:2611.06996

Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity

Ahsan Habib Shihab, Imre Felde, Ramis Akhmedov, Stefan Gubo, Berik Sabdenaliyev, Madina Mansurova, Amir Mosavi

原文摘要

The policy that converts runtime estimates of an autonomous agent's condition into operational authority is rarely specified or measured. We empirically characterize the Trust Responsive Authorization Policy (TRAP), which maps an Authorization Readiness Score (ARS), a weighted combination of runtime trust, operational stability, and contextual risk, onto discrete authorization levels through an asymmetric rule: escalation requires consecutive observations above a band edge plus a margin, while a sharp drop in readiness restricts authority at once. On one matched set of 100 Monte Carlo traces, we compare TRAP with static, trust-only, risk-only, and symmetric policies. Under abrupt degradation, TRAP restricts at onset and re-escalates sooner after recovery than the symmetric policy, with the highest and, descriptively, least variable stability among the adaptive policies, although more of its post-recovery escalations occur below the selected trust threshold. Paired bootstrap intervals exclude zero for the remaining differences. In one-factor sweeps, recovery time rises with the escalation margin and run length, shifts with the score weights, and is unchanged by the restriction threshold. In an exploratory post-freeze experiment, when the same degradation is spread over 5-20 intervals, TRAP restricts only on the 4 traces that retain a single-interval drop above that threshold; averaged over all 100 traces, it holds authority above what readiness supports for 15.9-18.9 of the 20 degradation intervals, against 0.8 under abrupt degradation and about 10 for the symmetric policy. Its restriction advantage therefore depends on degradation being abrupt. All reported values are traceable to the publicly available, versioned research release.

cs.AI

新论文 · v1arXiv:2611.06897

MCP-Eco:MCP 服务器、消费者与开发活动的关联数据集

MCP-Eco: A Linked Dataset of MCP Servers, Consumers, and Development Activity

Khalid Tounoussi, Mohammed Sayagh, Ali Ouni, Yutaro Kashiwa

AI 速读 基于摘要

MCP-Eco 是一个关系型数据集,把 MCP 服务器接口、配置这些服务器的消费方项目及其开发活动记录关联起来。

cs.SE

查看原文摘要

The Model Context Protocol (MCP) enables LLM agents to access external tools and data. Studying its software ecosystem requires connecting server interfaces, the projects that configure these servers, and their development activity. However, this information is scattered across directories, package registries, configuration files, and repository histories. We present MCP-Eco, a relational dataset that integrates these sources and links consumer configuration declarations to candidate server projects. Its frozen release contains 16,880,899 records across 19 Parquet tables, covering 78,302 candidate server projects, 16,165 candidate consuming repositories, and 9,200 configuration declarations. Of these declarations, 5,975 resolve to 5,138 distinct repository-server pairs. The dataset also includes tool, resource, and prompt descriptions, declared dependencies, and associated development records, including pull requests, reviews, issues, and commits. Provenance fields distinguish directory-reported capabilities from those observed through live probing and document discovery sources and declaration-matching methods. These connections support research on MCP interface design, configuration practices, and repository maintenance, while enabling practitioners to inspect tool schemas and existing integration configurations. The dataset and accompanying analysis scripts are publicly available at https://huggingface.co/datasets/mcp-research-alliance/mcp-ecosystem Demo video: https://www.youtube.com/watch?v=N7TqnNneSfU

新论文 · v1arXiv:2611.06896

超越0.55的在线边加权匹配

Online Edge-Weighted Matching Beyond 0.55

Alireza Farhadi, Mohammad Hajiaghayi

AI 速读 基于摘要

作者提出一个0.556195竞争比的随机算法,用于带自由处置的边加权在线二分匹配,改进了Blanc和Charikar的0.5368保证。

cs.DS · cs.GT

查看原文摘要

We give a $0.556195$-competitive randomized algorithm for edge-weighted online bipartite matching with free disposal, improving the $0.5368$ guarantee of Blanc and Charikar. The result holds for arbitrary nonnegative edge weights and any input sequence fixed independently of the algorithm's randomness. Our algorithm builds on online correlated selection, introduced by Fahrbach, Huang, Tao, and Zadimoghaddam, and its multiway extension due to Blanc and Charikar. Our main contribution is a state-dependent primal--dual analysis of correlated selection. At each weight threshold, we track the state of the selection process jointly with an auxiliary failure event. The analysis accounts for arrivals below the threshold, which change the state without improving the matching value at that threshold. A potential function bounds the dual increase in both cases. We instantiate the analysis with an explicit win map that assigns a common score to an initial range of states. Its selection inequalities are verified by a finite computer-assisted proof covering every required candidate multiplicity and every real threshold; the verifiers are available in an accompanying repository. Triangular unit-weight inputs asymptotically attain the guarantee of the underlying ideal algorithm, proving that its analysis is tight.

新论文 · v1arXiv:2611.06895

学习时变连接组以实现发育过程中的稳定行为

Learning Time-Varying Connectomes for Stable Behavior Across Development

Christof Fehrman, Jacob J. Morra, Eva A. Naumann

AI 速读 基于摘要

作者报告,用单一紧凑生成编码(以发育时间为输入的CPPN)生成随年龄变化的循环控制器,可在显著发育变化下保持视运动行为稳定。

q-bio.NC · cs.NE

查看原文摘要

Neural circuits must maintain functionality to drive effective behavior while their size, topology, geometry, and intrinsic dynamics change across development. To model developing visuomotor circuits and behavior, we investigated whether a single compact generative encoding could produce functional recurrent controllers across such changes. Building on the HyperNEAT algorithm, we represented this program as a compositional pattern-producing network that received developmental time as an input to generate age-specific connectivity. The developmental substrate prescribed neuronal birth, position, sensory organization, and intrinsic time constants. We tested this approach using two geometrically distinct developmental substrates and two visuomotor tasks: optomotor responses and phototaxis. Controllers optimized at only the initial or mature substrate generally failed when evaluated at other ages. In contrast, controllers optimized across multiple developmental snapshots maintained substantially higher and more consistent performance across trained and unseen ages. Optimization at only three developmental snapshots was often sufficient to produce effective behavior across the tested developmental interval. The resulting connectomes changed substantially with age and did not converge on a single trajectory of sparsity or connection-weight statistics. Controllers also differed in whether they relied on neurons born later in development. These results demonstrate that a shared spatiotemporal time-varying connectivity program can produce recurrent neural networks that preserve behavior across substantial developmental changes. Together, these results provide a framework for studying how functional stability can emerge without requiring structural or dynamical stability.

新论文 · v1arXiv:2611.06894

非均匀批量购买网络设计:改进的近似算法与LP整性间隙

Nonuniform Buy-at-Bulk Network Design: Improved Approximation and LP Integrality Gap

Iman Gholami, MohammadTaghi Hajiaghayi

AI 速读 基于摘要

针对非均匀买断-租用网络设计问题,作者提出确定性多项式时间O(log²h/(loglog h)²)近似算法,并给出自然仿射多商品流LP的相同整性间隙上界。

cs.DS

查看原文摘要

In nonuniform buy-at-bulk network design, we are given an undirected graph and $h$ terminal pairs with positive demands, and we must route every demand at minimum total cost when each network resource has two independent parameters: a fixed buying price paid once if the resource is used, and a per-unit rental cost (or physical length) paid proportionally to the traffic it carries. Unlike the uniform-cost or single-sink variants, the general multicommodity problem allows unrelated buying and rental metrics across arbitrary source--sink pairs, arbitrary demands, and both edge and node resources. We give a deterministic polynomial-time $O(\log^2 h / (\log\log h)^2)$-approximation algorithm for undirected nonuniform buy-at-bulk network design. The guarantee holds for edge costs, node costs, and their combination, and applies to arbitrary positive rational demands with no dependence on the number of vertices or the numerical demand ratio. This improves upon the $O(\log^4 h)$ bound of Chekuri, Hajiaghayi, Kortsarz, and Salavatipour (2010) for unrestricted instances. Our result also establishes the same $O(\log^2 h / (\log\log h)^2)$ upper bound on the integrality gap of the natural affine multicommodity flow LP, bounding integral buying and rental costs separately against their fractional counterparts and preserving zero rental budgets exactly.