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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 19:38 — 2026-11-16 19:38(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 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 76 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2606.26289

Augmentation with Dilution? A Large-Scale Empirical Study of Human Contributor Ecosystems After AI Coding Agent Adoption

Weixing Zhang, Bowen Jiang, Tianhai Liu, Jialong Li, Anne Koziolek

原文摘要

AI coding agents are rapidly proliferating in open-source software development, and the long-term sustainability of open-source projects is closely tied to the health of their human contributor ecosystems. Yet most existing studies treat human contributors as a static backdrop, and the available evidence on human participation after agent adoption mainly concerns newcomer outcomes. This paper takes the human contributor ecosystem as its dependent variable. To the best of our knowledge, it is the first study to estimate how agent adoption changes the number of distinct humans behind each pull request, and to relate this change to agent pull requests recorded under developer accounts. Using the AIDev dataset, GitHub API scanning, agent-trace screening, and two-stage propensity score matching, we construct a balanced panel of 2,246 treated and 3,798 control repositories from January 2023 to May 2026, and estimate effects with the Sun-Abraham estimator for staggered difference-in-differences, event studies, and HonestDiD sensitivity analysis. AI agent adoption is associated with a decline in human contributor density of 0.019 to 0.048, about 4-10% of its pre-adoption level, depending on the reference month (both p < 0.01); because this estimate tolerates only small violations of parallel trends, we regard it as suggestive evidence. The share of newcomers shows no detectable change (ATT = -0.009, p = 0.28), with the 95% confidence interval ruling out a decrease of more than 2.4 percentage points. Whether the decline in density is associated with agent pull requests recorded under developer accounts remains inconclusive (high minus low share: -0.013, 95% CI [-0.083, 0.057]). These findings are consistent with a pattern of augmentation with dilution: we detect no decrease in the share of newcomers, but each human contributor appears to correspond to more pull requests.

cs.SE

新论文 · v1arXiv:2611.08721

Remembering Is Not Enough: Evaluating Timing and Omission in Longitudinal AI Mental Health Support

Eli Min, Mohit Chandra, Aamogh Sawant, Mengting Tu, Freya Lin, Ridwan Shams Khan, Reigna El-Yashruti, Christopher L. Smith 等 11 位作者

原文摘要

Evaluations of large language models (LLMs) for mental health support commonly focus on the clinical appropriateness of individual responses, potentially overlooking failures that emerge across extended interactions. As AI assistants accumulate memory of users' circumstances and prior disclosures, this raises an accountability question: Do AI chatbots provide appropriate support as users' needs evolve? We investigate by analyzing 14,256 longitudinal simulations grounded in donated chatbot histories from 22 users, examining how a memory-equipped assistant responds to suicidal ideation, self-harm, and anxiety crises across recovery trajectories and communication styles. We introduce the Context-Aware and Readiness-Evaluative (CARE) framework, developed with mental health professionals, to assess the timing and quality of advice, including omissions. Advice was less aligned with users' readiness after a crisis than in matched control stretches of the same conversation, largely because of premature recommendations, which were most common when recovery stalled. Revisiting a crisis reduced premature advice but not lagging advice, and users' communication style changed how often and when the assistant gave recommendations. Although explicitly unproductive advice was rare, the assistant frequently omitted clinician-expected support such as follow-up and planning for next steps. These findings show the limits of single response-level safety evaluation and the need to assess timing, omission, and consistency across users when holding AI systems accountable for longitudinal support.

cs.CY · cs.AI

新论文 · v1arXiv:2611.08428

元访问的力量:面向未来软件的演示——以LLM聊天界面与Chat AI为例

The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI

Julian Kunkel, Ali Doosthosseini

AI 速读 基于摘要

提出“元访问”概念,让LLM助手获得对界面自身结构化、受权限约束的访问能力,并以Meta Chat原型演示聊天客户端如何成为整个工作区的控制层。

cs.AI

查看原文摘要

Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation. Yet the model sees the current dialogue but not the workspace around it. We explore meta access---giving the assistant a structured, permissioned view of the interface itself and propose a ladder of levels: feature tutoring; metadata, settings, and preference access; retrieval over summaries and messages, confirmed mutation, and full orchestration. Meta access can turn a chat client from many screens into one entry point for finding, navigating, organising, and operating it, while raising risks around grounding, privacy, prompt injection, and trust. General-purpose agentic harnesses are runtimes; because they can change their own settings, meta access becomes reflexive and needs a separate control-plane boundary. We ground this in the Meta Chat prototype of the Chat AI client. It builds bounded context from, e.g., summaries, settings, and relevant messages; links references to conversations, topics, and personas; supports confirmed, reversible changes; offers a browsable tutorial library; and recommends personas as user-started conversations. By exposing application state in structured form, meta access can extend screen readers from widget descriptions to semantic workspace operations. Meta access thus turns chat from a window onto one conversation into a control layer for the whole workspace, extending chat toward agentic capability without surrendering user control. As assistants become embedded in IDEs, dashboards, office suites, and operating systems, AI-era interfaces should expose a structured, permissioned model of their state and capabilities, ideally by opening their existing metamodels through a debugger-like interface.

新论文 · v1arXiv:2611.08417

基准即软件:Terminal-Bench 与持续基准测试的必要性

Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks

E. Kelly Buchanan, Crystal Zhou, Scott W. Linderman, Christopher Ré

AI 速读 基于摘要

作者提出“基准维护债务”概念与持续验证工作流,并在 Terminal-Bench 2.0 审计中修复约30%的问题、发布 2.1 版本,说明资源预算也是测量规范的一部分。

cs.AI

查看原文摘要

Coding agents are among the most economically consequential deployments of LLMs to date, making reliable evaluation increasingly important. Yet even benchmarks that are carefully validated at release can become stale. As models improve, they can discover valid solutions that existing verifiers reject, while changes to evaluation infrastructure can invalidate assumptions embedded in tasks and tests. We call the resulting accumulation of defects benchmark maintenance debt: a growing gap between benchmark scores and the capabilities they are intended to measure. We introduce a continuous-validation workflow for agentic benchmarks that combines community reports, task artifacts, agent traces, automated oracle checks, and human-gated repairs. We apply this workflow to Terminal-Bench 2.0, a benchmark that underwent extensive human and LM-assisted review and red-teaming before release. Our audit identifies issues in roughly 30% of the benchmark, and we release the resulting repairs as Terminal-Bench 2.1. These repairs change evaluation results: accuracy increased by over 10 percentage points and leaderboard positions move by up to three ranks, even as the overall ranking remains highly correlated (Spearman rho = 0.958). We evaluate how resource allocation shapes benchmark conclusions. We show that fixed wall-clock can materially change agent performance: For example, extending the time limit closes a 20pp harness gap on GPT 5.4 and shrinks a 30 pp gap on GPT 5.4 mini to 5 pp. Benchmark maintenance is therefore not only about repairing task artifacts: resource budgets are part of the measurement specification and must be validated alongside the tasks themselves. More broadly, benchmark maintenance debt is not just accumulated implementation bugs: our results show that as models improve, both evaluation assumptions and resource settings may need to be revalidated.

新论文 · v1arXiv:2611.08568

Personalized health coaching via coachable health age and counterfactual wearable trajectories

Simon A. Lee, Zeinab Esmaeilpour, Menglian Zhou, Marius Guerard, Sohrab Sidhu, Alexandru Solot, Hamid Palangi, Pramod Rudrapatna 等 20 位作者

原文摘要

Personalized health coaching requires moving beyond retrospective wearable summaries toward quantitative, actionable behavioral prescriptions. We introduce Coachable Health Age (CHA), an interpretable health-age metric built from modifiable physiological and behavioral signals passively captured by consumer wearables. Across the WEAR-ME (N=2,780), All of Us (N=22,748), and longitudinal Fitbit (N=1,464) cohorts, CHA aligns with established cardiometabolic health constructs and improves prognostic discrimination for incident cardiovascular and metabolic disease beyond age, sex, and body mass index. To enable prospective behavioral optimization, we developed Sensor World Model (SensorWM), an action-conditioned wearable world model pretrained on over 2.2 million person-weeks of longitudinal sensor data from approximately 100,000 participants. SensorWM accurately forecasts multi-week physiological responses to candidate lifestyle changes ($R^2=0.664$), outperforming generic time-series foundation models while preserving downstream clinical signal for diabetes, hypertension, and other health outcomes. Finally, we integrate CHA and SensorWM into an agentic counterfactual coaching system to synthesize personalized 12-week coaching plans. In blinded paired reviews, certified lifestyle coaches preferred counterfactual-grounded plans over plans grounded in wearable history alone for overall quality (71.4%, P < 0.001) and anticipated adherence (71.0%, P < 0.001), and board-certified clinicians judged 99.2% of counterfactual-grounded plans to meet clinical safety criteria (vs. 97.6% of comparison plans). Automated evaluations across the full cohort (N=2,780) also favored counterfactual-grounded plans. By closing the loop between longitudinal tracking, trajectory prediction, and counterfactual coaching, our framework provides a scalable path to systematically improve cardiometabolic health.

q-bio.QM · cs.LG

版本更新 · v2arXiv:2610.12532

LLM驱动音色生成与插值中的结构与表征能动性

Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation

Joseph Cameron, Alan Blackwell

AI 速读 基于摘要

在一项LLM驱动音色界面的测量研究中,作者报告用户实际能改变的声音空间与界面所报告的位置可以分离:前者由结构精确刻画,后者存在显著误差。

cs.SD · cs.HC · cs.LG · cs.MM · eess.AS

查看原文摘要

Generative creative interfaces routinely report the user's position within a space of possibilities. Such displays imply that the quantities shown were measured from the artefact; in a growing class of systems they are instead predicted by a language model describing its own output, and the two are indistinguishable on screen. Most creative domains lack an agreed measurement against which such a self-report can be checked; audio admits one. In a measurement study of a working LLM-driven timbre interface, what a user can cause proves separable from what the interface reports. The first is exactly characterisable: the reachable set is a zonotope in parameter space whose dimension increases by one per sound placed, so the space the model may act within is demonstrably the user's own. The second is inaccurate. The displayed position differs from measurement by approximately three times the width of that region, and the error has two independent sources: model-predicted coordinates, whose accuracy varies twofold between the two models evaluated, and the interpolation step, which arises from combining synthesiser parameters and is unaffected by model quality. End to end, 27 of 36 refinement instructions produced no perceptible change, and under the weaker model the facility performed no action while reporting convergence. Effective agency (what a user can cause) and epistemic agency (whether they can know it) are therefore separable and independently engineered: structurally enforced constraints survive model failure, whereas guarantees resting on the model's own report do not. The failure mode that remains is silence presented as success. We close with a short protocol for building and auditing such displays.

新论文 · v1arXiv:2611.07984

Technohybridism: Recursive Semantic Normalization in AI-Mediated Societies

Charalampos M. Liapis, Epameinondas Panagopoulos

原文摘要

Language-generating AI systems are no longer only objects of linguistic interaction: their outputs increasingly re-enter the communicative and institutional practices from which their training material was drawn. Drawing on social theory, social epistemology, and the philosophy of language, this article develops a sociotechnical account of that re-entry. We introduce recursive semantic normalization: the process through which machine-generated formulations, once recurrently taken up, evaluated, reused, and institutionally retained, participate in the reproduction and transformation of semantic regularities. Under the heading of technohybridism, we argue that the relevant unit of analysis is the hybrid semantic system, a recursively coupled configuration of human practices, computational generation, and institutional uptake. First, we distinguish the concept from neighbouring accounts, including model collapse, looping effects, machine habitus, machine culture, and the epistemology of AI testimony. Second, we develop an analytical model that separates generation, selection, uptake, and persistence and distinguishes machine-attributable change from change that would have occurred anyway. Third, we analyse uptake as routinized, institutionally diffused, and socially stratified practice and state conditions under which machine-derived regularities become norms. Fourth, we identify social-epistemic consequences: the laundering of provenance that weakens epistemic vigilance, the erosion of the cognitive diversity on which collective inquiry depends, and the narrowing of shared hermeneutical resources. An evidential ladder for empirical research follows. The account attributes no normative authority to machine outputs; what changes is the field within which human and institutional uptake operates.

cs.CY · cs.AI · cs.HC

新论文 · v1arXiv:2611.05720

Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis

Yanru Xiao, Yingwei Yu

原文摘要

Search can help LLM agents correct mistakes, but their starting conditions may shape which evidence they find and use. Drawing on cognitive-bias paradigms, we develop a controlled search harness to examine result order, records of prior work, and initial hypotheses while holding each question and document collection fixed. Matched controls distinguish order effects from differences in document composition and the effects of failed work from context length. Across 10 models and 1,000 synthetic search worlds, we track queries, retrieved documents, document openings, and final answers. Our comparisons suggest that final answers are more sensitive to initial evidence order during active search than when all evidence is supplied in full. Dead-end histories can reduce strategy switching relative to matched neutral histories, indicating an effect beyond context length. Under wrong hypotheses, stage measurements distinguish reduced retrieval or opening from errors that persist after counter-evidence is opened. Exploratory interventions show that opening counter-evidence more often can coincide with lower accuracy, while accuracy can improve with little change in opening.

cs.CL

版本更新 · v2arXiv:2611.03576

NitiBench+:跨17个领域的泰国法律时序问答基准

NitiBench+: A Temporal Thai Legal Question Answering Benchmark Across 17 Domains

Pawitsapak Akarajaradwong, Sarana Nutanong, Chompakorn Chaksangchaichot

AI 速读 基于摘要

作者构建了包含1,670道题、覆盖17个领域的泰国法律问答基准NitiBench+,为每个被引法条同时保留判决日有效文本与现行文本,并据此评估模型在正确法律文本下的表现。

cs.CL

查看原文摘要

Law changes over time. A court decides a case under the law in force on that day, and legal QA benchmarks grade answers against today's law. We checked 156,650 decisions of four Thai courts. Up to 67% of them cite law that has since been amended or repealed. We introduce NitiBench+, the sequel of our NitiBench, a Thai legal QA benchmark with 1,670 items across 17 domains, built from decisions of three courts. For each cited section it holds both the text in force on the decision date and the current text, and its retrieval corpus holds every dated version of every Thai statute section. Answers are graded on the Thai Bar Council rubric, the Bar-standard score, and on the overlap between the cited sections and the court's. The report has two parts. Part I measures the cost of the wrong text on 13 open-weight models. Reading the current text of amended law drops the Bar-standard score by 0.25 and missing repealed law drops it by 0.79. The penalty comes from rule changes, 0.45 on the 428 rule-changed items and none on the 331 wording-only items, and Citation F1 does not see it. The text in force is the fair setting. Part II benchmarks today's models on that setting. A public leaderboard ranks 26 models on a held-out test split of 500 items stratified by domain, with a validation split of the same shape released for public use, from memory alone, with the court's sections provided, and as a retrieval agent over the law in force, with the cost per item and the hallucinated citations. The best model scores 7.78 out of 10 and the best open-weight model 6.39. Without a search tool only five open-weight models recall any Thai law, and with it twenty of the 26 models gain and six lose. Leaderboard will take new models as they are released. Legal benchmarks must track dates, and on the right text today's models still leave a wide gap on Thai law.

版本更新 · v2arXiv:2611.02978

CAREFUL-Bench: Effect-Aware, Judge-Free Evaluation of Multi-Turn LLM Function Calling

Alexander Kovalenko, Artem Redchych

原文摘要

The multi-turn checker of the Berkeley Function Calling Leaderboard (BFCL) checks only the final state of a simulated service, never the calls that produced it. Extra calls cost nothing, no function doc says what a function does, and the scripted user never answers a proposal, so a model that asks before deleting or paying fails the turn; 322 of the 734 reference turns in the base category act destructively without confirmation. We add effect information to BFCL without replacing it. Effect declarations for all 128 functions are inferred by executing each function in BFCL's own simulators and diffing the state; the remaining judgment, which writes are destructive, is made by four annotators, two humans and two language models (Fleiss' kappa = 0.75), and adjudicated. A judge-free replay scorer re-scores any logged BFCL run, reproduces BFCL's results on all 800 reference trajectories, and reports, alongside the official score, unrequested destructive calls, duplicate writes, redundant reads, surplus steps and their token cost. A confirmation-aware protocol adds a deterministic user that answers proposals. On 11 open models the effect-aware score preserves the official ranking (rho = 0.99) but changes the gaps: the leader loses 14.0 points to unrequested destructive calls, and surplus steps account for 2-28% of all input tokens. Effect hints in the function docs produce no measurable change for any of eight models, consistent with their advisory status in the Model Context Protocol. A user that answers recovers up to four points for the models that ask and none for the rest, with every comparison paired on the same conversations. The gains come from clarifying questions rather than requests for permission: of the 712 conversations that require a destructive call, no model completes more than 6 with every such call confirmed, a difference the official score does not record.

cs.AI · cs.SE

版本更新 · v2arXiv:2609.09986

A Sharp Barrier of Consistent Submodular Maximization: Any Improvement over $2-\sqrt{2}$ Entails Exponential Queries or Linear Recourse

Shi Fu, Qixin Zhang, Dacheng Tao

原文摘要

Consistent submodular maximization aims to maintain a high-utility subset of size at most $k$ as new elements arrive one by one, while changing only a limited number of elements per update. Previously, [DFL+25](STOC '25) established an information-theoretic bound of $2/3$ and gave the first polynomial-time randomized algorithm with a $0.51$-approximation guarantee. However, a fundamental question remained open: Is it possible to design an efficient algorithm for consistent submodular maximization that matches the classical offline $(1-1/e)$-approximation? In this paper, we answer this question in the negative by proving that the sharp approximation threshold achievable with polynomially many value queries and worst-case constant recourse is \[β:=2-\sqrt{2}\approx0.5858<1-1/e.\] Specifically, we develop an improved poly-time randomized algorithm, which can attain a $(β-\varepsilon)$-approximation in expectation at each fixed time with $O(\varepsilon^{-2})$ worst-case recourse. The cornerstone of this algorithm is a novel anchored sampling scheme, which uses only value queries on subsets of the elements seen so far to construct a solution that remains competitive under unknown future arrivals. Conversely, we establish a matching lower bound by showing that any fixed improvement over $β$ requires either exponentially many value queries or $Ω(k)$ changes per update. Furthermore, we characterize the impact of curvature by establishing a sharp threshold of $1-(\sqrt{2}-1)\vartheta$ for consistent submodular maximization, where $\vartheta\in[0,1]$ denotes the total curvature. Surprisingly, for weighted coverage objectives, we devise a poly-time randomized algorithm that can match the optimal $(1-1/e-\varepsilon)$-approximation with $O(\varepsilon^{-1})$ worst-case recourse, thereby separating coverage maximization from general submodular maximization in the consistent settings.

cs.DS · cs.LG

版本更新 · v2arXiv:2607.20827

Auditing Provenance Sensitivity in LLM Agent Action Selection

Junchi Liao, Qiang Huang, Rui Qian, Xutao Mao, Juntao Cheng, Kangning Cui, Yu Li, Jingyu Sun 等 9 位作者

原文摘要

LLM agents choose tools and arguments from context that mixes user requests, tool outputs, retrieved records, memory, and untrusted text. Evidence can be relevant without being authorized to determine a decision, so a correct action need not be grounded only in permitted evidence. We introduce a target-specific authorization audit that labels context factors separately for each tool and argument target. Its primary test holds the task, proposition, position, and policy fixed while changing only the proposition's source authority. We then test behavior when valid evidence is weakened and use context-subset interactions as a secondary localization diagnostic. Across 450 controlled next-action tasks and multiple open-weight LLM families, trusted and untrusted variants produce different actions in 5.4 percent of competing cases versus 1.7 percent of supporting cases. Under controlled degradation, unauthorized competition is retained in a full-correct, mixed-error, clean-correct pattern in 2.4 percent of comparisons, with a 95 percent confidence interval from 2.1 to 3.0 percent. These are controlled stress-set rates, not deployment prevalence. The models respond to textual source-authority cues, but this does not prevent untrusted evidence from influencing their actions.

cs.AI

新论文 · v1arXiv:2611.03964

Ermakov--Based embeddings as a parameter-free layer for physics-informed neural networks

Roberto Bernal-Jaquez, Roberto Romero Huerta, Alexander Schaum

原文摘要

Evolution equations with time-dependent coefficients force a neural solver to spend capacity on a scale that the equation already determines. We show that a single classical object, the Ermakov-Pinney scale function $ρ$, can be written into the input layer of a physics-informed neural network as a parameter-free embedding. One construction covers three problem families through the two signs of the Pinney constant $c$: linear diffusion ($c=-1$, $ω\equiv0$), diffusion in a time-dependent confining trap ($c=-1$, $ω\neq0$), and the quantum oscillator with time-dependent frequency ($c=+1$). An exact moment identity gives $ρ$ in closed form from the initial data alone, so no auxiliary network or knowledge of the solution is needed. Our central finding is comparative: each family requires a different component of the construction and has a different honest control. In family I, the diffusive-time reparametrisation alone reproduces most of the gain, so that family is a poor test of the idea and shows why an ablation is mandatory. In family II no time reparametrisation exists, the control degrades accuracy, and the amplitude prefactor becomes essential (40.8x). In family III the adiabatic approximation also fails, and the quadratic phase factor is what matters (5.7x). The method does not help when the reduced solution does not converge to a fixed point: its extrapolation advantage then disappears. The reduction itself is the classical scaling-variable change of the self-similar-asymptotics literature; what is new is the moment identity that makes it architectural for time-dependent coefficients, and the comparative anatomy above.

cs.LG

新论文 · v1arXiv:2611.03222

CERBO: Certified Recourse at a Requested Rate for Gradient-Boosted Trees

Farhan Shahriyar Hossain, Taufikur Rahman Fuad, Md. Zarif Bin Hasnat, Md Abrar Jahin, Md Rizwan Parvez

原文摘要

Recourse-aware learning trains models so that people who receive an adverse decision can reverse it with an affordable change. For gradient-boosted decision trees (GBDTs), the existing method, RABIT, exposes a single recourse weight whose effect on the recourse rate is abrupt and data-dependent, and its training bound cannot certify recourse for any rejected individual. We present Certified Recourse Boosting (CERBO), which takes a requested recourse rate and returns a GBDT with certified actions: it tracks exact additive effort along tree paths, trains against committed boxes (a family of bounds that contains RABIT's and certifies a within-budget action for each training sample) and adjusts the weight after every tree until the certified rate meets the request. A calibration step guarantees the rate on new individuals, and the certifier runs on any tree ensemble, including XGBoost and LightGBM, in milliseconds per person without a solver. In RABIT's own experimental protocol, at equal accuracy, CERBO raises the recourse ratio from 0.90 to 0.99 on FICO and from 0.64 to 0.77 on Bail. Under additive costs on six data sets, it raises the area under the accuracy-recourse frontier in all 12 settings, and in simulated deployments it guarantees recourse to 70% of rejected individuals in 11 of 12 settings, against 2 for RABIT.

cs.LG · cs.AI · cs.CY

版本更新 · v2arXiv:2609.02171

Progressive Pseudo-Label Optimization for Point-Supervised Change Detection

Hailong Ning, Hao Wang, Yimeng Wang, Tao Lei, Renwei Dian, Asoke K. Nandi

原文摘要

Point-supervised change detection (PS-CD) aims to identify pixel-level changes between bi-temporal images using only sparsely annotated points. Although point annotations substantially reduce labeling costs, their limited spatial coverage often results in incomplete and noisy pseudo-labels. To address this issue, we propose a two-stage framework that introduces SAM2 priors into PS-CD and progressively adapts them to the target task. In Stage I, SAM2 generates object-aware candidate masks from point annotations on the bi-temporal images, and a bi-temporal mask selection strategy is designed to convert generic segmentation responses into more reliable change pseudo-labels. Subsequently, a lightweight CNN refinement module with an uncertainty-aware loss is employed to improve boundary quality and local structural consistency. In Stage II, we construct a teacher-student self-training framework in which the teacher is updated by exponential moving average and periodically refreshes the pseudo-labels. This design establishes a closed-loop optimization process that alternates between pseudo-label refinement and model re-optimization. Experiments on three benchmark datasets, including WHU-CD, LEVIR-CD, and SYSU-CD, demonstrate that the proposed method outperforms previous weakly supervised approaches on most benchmarks and remains competitive with several fully supervised methods.

cs.CV

新论文 · v1arXiv:2611.02484

Benchmark of THReD: Evaluating an LLM Agent and Its Preprocessing Tools for Turning Electronic Health Records into AI-Ready Datasets

Javad Mohammad Alizadeh, Huanmei Wu

原文摘要

LLM agents are increasingly built into data-analysis software, yet little evidence shows how reliably they preprocess clinical data or whether the tools they invoke give correct, reproducible output. We report a benchmark of THReD, a web-based system that turns electronic health record (EHR) extracts into AI-ready datasets through a chat agent whose proposed steps run only after user confirmation. The agent benchmark has 141 tasks (100 templates) in seven categories, including goal-level requests, failure recovery, requests calling for no action, schema variation and prompt injection through the data, on synthetic tables calibrated to a regional health information exchange; success is judged by checks on the produced data. Over 2,550 episodes with Claude Haiku 5.5 in four context configurations, the deployed agent completed 92.7% (95% CI 88.1-96.4) of tasks on its first answer, abstained on every advice request, recovered from every injected fault, and never proposed an action requested by planted text. Without the data profile, completion fell to 58.0%; goal-level requests were hardest (80.6%). Six experiments on real records of two chronic-disease cohorts and on synthetic data at scale validate the tools: 91-92% of inferred patient classes and 99.7-99.8% of inferred vital-sign labels were correct in masked reconstruction; a dictionary builder combining curated dictionaries with LLM suggestions mapped 99.0% of 2,208 raw variants correctly; all 2,176 replays of 128 saved pipelines gave byte-identical files under pinned dependencies; subgroup differences in inference accuracy vanished within facility and lookup key; and the same-day consolidation rule changed 90-day emergency revisit rates by up to 3.2 points without shifting cohort composition by more than one point. Processing time grew roughly linearly to 5.5 million records while the prompt stayed at about 13 thousand tokens.

cs.AI

新论文 · v1arXiv:2611.02452

Adjustment control usability and dynamic accommodation in office chairs: A comparative study of two contemporary designs

Yejin Kang, Dusan Baek, Dongwoo Park, Kitae Hwang, Woojin Park

原文摘要

Adjustability is a core determinant of ergonomic fit in office chairs, but its benefits depend on users being able to operate the controls and, on the chair, continuing to support the body as posture changes during work. We compared two high-end office chairs, the T90 (Sidiz; Chair A) and the Aeron (Herman Miller; Chair B), in two experiments to explore which design features may explain differences between them. In Experiment 1, 20 participants adjusted ten controls common to both chairs and rated perceived adjustment difficulty on four items. Chair A had significantly lower overall difficulty (Wilcoxon signed-rank test, p = 0.008), with control-level advantages for headrest angle, armrest height, armrest rotation angle and lumbar support position; Chair B was easier for seat height, possibly because its side-mounted lever is more visible than Chair A's underside button. The headrest comparisons involved a third-party headrest fitted to Chair B, and control- and item-level tests were not corrected for multiple comparisons. In Experiment 2, the same participants completed a 15-minute multi-device task requiring repeated posture changes, reach and reorientation, then rated body-part discomfort, general comfort and satisfaction with five components. Discomfort and comfort did not differ; Chair A had higher satisfaction for the seat-pan and lumbar support (exploratory, uncorrected). Interviews suggested links to mechanism properties: Chair B's rear lumbar dial was often described as producing little perceptible change, and for controls without significant differences each chair appeared to leave a different aspect of the same need unmet. These findings suggest mechanical and interface properties that designers of adjustable office chairs may consider for dynamic, multi-device work.

cs.HC

新论文 · v1arXiv:2611.02437

Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm

Amindu Kumarasinghe, Vinh Bui, Reza Ghanbarzadeh

原文摘要

Skin cancer classifiers need large sets of annotated images, which are scarce, especially for rare lesion types. AI-generated images can fill the gap, but a generator produces images of widely varying quality, so selecting which images to retain is important. That choice usually rests on a single quality score, most often the Fréchet Inception Distance (FID), which has not been tested against what a classifier needs and cannot tell whether the generator memorizes its training photographs. We test that practice with a tournament of 16 quality metrics. Each metric alone selects a training subset from a pool of 275,472 images generated by a diffusion model (EDM2), and a classifier trained on each subset scores the metric per class. The tournament shows that no single metric serves every class: FID computed on Inception features gives the best classifier for one lesion type and no measurable advantage over random sampling for another, and the generation setting it prefers is also the one closest to the training images. We turn these per-class measurements into a safety-aware evaluation algorithm that weights each metric by its measured value in each class and removes images too close to a real training image. On the held-out ISIC-2018 test set, the algorithm improves Macro-$F_2$, a recall-weighted measure of classification performance, over the FID baseline for a Swin-B classifier by +0.0136 to +0.0164 across four safety thresholds (Bonferroni-corrected $p < 0.02$) and over random sampling by about +0.03, though not for ResNet-50. Tightening the threshold improves a memorization-safety score with no measurable change in utility, but every curated set remains less safe than random sampling. The results show a modest but statistically significant gain on the primary classifier, and offer a practical, safety-aware procedure for evaluating and using synthetic data.

cs.CV · cs.LG

版本更新 · v2arXiv:2609.13890

Learning How Much to Collaborate: Difficulty-Aware Topology Selection for Multi-Agent Code Generation

Yunsong Hong

原文摘要

Multi-agent code-generation systems often use one communication topology for every problem. Across five topologies and 614 problems from APPS, HumanEval+ and LiveCodeBench, the advantage of hierarchical collaboration over a single agent grows from 2.4 points of pass@1 on the easiest third to 21.1 points on the hardest third, at about ten times the token cost. We propose the Difficulty-Aware Topology Selector (DATS), which predicts each topology's success probability and maximises predicted success minus cost. Its graph predictor treats topologies as nodes of a connectivity order. The complete graph-head comparison reports a 1.7-point advantage over a flat multi-label head while changing several mechanisms; capacity-matched adjacency controls show smaller descriptive differences. A scalar cost penalty can be recalibrated without retraining for approximately matched-spend comparisons when targets are attained. With a shared penalty, six methods span 21.6 percentage points of spend; two leading baselines fall behind DATS after method-specific calibration near the common target. At 40% of always-hierarchical cost, DATS reaches 77.7% pass@1 versus 73.6% for always-hierarchical and 74.3% for the strongest learned competitor. The main comparison includes Holm--Bonferroni-adjusted McNemar tests; unequal-cost differences do not imply matched-budget superiority. Backbone-specific gains are 4.07--4.23 points across four backbones. Alternatives to the 39 interpretable features, including a hybrid encoder, yield a largest observed gain of 1.3 points, with no significant pairwise improvement; this establishes neither equivalence nor an upper bound. A study on 400 mathematical reasoning problems reproduces difficulty-dependent collaboration gains, widening from 2.5 to 20.9 points.

cs.MA · cs.SE

新论文 · v1arXiv:2611.01815

When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?

Anton Hristov, Aleksandar Slavov, Vasil Vasilev

原文摘要

Prediction errors from video world models are often treated as physical surprise, but they can also reflect appearance, static content, motion, or ordinary prediction difficulty. We present an evaluation framework that separates what frozen representations contain, how they organize appearance and physical differences, and what changes a model's own prediction error. On IntPhys2, a benchmark of physically possible and impossible events, we compare representations from latent prediction, masked pixel reconstruction, and simple visual statistics. Appearance remains easy to decode, while V-JEPA2 exposes modest information about whether events are possible or impossible. Looking at the latent geometry, appearance changes become smaller compared with differences between videos, their directions line up more consistently across scenes, and their overlap with physical changes decreases in deeper layers. Across action-conditioned models, incorrect actions raise prediction error, while appearance changes also produce substantial responses. In Physion++ video clips, repeating a single frame can produce higher error than the original clip, while changing color throughout the clip can lower it. Using Kubric, a simulation and rendering framework, we find that impossible events can produce lower error than possible events. A fixed error threshold also incorrectly flags many possible events as impossible. A model can therefore represent physical information and respond to incorrect actions without its native prediction error reliably measuring physical surprise.

cs.CV · cs.LG

新论文 · v1arXiv:2611.01234

How Much Can Approximate Equilibria Change the Social Cost of Selfish Routing?

Yu Cheng, Tianle Jiang

原文摘要

We study approximate Nash equilibria in nonatomic congestion games, with the goal of understanding how much the social cost can change when the equilibrium condition is relaxed. We consider $ε$-approximate Nash equilibria ($ε$-NE), in which each player uses a strategy whose cost is at most $1 + ε$ times the minimum available cost. We compare the social costs of $ε$-NE and exact Nash equilibria. This lets us quantify, for example, how much a navigation app can reduce total travel time when drivers tolerate routes slightly slower than the fastest available route. For degree-$d$ polynomial latencies in both general nonatomic congestion games and single-commodity routing games on series-parallel networks, we give tight lower and upper bounds on the relative change in social cost from an exact Nash equilibrium to any $ε$-NE, with matching instances for every $ε$. For small $ε$, the largest possible relative reduction and increase in general congestion games are both $Θ(\sqrt{dε})$, independently of the number of resources and populations. In contrast, on series-parallel networks of depth $h$, the largest possible relative reduction is $Θ(hε)$, while the largest possible relative increase is known to be $ε$. For the classes of games we study, these results give a tight and quantitative characterization of the possible changes in social cost and establish a separation between general and series-parallel networks.

cs.GT · cs.AI · cs.DS · math.OC

版本更新 · v3arXiv:1704.04538

A Simple Randomized Estimator for Harmonic Numbers and Logarithms

Ali Dasdan

原文摘要

Scanning a list of $x$ distinct numbers in uniformly random order for its maximum replaces the running maximum $H_x$ times on average, where $H_x$ is the $x$th harmonic number. Run backwards, this gives an estimator: the replacement count of a random list is an unbiased Monte Carlo estimate of $H_x$, and since $H_x = \ln x + γ+ O(1/x)$, a corrected estimate of $\ln x$. We give the exact variance of the count, an error decomposition with sample-size rules, and an exact sampler of the count using $H_x$ integer draws on average instead of a scan of length $x$. Coupling two counts estimates $\ln(a/b)$ without $γ$, and a binary range reduction then bounds the standard error by $\sqrt{\ln 2/n}$ for every $x$ at fewer than $1.7$ draws per repetition on average. A classical deterministic series on the same reduction reaches the rounding floor with sixteen terms in the reported experiments, quantifying the gap between the two approaches. The purpose is pedagogical: the analysis of an algorithm becomes an estimator of the quantity that analysis produces, with exact variances, finite-sample error bounds, reproducible experiments, and machine-checked algorithm contracts and moment identities. The ingredients are classical; the contribution is their assembly.

cs.DS

版本更新 · v2arXiv:1504.06203

A Behavioural Thesis of Synchronous Parallel Algorithms -- Correction of the Simplified Parallel ASM Thesis

Flavio Ferrarotti, Klaus-Dieter Schewe, Loredana Tec, Qing Wang

原文摘要

A behavioural theory consists of machine-independent postulates characterizing a particular class of algorithms or systems, an abstract machine model that provably satisfies these postulates, and a rigorous proof that any algorithm or system stipulated by the postulates is captured by the abstract machine model. The class of interest in this article is that of synchronous parallel algorithms. For this class a behavioural theory has already been developed by Blass and Gurevich, which, though mathematically correct, fails to be convincing, as it is not intuitively clear that the postulates really capture the essence of (synchronous) parallel algorithms. We present a much simpler (and presumably more convincing) set of four postulates for (synchronous) parallel algorithms, which are close to those of Gurevich's sequential ASM thesis. The key difference is an extension of the bounded exploration postulate using multiset comprehension terms instead of ground terms formulated over the signature of the states. In addition, all implicit assumptions are made explicit, which amounts to representing states of a parallel algorithm by meta-finite first-order structures. The article first provides evidence that the axiomatization characterizes the whole class of deterministic, synchronous, parallel algorithms, then formally proves that parallel algorithms are captured by Abstract State Machines (ASMs). The proof uses the requirement of the bounded exploration postulate that update sets be uniformly definable, by equality-free first-order formulae, in the finite critical structures determined by the witness terms; these formulae are translated into the guards of a parallel ASM rule. This version corrects the characterization proof of the first version, whose key lemma was false; the bounded exploration postulate has been amended accordingly.

cs.LO

新论文 · v1arXiv:2610.40124

It Takes Two to Probe, Thousands to Retrieve: Putting Vision--Language Probes to the Retrieval Test

Ivana Beňová, Michal Gregor, Marián Šimko

原文摘要

Vision--language models (VLMs) are tested for fine-grained understanding with image--text matching probes, a model must prefer the correct image or caption over handcrafted negative. In retrieval, the correct item must beat thousands of alternatives. We measure how these two evaluation methods relate by using two probing benchmarks, \svo{} and SugarCrepe, for retrieval tasks. For 100 image and caption queries we judge the top-10 retrievals from full dataset of six VLMs, with human annotators and an LLM assessor. We than compare how well models rank pool of items on the same queries, while changing only where the negatives comes from: the benchmark, a random draw, or the judged-incorrect retrievals of other models. On \svo{} the accuracy of retrieving a positive over handcrafted negatives is significantly higher than for retrieved ones (the correct item is preferred in 85\% against 77\% of the time). Using pool of ten retrieved negatives leads to same accuracy as when one uses pool of 200 to 430 random negatives. On SugarCrepe the order is reversed: its handcrafted negatives are harder than the retrieved ones. Incomplete relevance labels explain most of the low retrieval scores on \svo{}, where the top-ranked item is correct for 54--90\% of the queries under human labels against 6--21\% under the benchmark's labels. However, we detect no association between passing the probe for a query and retrieving a correct item first. The LLM assessor o3 agrees with individual annotators ($κ$ 0.57--0.61) slightly less than they agree with each other (0.64--0.68).

cs.CV · cs.CL

版本更新 · v2arXiv:2609.11588

Quasilinear multiplication in the Cayley-Dickson tower

Harrison Lemley

原文摘要

Direct evaluation of the defining product of the Cayley-Dickson algebra $A_n$ of rank $N:=2^n$ over a unital commutative ring $R$ in which $2$ is invertible requires a quadratic number of arithmetic operations. This paper gives a uniform bilinear algorithm for multiplication in this algebra costing $O(N \log N)$ arithmetic operations in $R$ and $O(N)$ auxiliary storage when the doubling parameters of $A_n$ are units whose square roots lie in a fixed commutative coefficient algebra $S$ finitely generated as an $R$-module and admitting an $R$-linear map $π\colon S \to R$ with $π(1) = 1$. In particular, over $\mathbb{R}$ and every finite field $\mathbb{F}_{q}$ of odd characteristic, a quadratic field extension contains a square root of every possible doubling parameter, so the algorithm applies to every Cayley-Dickson tower over these fields, and the tensor rank of multiplication in $A_n$ over them is at most $(9n-21)2^n+28$ when $n\ge2$. When the top doubling parameter is a non-square, as in the standard real tower, the bound is $(9n-15)2^{n-1}+10$. To the author's knowledge, the algorithm presented in this paper is the first uniform subquadratic algorithm for multiplication in $A_n$. When $R=\mathbb{R}$ with every doubling parameter equal to $-1$, the real quasilinear schedule uses fewer total arithmetic operations than both direct multiplication and a uniform algorithm of Cariow-Cariowa for $n\ge4$. An implementation for the standard real tower is available in the MIT-licensed C11 library fastCD, with a NumPy-backed Python interface. In single-core benchmarks against direct multiplication and the uniform Cariow-Cariowa method, the quasilinear implementation had the lowest mean time of the three at every tested dimension $N\ge32$, for both single and batched products, and was over $17$ times faster than direct multiplication at $N=1024$.

math.RA · cs.SC · math.NA

版本更新 · v2arXiv:2610.37255HF 社区推荐

Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces

Jian Mu, Ruibo Shen, Yao Shu

原文摘要

Language model agents are post-trained and deployed through a harness, the prompts, tools, and control logic that present a task to the model and execute its outputs. Harnesses are often revised and judged by how an already trained model performs under them, which assumes that what the model learned under one harness carries over to the next. We ask what a policy learns from its harness and what survives when the harness changes. Under KL-regularized control, we show that the log odds of an optimal policy recover how strongly its harness favors each action over the others, so a trained policy carries the preferences of its harness. Deployed return then equals the ceiling of the harness, the best return it offers, minus the mismatch of the policy, the return lost to its own suboptimal decisions. Training changes only the mismatch, while changing the harness moves both terms. Comparing harnesses with a fixed model therefore mixes what each harness offers with how well that model uses it. In MiniWoB++, post-training makes a model's preferences specific to its training harness. Reversing the order of the observation fields leaves every optimal decision unchanged yet lowers a trained model's success from 85.0% to 19.2%. Conversely, every new harness that a fixed-model comparison rejects but that raises the ceiling outperforms the original agent after further training under it, and ceiling and mismatch measured beforehand predict these gains. For coding-agent harnesses on Terminal-Bench Lite, ceiling minus mismatch estimated with a stronger model as a stand-in for the optimum reproduces the accuracy ranking, while either term alone does not. Code is available at https://github.com/2020-qqtcg/HRP.

cs.LG · cs.CL

版本更新 · v2arXiv:2606.11440

INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration

Ahasan Kabir, Mengxin Zheng, Qian Lou

原文摘要

Multi-agent LLM systems spend additional computation on reasoning and collaboration, but shared serving queues can prevent that computation from producing answers before a deadline. This creates a coupled decision: the reasoning workflow determines the load, while changing load determines which reasoning choices remain affordable. We introduce INFRAMIND, a hierarchical policy that adapts workflow planning and execution to serving conditions. At arrival, a planner selects the collaboration graph using task information, load and the time budget. Before each agent call, an executor jointly selects the model and reasoning strategy using refreshed telemetry and remaining time. A shared latency penalty connects the two policies. Our analysis characterizes why observing load matters when congestion reverses the preferred computation. Across five benchmarks on a shared five-model deployment, INFRAMIND improves low-load accuracy by up to 7.6 percentage points over the strongest evaluated baseline. On 500 MATH questions with matched EDF scheduling and per-request deadlines of 10-300 s, it increases correct, on-time answers from 20.4% to 33.8%. With 15 models and Azure timings replayed on the same benchmark and deadline tiers, this fraction rises from 11.6% to 54.8% over MasRouter. These results support adapting reasoning decisions to the serving capacity available throughout a workflow.

cs.AI

版本更新 · v2arXiv:2603.11137

Scaling Reasoning Efficiently via Relaxed On-Policy Distillation

Jongwoo Ko, Sara Abdali, Young Jin Kim, Tianyi Chen, Pashmina Cameron

原文摘要

On-policy distillation (OPD) is a promising approach for transferring reasoning capabilities to capacity-constrained models, yet sampled-token OPD often suffers from entropy collapse and negative transfer. We identify uniform credit allocation as a key bottleneck: existing objectives obtain dense teacher feedback on student-generated trajectories, but apply it uniformly across sampled tokens despite highly heterogeneous token-level signals. Most tokens carry redundant near-zero credit, while rare heavy-tailed negative credits can dominate updates and prematurely suppress plausible reasoning trajectories. We introduce REOPOLD (Relaxed On-Policy Distillation), a framework that relaxes this uniform assignment by controlling where teacher feedback is applied, how strongly it affects the update, and when the allocation rule changes during training. Across diverse reasoning tasks, REOPOLD improves sampled-token OPD over recent post-training baselines with up to 12x higher sample efficiency, and extends to cross-vocabulary distillation, self-distillation, and test-time scaling.

cs.LG · cs.CL

版本更新 · v3arXiv:2508.04189

BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting

Kunlan Xiang, Haomiao Yang, Wenbo Jiang, Haoxin Wang, Shiyue Huang, Shaofeng Li, Yijing Liu, Ji Guo

原文摘要

Multivariate long-term time series forecasting (MLTSF) models are increasingly deployed in critical domains such as climate, finance, and transportation. Despite their growing importance, the security of MLTSF models against backdoor attacks remains entirely unexplored. To bridge this gap, we propose BadTime, the first effective backdoor attack tailored for MLTSF. BadTime can manipulate hundreds of future predictions toward a target pattern by injecting a subtle trigger. BadTime addresses two key challenges that become particularly severe in MLTSF: (i) the rapid dilution of local triggers over long horizons, and (ii) the extreme sparsity of backdoor signals under stealth constraints. To counter dilution, BadTime leverages inter-variable correlations, temporal lags, and data-driven initialization to design a distributed, lag-aware trigger whose influence persists over long-range forecasts. To overcome sparsity, it mixes label-similar and label-dissimilar poisoned samples and adopts a decoupled backdoor training objective that explicitly up-weights the sparse backdoor signal, enabling reliable learning at a poisoning rate as low as 1%. Extensive experiments show that BadTime significantly outperforms the state-of-the-art backdoor attack on time series forecasting by extending the attackable horizon from at most 12 timesteps to 720 timesteps (a 60x improvement) and reducing the MAE on target variables by 57% on average, while changing the average clean forecasting error by less than 1%.

cs.CR

新论文 · v1arXiv:2610.37430

When Visual Evidence Is Insufficient: How Instructions, Post-Training, and Internal Activations Shape Refusal in Multimodal Language Models

Ananth K Suresh, Aveen Dayal, Gouthaman KV, Aditya Pola, Vineeth N Balasubramanian

原文摘要

For reliable deployment, multimodal large language models (MLLMs) should recognize when an image provides insufficient evidence to answer a question and withhold unsupported answers. Yet refusal alone is not necessarily evidence of such recognition: models may refuse because of unrelated safety constraints or without identifying the missing evidence. We study how refusal on visually unanswerable questions is shaped by three sources of control: inference-time instructions, post-training, and internal activation interventions. Across three MLLMs on the MoHoBench benchmark, we systematically manipulate the meaning and placement of refusal instructions, compare supervised and preference-based post-training, and intervene on a refusal-related activation direction derived from naturally answered and refused examples. We find that refusal is highly sensitive to both the meaning and placement of instructions, with model-specific changes at the sample level that are obscured by aggregate refusal rates. Evidence-aware and general refusal instructions have stronger effects than an intentionally mismatched safety instruction. Post-training produces larger increases in refusal, but can also induce responses that combine refusal language with attempted answers. In contrast, activation intervention produces smaller yet transferable changes across prompt conditions, without evidence of indiscriminate refusal on tested visually answerable samples. These findings show that refusal is jointly shaped by external instructions, post-training, and internal representations, highlighting the need to disentangle evidence recognition from a model's learned propensity to refuse.

cs.LG · cs.CV