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

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 05:25 — 2026-11-19 05:25(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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。

26,870 已收录论文22,374 AI 相关8,156 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 180 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.22954

Sim2CBF: From Forward Simulations to Implicit Control Barrier Function Safety Filtering without Model Derivatives

Luzia Knoedler, Yihan Liu, Shaohang Han, Yifei Dong, Jana Tumova

原文摘要

Failure avoidance in complex robot-environment interactions is challenging because the underlying dynamics are difficult to model accurately, and available predictive models may not provide reliable derivatives. We present Sim2CBF, a failure-avoidance framework that solves the Control Barrier Function (CBF)-Safety Filter (SF) optimization problem using only forward-model evaluations, thereby avoiding differentiation of the predictive model. Specifically, we approximate the CBF constraint using finite differences and local linear interpolation over sampled control inputs while preserving failure-avoidance guarantees. The underlying CBF is implicit and constructed from backup-policy rollouts, enabling the use of expressive predictive models such as physics-based simulators and learned world models. Compared with purely sampling-based SFs, our formulation requires fewer control samples and yields less conservative behavior than direct nominal-backup blending. We evaluate Sim2CBF in simulation, hardware box-toppling, and vision-based control tasks, demonstrating its applicability to contact-rich and learned dynamics, as well as its adaptability to changes in the predictive model.

cs.RO · eess.SY

新论文 · v1arXiv:2611.22657

SpatialCast: Reading the 3D World via Cast Shadows

Enhan Li, Jinghao Zhou, Jiaze Zhang, Hongyang Du

原文摘要

As multimodal large language models (MLLMs) advance toward understanding and interacting with the physical world, spatial reasoning becomes essential for understanding scene structure and anticipating the effects of physical changes. Existing spatial benchmarks have made substantial progress in evaluating spatial relations, memory, and viewpoint reasoning, but less systematically assess how models connect physical scene conditions with visual observations. We introduce SpatialCast, a benchmark that uses cast shadows to evaluate this ability. Cast shadows provide observable evidence of a 3D scene. Their image appearance depends on object geometry and pose, illumination, and viewpoint. We examine this relationship through three complementary tasks that assess scene-projection consistency, predict intervention-induced changes, and infer the physical changes behind visual transitions. The benchmark contains 21,000 synthetic questions with separate scene and geometry test partitions, complemented by 200 SpatialCast-Real questions from 20 photographed scenes. Evaluations show that closed-source MLLMs outperform general-purpose open-weight MLLMs and MLLMs designed for spatial reasoning, which remain near chance on the synthetic benchmark, while even strong closed-source models struggle with shadow-length and light-height judgments. We also use SpatialCast training data for GRPO post-training, improving open-weight MLLM performance on the benchmark. Further evaluations show improvements on several external spatial benchmarks, suggesting transfer of the learned capabilities. These experiments support SpatialCast as a controlled resource for diagnosing spatial reasoning capabilities and studying their learning and generalization.

cs.CV

版本更新 · v4arXiv:2610.37584

REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation

Yuxi Huang, Silin Zhou, Chenhao Wang, Zihan Li, Gangming Guo, Pei Ke, Lisi Chen, Shen Gao 等 9 位作者

原文摘要

Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete semantic IDs (SIDs) of items. However, randomly initialized SID token embeddings and GR models trained from scratch do not directly inherit the semantic relations inherent in items, while inter-item collaborative relations are learned largely implicitly through token-level attention and next-token supervision. To address this limitation, we propose REGER, a unified framework that explicitly incorporates inter-item relations into semantic pretraining, history encoding, and SID generation. We pretrain the GR model through generative semantic retrieval, enabling it to inherit inter-item semantic similarity by learning to generate semantic neighbors' SIDs. We combine global attention with local attention aligned with SID boundaries to capture historical context and directed transitions between adjacent items. We formalize item-level preference distillation on the SID prefix tree, deriving an exact factorization of item preference distributions into prefix conditionals and a weighted decomposition of item-level KL divergence into conditional KL terms. Guided by this decomposition, we renormalize the generator's probabilities over legal next tokens and match the resulting distributions to the teacher's conditional preferences along the ground-truth SID path, jointly optimizing the distillation objective with cross-entropy. Extensive experiments on real-world datasets validate the effectiveness of the proposed preference distillation and demonstrate that REGER consistently outperforms existing GR baselines while retaining efficient inference.

cs.IR · cs.AI

新论文 · v1arXiv:2611.22584

InteractVLA: Turning VLAs into Interactive Tools for Agentic Robotic Manipulation

Chen Zhao, Zipeng Ye, Shifeng Bao, Yihan Lin, Haitao Shen, Yining Luo, Yuchen Xie, Jing Zhang

原文摘要

Existing agentic manipulation systems treat pretrained vision-language-action (VLA) policies as opaque, language-only primitives: when a policy call fails under unfamiliar instructions or scene perturbations, the agent cannot steer its behavior and is forced into futile retries or costly manual takeover. We present InteractVLA, a framework that turns pretrained flow-based VLAs into geometrically steerable and inspectable tools through a bidirectional geometric interface with vision-language agents. In the forward direction, test-time geometric guidance translates an agent-specified end-effector target into input gradients through the action expert via a differentiable command-to-pose mapping, while soft-time target alignment treats arrival time as a latent execution index to match the target pose without distorting the policy's approach motion. In the reverse direction, action-informed agentic refinement exposes generated action chunks and calibrated camera reprojections back to the agent, allowing it to diagnose spatial discrepancies, revise targets for subsequent VLA calls, or locally adjust motion segments on top of the guided trajectory. Making the VLA controllable not only boosts online agentic tool use, but also unlocks effective recursive self-improvement (RSI), achieving state-of-the-art performance of 99.4\% on LIBERO-Plus, 48.62\% on RoboDojo, and 89.4\% on RoboCasa365. Project page: https://lingwupro.github.io/InteractVLA/.

cs.RO

新论文 · v1arXiv:2611.22483

Manufacturing Differential Sparsity: Planner-Hardware Co-Design for Efficient World Model Planning

Wenbo Zhu, Paul Yi-Chia Chen, Yuanhan Li, Zishen Wan, Christopher Torng

原文摘要

JEPA-style latent world models let embodied agents plan toward new goals with model predictive control, but they are still too slow for real-life embodied control: sampling-based MPC repeats predictor inference tens of thousands of times per plan, and even on high-end GPUs one planning step can take tens of seconds. We observe substantial latent locality in this repeated-inference workload: the predictor maps close actions to close latents, and inside a quantized predictor this closeness takes a form that hardware can exploit, differential bit-level sparsity. Unlike an input stream, whose temporal similarity is given, a planner itself decides which candidates it evaluates together, so the planner can choose its own references and, with reference forest sampling, manufacture more sparsity: it couples the sampled action sequences of each group to a shared root, with competitive planning quality. We build the accelerator on the insights of the rich line of bit-level sparsity accelerators and design it and the planner tightly coupled as a single co-design: the planner increases sparsity and exposes structure for hardware scheduling, and the bit-exact hardware effectively uses the sparsity that the planner creates. On three JEPA world models, our co-design is 1.28-1.80x faster than a dense accelerator and uses 38-52% less energy, and it is 1.22-1.58x faster than prior bit-sparse design and uses 16-36% less energy, with the same area. To our knowledge, our planner is the first planner that manufactures differential bit-level sparsity across its candidates and exposes its structure for hardware scheduling, and our co-design is the first algorithm-hardware co-design for JEPA-style world-model planning.

cs.AR · cs.AI · cs.LG · cs.RO · eess.SY

版本更新 · v2arXiv:2611.19273

B-OPSD: On-Policy Self-Distillation with Self-Generated Problem Briefs

Zhi Xu, Yinqi Wu, Feng Zhang, Xiaotong Zhang, Hong Yu, Han Liu

原文摘要

On-Policy Self-Distillation (OPSD) has recently attracted interest because it provides dense teacher guidance without a separate, often larger teacher model. However, OPSD conditions its teacher on ground-truth solutions, which limits its use when such solutions are unavailable. We propose On-Policy Self-Distillation with Self-Generated Problem Briefs (B-OPSD). Using a prompt template, the initial model or a saved student checkpoint generates a problem brief from the question alone. The prompt asks for relevant principles, applicability conditions, and likely pitfalls, but not a final answer or a complete solution. A frozen teacher uses the brief as privileged context to guide the current student's on-policy rollouts through token-level distribution matching. B-OPSD uses no ground-truth solutions during training. Results on AIME 2024, AIME 2025, and HMMT 2025 show that both B-OPSD variants achieve higher average accuracy than OPSD at each of three Qwen3 model sizes. Code is available at https://github.com/ZevineXu/B-OPSD

cs.CL

新论文 · v1arXiv:2611.22310

EviDARL: Evidence-Centric Dual-Agent Reasoning via Alternating Reinforcement Learning for Multi-Table Question Answering

Dunhan Li, Leilei Gan, Lirong Gao, Wenyan Fan, Yongwei Wang, Sheng Guo, Fei Wu

原文摘要

Despite advances in LLM-based table reasoning, most studies focus on single-table settings. Multi-table QA requires multi-hop reasoning over complex table relationships and evidence dispersed across long contexts, often without verifiable intermediate traces. To address these challenges, we introduce EviDA, an evidence-centric dual-agent framework comprising an Evidence Construction Agent and a Reasoning and Answering Agent. The Evidence Construction Agent generates and executes table-manipulation programs over complete tables to produce question-specific evidence and verifiable intermediate traces, simplifying subsequent reasoning. The Reasoning and Answering Agent then performs multi-hop reasoning over this evidence to derive final answers. We further introduce EviDARL, which combines agent-specific fine-grained rewards with parameter-efficient alternating reinforcement learning to improve collaboration between the agents. By optimizing each agent in turn while holding the other fixed, EviDARL enables bidirectional adaptation between evidence construction and answer reasoning. Experiments on MMQA and TQA-Bench demonstrate that EviDARL substantially outperforms competitive open-model and multi-table reasoning baselines under constrained model and training budgets.

cs.AI

新论文 · v1arXiv:2611.22291

When the World Is the Test Suite: Agentic Intelligence for the Physical World

Kaixin Li, Meng Luo, Yanlin Li, Yuchen Tian, Xiang Liu, Xiangru Jian, Yan Yang, Zhiheng Xi 等 12 位作者

原文摘要

Coding agents built to repair software now write, test, and repair programs for robots, laboratories, and industrial controllers. Unlike in software engineering, no test suite comes with the code. Whether a program works must be established by running it on a robot, in a physics simulator, or through the policies it helps to train, and such evidence is costly to obtain and can itself be wrong. As these agents take on more physical tasks, how their programs are judged matters as much as how they are written. This paper examines this emerging area, agentic intelligence for the physical world, by treating the world as the program's test suite. We organize the discussion around three questions: how agents write programs for the physical world, how these programs are tested, and how agents learn from the results. We first trace how language models for robots and software engineering agents came together, ask which software testing practices carry over to physical tests, and describe each program by where it sits relative to the actuator and by what judges it. For writing, we cover programs that act as robot policies and programs that support policy learning by producing rewards, tasks, and training worlds. For testing, we examine what physical trials cost, what traces, learned judges, simulators, and formal checks can establish in their place, and what safety requires beyond task success. For learning, we discuss how tested programs are retained as experience, in skill libraries and in model weights. Finally, we turn to benchmarks and evaluation practice and outline open challenges. Writing programs is becoming cheap, while trustworthy evidence about what they do remains costly. Progress will therefore depend on a physical counterpart of continuous integration: verification cheap enough to run often, reliable enough to trust under search, and maintained alongside the experience it validates.

cs.RO · cs.AI · cs.SE

新论文 · v1arXiv:2611.22241

Where Does Hindsight Enter Clinical Agent Benchmarks? An Audit of Simulators and Case Construction

Meilu Zhu, Xiaohan Li, Axiu Mao

原文摘要

Benchmarks for LLM diagnostic agents are built from retrospective records: the case an agent reads is rewritten from discharge summaries, and unrecorded test results are generated by a simulator that often sees the final diagnosis. HindAudit separates three hindsight channels (the diagnosis given to the simulator, the retrospective context it conditions on, and the agent-facing case text) and measures each with judges trained only on real data. On 27,489 emergency admissions from MIMIC-IV, five registered tests found no leakage into simulated laboratory results: providing the diagnosis to five simulators had a negligible effect, and prompted gatekeepers diluted the diagnostic signal, although exploratory results suggest they can raise agent scores. The largest effect lay in the case text. Against a presentation-time reconstruction from triage records, benchmark-style summaries raised the zero-shot accuracy of four LLMs from 25.4% to 39.7% and discharge histories to 45.3%, and raised six interactive agents' scores while barely changing their ranking. The exploratory gap was reproduced in a registered replication on held-out patients. Masking diagnosis names left it unchanged. Because MIMIC lacks a contemporaneous bedside history, the gap is an upper bound on hindsight. We report all registered outcomes and recommend construction practices.

cs.CL

新论文 · v1arXiv:2611.22115

TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks

Xingchen AGI Lab, :, Baotian Hu, Bingkai Yang, Boyang Wang, Changzai Pan, Chao Lyu, Chao Wang 等 140 位作者

原文摘要

We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes the design principles and systems engineering behind the series, spanning architecture selection, large-scale pretraining, and reasoning and agentic post-training. We study how sparse activation, attention design, model depth and width, and speculative decoding balance model capacity with computation, memory access, and execution overhead. Our pretraining infrastructure builds on MindSpore HyperParallel, combining topology-aware hybrid sharding, efficient distributed optimizer execution, and coordinated management of long-sequence workloads and activation memory. CPU affinity and core isolation further reduce host scheduling interference. Together, these mechanisms support the pretraining of a 285B-parameter model on 8,192 Ascend 910C cards, providing a concrete setting for the architectural and systems studies. For post-training, we introduce TeleGym, a unified agent execution platform that connects execution, evaluation, and trajectory construction to policy optimization. Disaggregated asynchronous execution, bounded oversampling, and partial rollout accommodate heterogeneous task durations while preserving trajectory continuity across policy updates. Together, these advances establish an Ascend-oriented training foundation for the continued development of Xing 4 across model scales and increasingly demanding reasoning and agent workloads.

cs.AI

新论文 · v1arXiv:2611.21273

CAE-Bench: Benchmarking AI Agents for Reusable CAE Solver Development

Zhiyu Zhou, Tianyou Liu, Xinping Yang, Yiyao Liu, Jiayi Dong, Yihan Lin, Haokai Ye, Yifan Lu 等 11 位作者

原文摘要

We developed CAE-Bench, a benchmark to evaluate AI agents on Computer-Aided Engineering (CAE) solver development. A CAE solver is more than a PDE solver; it must be able to generalize across various inputs, such as different boundary conditions, geometries, and material properties. CAE-Bench evaluates the generalizability of AI-developed CAE solvers by providing the same task, such as a heat transfer problem, multiple cases, with each case specifying an input. The AI agent develops a solver for a fixed task using only a few public cases, and the resulting solver is then tested on held-out cases, i.e., cases it has never seen before. We evaluate 12 models across a range of reasoning settings on 80 computational tasks. Our experiments show that even if a solver developed by an AI agent performs well on the public cases, it may even get 0 score on held-out cases. For tasks such as fluid dynamics problems, even the solver developed by GPT-6 Astra performs poorly on held-out cases. A data format and an SDK for task registration are provided, so the researcher can use the benchmark on their own infrastructure. We hope that CAE-Bench will help the community to develop AI agents that can develop reusable CAE solvers that generalize to various inputs.

cs.AI

版本更新 · v3arXiv:2607.19358

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

Yu Zhao, Zekun Zhang, Fan Jiang, Bo Zeng, Xintong Wang, Chonghan Liu, Shimin Shan, Yichao Du 等 9 位作者

原文摘要

Long chain-of-thought (CoT) reasoning models such as DeepSeek-R1 keep lengthening their inference chains under test-time scaling, yet standard self-attention incurs quadratic cost in context length, making long-CoT deployment costly in production. We therefore introduce LISA (Linear-Indexed Sparse Attention), a plug-and-play replacement for self-attention that requires no full pretraining. LISA combines a linear-attention branch for long-range memory with a Lightning Indexer that dynamically selects the most relevant tokens for a sparse self-attention branch. The two branches are fused through a learned gate, so the model retains broad context while focusing computation on informative tokens. We train LISA in two stages. In Stage 1, a linear-attention branch is integrated with sliding-window attention and distilled from a frozen teacher's full-attention distribution. In Stage 2, the Lightning Indexer replaces the static window and is trained with a per-head KL-divergence objective to mimic teacher attention patterns. The resulting model reduces eager-mode self-attention computation from quadratic in sequence length to linear in the number of generated tokens and the selected context budget. Experiments on DeepSeek-distilled Qwen models show that LISA cuts measured eager-mode mean sample latency by 23.9% at 16K context without degrading long-context reasoning quality. Across nine mathematical and code reasoning benchmarks, the gated LISA-1.5B model improves the equal-weight benchmark average by 4.2 percentage points relative to the full-attention baseline.

cs.AI

新论文 · v1arXiv:2611.20882

Accelerate Bench: Evaluating Agents for Application-Level Program Optimization

Bowen Liu, Yuhan Li, Nuo Chen, Weile Luo, Miao Peng, Qintong Zhang, Qifan Zhang, Jia Li 等 10 位作者

原文摘要

Application optimization requires coding agents to discover useful changes and coordinate them across a complete program while preserving the required computation. We introduce Accelerate Bench, a benchmark of 32 CPU optimization tasks adapted from scientific applications and supercomputing competitions. Each task provides a working program and specifies the workload, correctness requirements, timing boundaries, and permitted edits, leaving agents to choose where and how to optimize. Public testing supports iterative development, and a separate verifier scores the final submission. On benchmark version 1.1, we evaluate 16 coding agents, each pairing a model with a harness. Their Score@1 ranges from 25.5% to 67.4%. Most of their programs are correct, and the size of the speedup separates them: the two leading agents are at least 2x faster on 22 or more of the 32 tasks, while the other fourteen reach 2x on 8 to 17 and leave 125 of their 412 correct outcomes below 1.25x. Controlled replays show why coordination across an application matters: identical source code runs between 0.29x and 2.12x depending only on build and runtime settings, and one code change is worth 1.01x or 6.4x depending on another. Accelerate Bench pairs executable workloads with agents' programs and trajectories to evaluate both their gains and the process behind them.

cs.AI

版本更新 · v2arXiv:2605.09636

PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation

Zhen Hang, Yushan Yashengjiang, Junhui Li, Huanshuo Dong, Yang Wei, Zhezheng Hao, Jiangtao Ma, Songlin Bai 等 24 位作者

原文摘要

PDE-to-solver code generation aims to automatically synthesize executable numerical solvers from partial differential equation (PDE) specifications. This task requires not only understanding the mathematical structure of PDEs, but also selecting appropriate discretization schemes and solver configurations, and correctly implementing the resulting formulations in finite-element method (FEM) libraries. Existing code generation benchmarks mainly evaluate syntactic correctness, or success on predefined test cases. To our knowledge, there is currently no publicly available benchmark specifically for PDE-to-solver code generation, and general-purpose code benchmarks do not fully capture the unique challenges of numerical PDE solution, such as ensuring solver accuracy, efficiency, and compatibility with professional FEM libraries. We introduce PDEAgent-Bench, to the best of our knowledge, the first multi-metric, multi-library benchmark for PDE-to-solver code generation. PDEAgent-Bench contains 645 instances across 6 mathematical categories and 11 PDE families, with common FEM libraries for DOLFINx, Firedrake, and deal.II. Each instance provides an agent-facing problem specification, a reference solution on a prescribed evaluation grid, and case-specific accuracy and runtime targets. PDEAgent-Bench adopts a staged evaluation framework in which generated solvers must sequentially pass executability, numerical accuracy, and computational efficiency checks. Experiments with representative LLMs and code agents show that models can often produce runnable code, but their pass rate drops substantially once accuracy and efficiency requirements are enforced. These results indicate that current agents remain limited in producing numerically reliable and efficient PDE solvers, and that PDEAgent-Bench provides a reproducible testbed grounded in the practical requirements of numerical PDE solving.

cs.AI

版本更新 · v2arXiv:2606.27058

UniFormer: Efficient and Unified Model-Centric Scaling for Industrial Recommendation

Bo Chen, Jinlong Jiao, Tijian Hu, Ruihao Zhang, Yanzhi Liu, Chenghou Jin, Qinglin Jia, Baixuan He 等 16 位作者

原文摘要

Recently, substantial progress has been made in industrial recommendation through component-centric model scaling, where individual components such as behavior modeling, feature interaction, or task modeling are independently scaled to improve model capacity. Although recent methods such as HyFormer and OneTrans further explore cross-module co-scaling by jointly modeling behavior and interaction, their designs are still confined to the feature space and lack a unified model-centric scaling framework over the overall modeling space. In this paper, we propose UniFormer, an efficient and unified model-centric scaling framework for industrial recommender systems. To improve efficiency, UniFormer decomposes the overall modeling space into feature and task spaces, which are modeled by stacked Feature-space Interaction Modules and Task-space Interaction Modules, respectively. Moreover, UniFormer introduces semantic-based tokenization scheme to enable user-item decoupling, thereby achieving request-level inference acceleration. To prevent preference collapse, UniFormer employs multi-sequence cross-attention to separately capture heterogeneous behavior patterns, followed by the self-attention to enhance interaction modeling. Besides, dedicated multi-view FFNs are introduced to support flexible and scalable parameter scaling across different modeling components. Extensive online A/B testing in two production scenarios, Kuaishou and Kuaishou Lite, shows that UniFormer consistently improves user engagement and interaction metrics, achieving gains of +0.101%/+0.260% in App Stay Time and +0.729%/+1.113% in Watch Time, respectively.

cs.IR

新论文 · v1arXiv:2611.20574

ExtremeDrive: A Real-World Dataset and Benchmark for Critical Driving

Xinhan Li, Yuhong Jiang, Shiyue Zhao, Junzhi Zhang, Chengkun He, Ruihai Ma, Shijie Zhao, Wenxuan Cheng 等 10 位作者

原文摘要

Existing autonomous driving datasets and benchmarks provide extensive resources for routine driving, yet real-world data covering safety-critical scenarios and extreme environmental conditions remain limited. To address this gap, we present ExtremeDrive, a real-world dataset and benchmark covering emergency maneuvers, complex traffic interactions, and adverse conditions such as slippery or snow-covered roads, alongside routine driving. The dataset comprises 589 driving scenes curated from a larger pool of real-world driving recordings, with calibrated and aligned multisensor data and reviewed annotations of road structure and traffic participants. We further establish a benchmark to evaluate planned trajectories through simulated vehicle execution, measuring safety-related metrics and driving performance. Experiments at equal training set sizes show that incorporating critical driving data reduces trajectory prediction errors and improves mean critical-success rates in critical scenarios. ExtremeDrive provides a unified resource for learning and evaluating autonomous driving in safety-critical scenarios and extreme environmental conditions.

cs.RO · eess.SY

新论文 · v1arXiv:2611.20468

Tabular Foundation Models as Emulators for Forecasting Terrestrial Ecosystem Dynamics

Zhihao Wang, Ruohan Li, Lei Ma, George Hurtt, Xiaowei Jia, Yiqun Xie

原文摘要

Process-based terrestrial biosphere models such as the Ecosystem Demography (ED) model underpin global carbon budgets, but their cost limits global, high-resolution and scenario-rich simulation. Deep emulators such as DeepED reduce that cost but require task-specific architectures and training. Tabular foundation models offer a different route: TabPFN predicts new rows by in-context learning, without being trained on the task. We compare TabPFN-3.5 with two DeepED baselines, $DeepED_{LSTM}$ and $DeepED_{Transformer}$, on CarbonGlobe's overall evaluation, which trains on a uniform 1/16 sample of sites and tests on the other 50,779, predicting the 40-year state of all seven ED outputs. We then test every model, trained on present-day data only, on ED runs forced by SSP1-2.6 and SSP5-8.5 for 2021--2060 in six continental forest regions. With no training, TabPFN-3.5 has the lowest present-day height error of the three models and is within 4% of $DeepED_{LSTM}$ for soil carbon, but is less accurate for AGB, LAI and the carbon fluxes. In 2060, errors are several times larger than at the same sites under present-day forcing, and every model underestimates the biomass that ED gains. Under SSP5-8.5, TabPFN-3.5 is the most accurate model for height, AGB, soil carbon and LAI, with the lowest AGB error in all six regions, although, unlike ED, it predicts no larger biomass gain than under SSP1-2.6. Under SSP1-2.6, no model is best overall.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.18449

Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery

Yibo Wen, Han Liu

原文摘要

AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide fixed datasets, while others that support active experimentation largely rely on simulation. We introduce Autonomous Science Bench, an initial release comprising six budgeted design-build-test-learn campaigns grounded in published experiments across biology, chemistry, and materials science. Agents select batches of designs, receive measurements from a lab service, and use the results to guide subsequent experiments before delivering a predictive model. Success requires passing two calibrated gates: a discovery gate, which evaluates the designs the agent measured, and a learning gate, which evaluates its model's ranking of held-out designs. In a pilot evaluation of ten agent-model configurations and 180 trials, the best configuration succeeds in 72% of trials, while the hardest campaign is solved in only five of 30 attempts. The two gates reveal different weaknesses: some agents build accurate rankings but find too few promising designs, while others find promising designs but fail to predict which unseen designs will perform well. These differences are obscured by overall success rates alone. We release version 0.1 of the campaigns, lab runtime, and public leaderboard at https://asb.open-ssi.org/.

cs.AI

新论文 · v1arXiv:2611.20218

SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

Xinping Lei, Minghao Liu, Ruijie Zhu, Xiaohui Hu, Xingqiao Li, Ao Zhang, Wenhao Chai, Han Li 等 26 位作者

原文摘要

A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment places an agent in a simulated engineering organization with 26 colleagues who have distinct responsibilities, bounded knowledge, and controlled collaboration behavior. Starting from a brief handoff, agents must recover requirements distributed across colleagues and workplace records, reconcile conflicting evidence, and implement changes evaluated by private executable tests. We evaluate eleven models and find a substantial gap between partial implementation and complete task delivery. The two leading models satisfy approximately 63% of fail-to-pass (F2P) tests but complete fewer than 8% of assignments. Providing complete requirements upfront improves F2P by approximately 16 percentage points for Seed Evolving and GPT-6 Astra, yet leaves complete task success unchanged. Requirement-level trajectory analysis reveals failures throughout the delivery process: Claude-Opus-5.5 directs a mean of 93% of first questions about queried cards to their accountable owners across runs but obtains only 64% of colleague-held requirements. Deferred questions go unfollowed, implementations remain incomplete even after requirements are acquired, and 31% of requirements reported as completed fail their tests. These findings highlight sustained requirement tracking, from clarification through implementation, verification, and handoff, as a key challenge for reliable autonomous software engineering.

cs.SE · cs.AI

版本更新 · v2arXiv:2605.06481

OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation

Yushan Liu, Peibo Sun, Shoujie Li, Yifan Xie, Lingfeng Zhang, Xintao Chao, Shiyuan Dong, Fang Chen 等 10 位作者

原文摘要

World action models (WAMs) learn manipulation by predicting actions and future observations, yet their success drops sharply when the camera viewpoint, object layout or robot initial state changes. Such changes keep the instructed object the same but alter the appearance and pose features the policy observes, which in standard attention also form the keys that locate the object. We introduce OA-WAM, an object-addressable WAM that finds each object by an identity address fixed for the episode and reads its changing state. In every layer of a pretrained multimodal trunk, object-slot keys depend only on the address and frame position, and values carry the current state; the same addresses key the action pointer and index per-object forecasts, which can trigger re-grounding. Fine-tuned on standard LIBERO demonstrations, OA-WAM transfers zero-shot to LIBERO-Plus with 90.5% success, outperforming all ten published baselines. It also leads on LIBERO (99.0%) and, fine-tuned on BridgeData V2, on SimplerEnv WidowX (88.9%). On five real-robot tasks, it succeeds in 89 of 100 nominal trials, versus 73 for the strongest baseline. Ablations trace its robustness to addressing rather than to object slots: with standard attention, slots do no better than a slot-free policy, and addressing them by identity raises geometric success by 10.7 points. Forecasting the addressed objects is likewise a stronger training signal than forecasting image codes.

cs.RO

版本更新 · v2arXiv:2606.05636

StableRCA: Mechanism-Level Root Cause Analysis without Global Graph Discovery

Xiaoyu Lin, Nicholas Tagliapietra, Kehan Li, Lavdim Halilaj, Juergen Luettin, Peng Cui

原文摘要

Root-cause analysis (RCA) seeks to identify the true causal variables that are responsible for a system's abnormal behaviors. A central challenge in this task is to distinguish changes where the anomaly occurs from downstream propagated abnormal effects, particularly when the underlying causal structure is unknown. To address this challenge, we propose StableRCA, an RCA framework that helps distinguish root causes from variables affected by fault propagation by examining how each candidate's conditional distribution, given a selected set of other variables, changes between the normal and anomalous regimes, without requiring knowledge of the underlying causal graph. The method first identifies variables with marginal distribution shifts as root-cause candidates, then selects a local conditioning set for each candidate using stable learning, and finally ranks the candidates by the magnitude of their local conditional shifts, using an importance-weighted Relative Risk Variation (RRV) score as a proxy. Our theoretical analysis establishes sufficient conditions under which comparing the conditional distributions of candidate variables across the normal and anomalous regimes, given suitable conditioning sets, identifies the root causes. Experiments on synthetic benchmarks and four real-world application benchmarks demonstrate StableRCA's competitive performance across diverse domains.

cs.LG

新论文 · v1arXiv:2611.19904

DiffWAM: Learning World Action Model from Consecutive Visual Difference

Xinheng Zhang, Haoyu Xiong, Chao Jing, Xiaohan Zhang, Linshan Li, Hongbang Fan, Xingyu Chen

原文摘要

World Action Models (WAMs) have emerged as an important paradigm in robot learning, jointly predicting future scene states and robot actions from current observations and instructions. However, future states entangle task-related changes with large amounts of task-irrelevant content, such as static backgrounds, which weakens the model's ability to capture changes relevant to task execution. To address this, we propose Difference World Action Model (DiffWAM), a Mixture-of-Experts (MoE) framework that enhances world representations by jointly learning future-state prediction and consecutive visual difference prediction. We define consecutive visual differences as differences between the latent representations of consecutive observations, providing an explicit learning signal for temporal variation. The framework comprises a World Expert for future frame prediction, an Action Expert for action generation, and a Diff Expert for predicting these latent differences along the trajectory. A structured unidirectional attention mask conditions the Diff, World, and Action Experts solely on the current-frame representation while blocking attention between experts. This design allows both the World and Diff Experts to be removed during inference, introducing no additional inference overhead. DiffWAM achieves state-of-the-art performance on the LIBERO and RoboTwin 2.0 benchmarks and substantially improves over FastWAM on real-world manipulation tasks. Specifically, it attains average success rates of 98.8%, 92.65%, and 88.3%, outperforming the state-of-the-art baseline (i.e., FastWAM) by 1.75, 1.55, and 15.0 percentage points, respectively.

cs.RO

新论文 · v1arXiv:2611.19850

Sharp Gaussian Approximation for Q-Learning

Xingtu Liu

原文摘要

Gaussian approximation provides a foundation for online statistical inference in reinforcement learning. We establish sharp non-asymptotic Gaussian approximation rates in Wasserstein distance for asynchronous Q-learning with Polyak-Ruppert averaging. We prove an upper bound of $\widetilde{O}(n^{-1/4})$, where $n$ is the number of iterations, together with a matching lower bound up to logarithmic factors. Q-learning is more challenging to analyze than linear stochastic approximation due to the nonlinearity of the Bellman operator. Asynchronous updates introduce further challenges due to Markovian noise. Our analysis separates the errors from Bellman nonlinearity, Markovian noise, and the finite-sample covariance discrepancy. In particular, we show that Markovian noise induces an unavoidable bias even when the Bellman operator is linear. The trade-off between this bias and the covariance discrepancy determines the convergence rate. We further extend our analysis to the synchronous setting and establish a sharp rate of $\widetilde{O}(n^{-1/2})$.

stat.ML · cs.LG · math.ST

新论文 · v1arXiv:2611.19773

SemLite-GS: Semantic-Selective Parallel Gaussian Splatting for Lightweight Building Reconstruction from UAV Oblique Imagery

Tengfei Wang, Xin Wang, Zihan Li, Quanjian Ji, Yifei Yu, Dong Lin, Zongqian Zhan

原文摘要

Lightweight 3D building models support urban spatial analysis, but their production often requires dense scene reconstruction, building extraction, and mesh simplification. Although 3D Gaussian Splatting (3DGS) is more efficient than conventional multi-view stereo, existing large-scale methods lack semantic selection and parallel instance-level training. We present SemLite-GS, a building-centric framework that reconstructs lightweight building meshes from large-scale UAV oblique imagery. First, an orthographic reference map establishes globally consistent building identities, which are propagated to oblique views to form camera-instance pairs and regions of interest. Second, semantic-selective parallel PGSR training jointly processes multiple pairs within relevant image regions while updating only target Gaussians; contextual Gaussians remain fixed to preserve visibility. Third, architectural planes extracted from rendered depth, opacity, and normal maps guide signed distance field optimization, producing meshes with adaptive polygon allocation and well-defined structural boundaries. Experiments on multiple large-scale UAV datasets demonstrate that our SemLite-GS substantially reduces building reconstruction time compared with representative full-scene 3DGS methods. With comparable polygon budgets, SemLite-GS achieves superior preservation of dominant planar structures and sharp architectural transitions compared with conventional dense reconstruction followed by mesh decimation. The source code is available at https://github.com/IRIS-LAB-whu/SemLite-GS.

cs.CV

新论文 · v1arXiv:2611.19742

Exploration of Reinforcement Learning in Generative Recommendation Models

Pengfei Zheng, Wuchao Li, Shiyao Wang, Honghui Bao, Hongyi Xie, Jiaxin Deng, Xingmei Wang, Jinghao Zhang 等 14 位作者

原文摘要

Traditional cascaded recommender systems balance accuracy and efficiency over large item spaces, but misaligned stage-wise objectives hinder end-to-end optimization. Generative recommendation unifies these stages in an autoregressive framework, providing a natural interface for reinforcement learning (RL) to optimize the entire generation process. However, directly applying RL often leads to unstable optimization and degraded recommendation quality. We revisit Group Relative Policy Optimization (GRPO) and other ratio-based objectives through a unified logit-gradient view. We identify three issues: (i) clipped surrogates create dead-gradient regions, under-utilizing samples; (ii) negative-advantage updates can become effectively unbounded as importance ratios grow, allowing a small subset of negatives to dominate optimization; and (iii) ratio-based control lacks sensitivity to absolute policy confidence, so updates on high-confidence cases may fail to vanish. Motivated by this diagnosis, we propose \emph{Gradient-Bounded Policy Optimization} (GBPO), a simple objective with stop-gradient normalization that is simultaneously (a) fully gradient-active, (b) sign-symmetrically bounded for both positive and negative updates, and (c) explicitly confidence-weighted under current policy probabilities. This ensures that updates gracefully vanish for $π\!\to\!1$ positives and $π\!\to\!0$ negatives. Across the evaluated settings, GBPO achieves competitive recommendation performance with more stable training than competing RL methods.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.17048

Beyond Answering: Learning to Speak First and Act in Streaming Video

Shuhan Li, Huankang Guan, Xintong Guo, Yang Bo, Yuyang He, Dunyuan Xu, Jingyan Chen, Fang Liu 等 18 位作者

原文摘要

Most AI assistants respond only when prompted, remaining silent even when events in the video stream offer meaningful opportunities for conversation. To move beyond purely user-driven interaction, we present AURA 2.0, a streaming video large language model that introduces three core upgrades to AURA. The key advance is Model-Initiated Conversation (MIC), which enables the model to identify topics worth discussing in the evolving visual stream and initiate conversations at appropriate moments without a user query. Stream-Aware Tool Calling (SATC) lets the model act on what it sees by invoking external tools using the current visual and conversational context and incorporating returned information into the ongoing interaction. Interactive Visual Grounding (IVG) supports visual grounding in both user inputs and model outputs. The model can identify objects marked by users on video frames and produce frame-aligned bounding boxes to link its responses to specific objects and regions. To develop these capabilities, we construct a dedicated streaming interaction dataset and adopt a three-stage training scheme to integrate the new behaviors with AURA's existing streaming interaction abilities. We further incorporate Long-Horizon Interaction Memory (LHIM) to maintain contextual continuity over extended video streams. Evaluations on public streaming benchmarks show that AURA 2.0 achieves leading performance among open-source streaming models, while targeted evaluations further validate its new interaction capabilities.

cs.CV · cs.AI

版本更新 · v2arXiv:2510.22622

DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection

Kangran Zhao, Xiaoyu Zhang, Yupeng Chen, Yize Chen, Weinan Guan, Bo Zheng, Yufan Liao, Chengzhe Sun 等 12 位作者

原文摘要

Audio-visual deepfakes can spread misinformation and enable impersonation, undermining trust in digital media. However, existing datasets provide limited coverage of forgery operations and their combinations, constraining detector development and systematic evaluation. We introduce Mega-MMDF, containing 100,000 real and 1.2 million forged clips across 22 pipelines spanning modality-specific manipulations, stacked forgeries, and joint audio-video generation. To assess its training value and enable fair comparisons, we develop DeepfakeBench-MM, which standardizes training and evaluation across 8 datasets and 10 detectors. Training-based detectors achieve their highest mean AUC when trained on Mega-MMDF, with gains of up to 0.0784 over the best alternative training dataset for each detector. Experiments on data scale and pipeline coverage further support the value of large, diverse training data. Cross-pipeline evaluations reveal bidirectional and asymmetric generalization. Training on composite forgeries does not necessarily enable detection of their constituent operations in isolation. Our analysis of altered inputs shows that modality masking can increase false alarms and missed detections, and temporal misalignment can raise mean predicted forgery probabilities. Together, these resources provide a foundation for understanding and improving multimodal deepfake detection, with publicly available code and dataset access subject to application and usage terms.

cs.CR · cs.CV · cs.MM

版本更新 · v2arXiv:2611.17332

ArchSpace:记录、评审与引用 LLM 架构研究

ArchSpace: Recording, Reviewing, and Referencing LLM Architecture Research

Jie Wang, Tong Zhu, Jiahao Kuang, Zhe Xu, Mowen Ruan, Yunkai Chai, Yuliang Liu, Dehong Zheng 等 14 位作者

AI 速读 基于摘要

ArchSpace 是一个公开平台,用于记录 LLM 架构提案及其实验与推理、由社区评审,并供后续工作引用,同时借助缩放定律在小规模实验上预测更大规模的模型损失。

cs.CL · cs.LG

查看原文摘要

Model architecture shapes the scaling behavior, training efficiency, and inference cost of LLMs, making it a central focus of both industry and academia. In industry, teams such as those behind DeepSeek, Qwen, and Kimi routinely introduce architectural innovations, yet public reports rarely document which ideas succeeded, which were abandoned, and why. In academia, limited compute and inconsistent baselines often restrict evaluations to small-scale, single-point comparisons, making it difficult to establish whether improvements hold at larger scales or translate into broader impact. ArchSpace addresses both gaps as a public platform for Recording, Reviewing, and Referencing Architecture Research: each proposal is recorded with its experiments and reasoning, reviewed by the community, and referenced by later work. To evaluate ideas before costly large-scale training, ArchSpace leverages scaling laws to predict model loss at larger scales from smaller experiments, a practice widely adopted in industry. We provide initial references that make the platform usable: Qwen3.5 and OLMo3 baselines, fitted scaling laws, and a reusable training recipe. Ideas validated through this review can in turn become new baselines, and ArchSpace thereby aims to broaden the range of ideas that shape the next generation of models.

新论文 · v1arXiv:2611.18389

A systematic comparison of physics-informed neural networks and mechanistic models for epidemic modeling and forecasting

Martina Rama, Yuhan Li, Bruno Lepri, Nicola Perra, Michele Tizzoni

原文摘要

Physics-Informed Neural Networks (PINNs) have recently been applied to epidemic modeling and forecasting with promising results. These methods integrate mechanistic knowledge with data-driven learning. Yet, their comparative performance against well-established, and simpler epidemic models is underexplored. Here, we conduct a systematic comparison of a PINN-based framework and a stochastic mechanistic model. Both approaches share the same age-structured SEIRD core and rolling-window forecasting pipeline, in a deliberately minimal setting. We evaluate their retrospective fits and probabilistic forecasts in two synthetic scenarios and the first COVID-19 wave in London. Interestingly, while PINNs underperform in synthetic scenarios, they achieve better performance on real data. Furthermore, PINNs provide narrower uncertainty intervals and sharper estimation of parameters in synthetic scenarios. Our findings confirm PINNs as a promising tool in epidemiology. At the same time, the results reaffirm the value of simpler approaches such as traditional compartmental models, and promote additional benchmarking studies.

physics.soc-ph · cs.LG

新论文 · v1arXiv:2611.17696

Co-Sight Harness: Externalized Control Assets and Deterministic Enforcement for Long-Horizon Business Agents

Luyao Wang, Xijun Zhu, Zhaohui Hao, Xiwen Zhang, Xingyu Wen, Weishan Li, Yuyang Liao, Yanqin Gao 等 14 位作者

原文摘要

Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflows can be made reliable without changing the language model. Our method keeps the backbone fixed and moves the workflow definition, state and domain knowledge into versioned control assets outside the model. A state machine and machine-checkable acceptance gates enforce these assets during execution; an independent auditor grades the resulting trace. The assets are updated only after a regression check and human approval .We evaluate the method on three deployed workflows exceeding 200 steps. On Domain A, a 120-case end-to-end evaluation set shows unattended completion rising from 50% to 100%, retrieval recall from 56% to 91.67%, and end-to-end latency dropping from 440 to 159 minutes, with scenario-analysis recall rising from 45% to 93%. Two other domains were taken over by teams that did not write the assets, one in four days and one in seven days. A controlled ablation separates the two failure sources. The code is available at https://github.com/ZTE-AICloud/Co-Sight/tree/master/Co-Sight%20Harness.

cs.AI