探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13663

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

作者:

Yaxin Du↗Yifan Zhou↗Yujie Ge↗Jiajun Wang↗Xianghe Pang↗Shuo Tang↗Tuney Zheng↗Bryan Dai↗Jian Yang↗Siheng Chen↗

Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an execution-granularity mismatch: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce HyperTool, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69\% to 35.29\% on Qwen3-32B and from 9.93\% to 33.33\% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.13929

Self-Evolving Visual Questioner

作者:

Yijun Liang↗Hengguang Zhou↗Ming Li↗Lichen Li↗Cho-Jui Hsieh↗Tianyi Zhou↗

Vision-language models (VLMs) are typically trained as passive answerers, while their ability to actively ask diverse, non-trivial, visual-centric and grounded questions remains underexplored. Existing visual questioners' performance is bottlenecked by the availability of high-quality training data or the cost of curating them. We show that a VLM can continuously improve itself as a visual questioner without any external supervision. We propose a self-evolving framework that uses a VLM itself as both a proposer and a filter to produce harder, more informative, and visual-centric questions, while maintaining their exploration diversity to avoid training collapse. These questions are then used to train the VLM in both questioner and answerer modes. To evaluate the questioner, we introduce an agentic protocol that assesses questions along perception, reasoning, and diversity dimensions. Experiments across various backbone VLMs show that our method substantially enhances the quality and substantially expands the difficulty boundary of autonomous question generation. Under the same budget, our self-supervision is more effective than training on the static source data. Moreover, the self-evolving questioner remains a competitive or even better answerer.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2603.09377

SinGeo: Unlock Single Model's Potential for Robust Cross-View Geo-Localization

作者:

Yang Chen↗Xieyuanli Chen↗Junxiang Li↗Jie Tang↗Tao Wu↗

Robust cross-view geo-localization (CVGL) remains challenging despite the surge in recent progress. Existing methods still rely on field-of-view (FoV)-specific training paradigms, where models are optimized under a fixed FoV but collapse when tested on unseen FoVs and unknown orientations. This limitation necessitates deploying multiple models to cover diverse variations. Although studies have explored dynamic FoV training by simply randomizing FoVs, they failed to achieve robustness across diverse conditions – implicitly assuming all FoVs are equally difficult. To address this gap, we present SinGeo, a simple yet powerful framework that enables a single model to realize robust cross-view geo-localization without additional modules or explicit transformations. SinGeo employs a dual discriminative learning architecture that enhances intra-view discriminability within both ground and satellite branches, and is the first to introduce a curriculum learning strategy to achieve robust CVGL. Extensive evaluations on four benchmark datasets reveal that SinGeo sets state-of-the-art (SOTA) results under diverse conditions, and notably outperforms methods specifically trained for extreme FoVs. Beyond superior performance, SinGeo also exhibits cross-architecture transferability. Furthermore, we propose a consistency evaluation method to quantitatively assess model stability under varying views, providing an explainable perspective for understanding and advancing robustness in future CVGL research. Codes will be available upon acceptance.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2510.03584

FrameOracle: Learning What to See and How Much to See in Videos

作者:

Chaoyu Li↗Tianzhi Li↗Fei Tao↗Zhenyu Zhao↗Ziqian Wu↗Maozheng Zhao↗Juntong Song↗Cheng Niu↗Pooyan Fazli↗

Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in content density or task complexity. To address this, we present FrameOracle, a lightweight, plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained via a curriculum that progresses from weak proxy signals, such as cross-modal similarity, to stronger supervision with FrameOracle-41K, the first large-scale VideoQA dataset with validated keyframe annotations specifying minimal sufficient frames per question. Extensive experiments across five VLMs and six benchmarks show that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without accuracy loss. When starting from 64-frame candidates, it reduces inputs to 13.9 frames on average while improving accuracy by 1.5%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2503.07459

MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks

作者:

Yanjun Shao↗Xiangru Tang↗Jiwoong Sohn↗Jiapeng Chen↗Yuxuan Liao↗Jiayi Zhang↗Jinyu Xiang↗Fang Wu↗Yilun Zhao↗Chenglin Wu↗Wenqi Shi↗Arman Cohan↗…

Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: internalized reasoning and externalized agent scaffolding (frameworks that decompose problems collaboratively amongst multiple LLMs). To determine whether these routes are exclusive or complementary, we introduce MedicalAgentsBench, a filtered benchmark of 862 complex clinical questions drawn from the union of eight medical datasets via difficulty-aware curation and contamination screening. Evaluating three internalized reasoning models (DeepSeek-R1, o1-mini, and o3-mini), seven base models, and nine externalized agent-based methods, we find that internalized and externalized approaches each independently improve performance, and that their benefits compound: the highest accuracy is achieved by layering agent workflows onto an internalized reasoning model (i.e., o3-mini + MDAgents with 35.1%). Pareto analysis shows this combination dominates the cost-performance frontier; moreover, lightweight optimization on inexpensive models offers an entry point for resource-constrained settings. Our benchmark is at https://github.com/gersteinlab/MedicalAgentsBench.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11206

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models

作者:

Yucheng Zhou↗Junwei Sheng↗Qianning Wang↗Jianbing Shen↗

Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization. Recent work attributes this issue to pathological gradient scaling and proposes Dynamic Fine-Tuning (DFT) to correct it at the token level. However, DFT assumes all demonstrations are equally suitable learning targets, an assumption violated by the strong heterogeneity of large-scale instruction data, where demonstration-policy mismatch induces high-variance updates at the sample level. We introduce Compatibility-Aware Dynamic Fine-Tuning (CADFT), a principled extension of DFT that controls sample-level optimization variance. CADFT derives a dynamic, policy-dependent compatibility signal from model likelihoods to modulate supervised updates, suppressing high-variance gradients from incompatible demonstrations. We further propose a delayed, low-frequency compatibility-guided rewriting strategy to transform persistently incompatible demonstrations into learnable targets. We show that CADFT can be interpreted as a variance-controlled estimator that generalizes token-level stabilization in DFT to the sample level. Extensive experiments demonstrate improved stability, generalization, and cold-start reinforcement learning initialization, while remaining fully supervised and independent of explicit reward modeling.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19588

Analyzing the Narration Gap in LLM-Solver Loops

作者:

Zunchen Huang↗Songgaojun Deng↗

arXiv:2606.19588v1 Announce Type: new Abstract: Formal tools such as SAT and SMT solvers are increasingly embedded in language model reasoning pipelines when a safety or security critical question can be formulated in logic. Unlike chain of thought whose steps are sampled from the model distribution without formal guarantee, a solver produces a sound and independently verifiable answer. However, the soundness guarantee can be lost in the interaction between the solver and the model. The hybrid pipeline has three components: formalizing the question, deciding it, and narrating the result. Prior work has studied the formalization and decision, but not narration, which is the step that turns a formal tool's output into the user answer. To fill the narration gap, we first model the LLM-solver loop as a verified decision procedure. We further evaluate five open-sourced models under prompt injection, and we find certificate gating makes the solver verdict sound, while an adversary can invert a verified conclusion across phrasings and channels. We study the mitigation through hardened prompt that reduces injection significantly but cannot eliminate it and still suffers under adaptive attack. Combining the formal analysis and empirical studies, we show in the LLM-solver loop, robustness does not reach to the answer that the user finally reads.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2605.10840

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

作者:

Yixuan Yang↗Mehak Arora↗Ryan Zhang↗Baraa Abed↗Junseob Kim↗Tilendra Choudhary↗Md Hassanuzzaman↗Kevin Zhu↗Ayman Ali↗Chengkun Yang↗Alasdair Edward Gent↗Victor Moas↗…

arXiv:2605.10840v3 Announce Type: replace-cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation learning in vision, but extending the paradigm to EHR data – to obtain a single backbone that simultaneously forecasts patient trajectories and serves diverse downstream risk-prediction tasks without per-task fine-tuning – remains an open challenge. Existing JEPA frameworks either discard the predictor after pretraining (I-JEPA, V-JEPA) or train it on a frozen pretrained encoder (V-JEPA 2-AC), leaving the encoder unaware of the rollout signal that the retained predictor must use at inference; co-training the encoder and predictor under a shared JEPA prediction objective would supply this grounding, but naïve co-training is unstable, with representation collapse and online/target drift causing autoregressive rollout to diverge. Clin-JEPA's five-phase pretraining curriculum – predictor warmup, joint refinement, EMA target alignment, hard sync, and predictor finalization – addresses each failure mode by phase, stably co-training a Qwen3-8B-based encoder and a 92M-parameter latent trajectory predictor. On MIMIC-IV ICU data, three independent evaluations support the framework: (1) latent $\ell_1$ rollout drift uniquely converges ($-$15.7%) over 48-hour horizons while baselines and ablations diverge (+3% to +4951%); (2) the encoder learns a clinically discriminative latent geometry (deteriorating-patient cohorts displace 4.83$\times$ further than stable patients in latent space, vs $\leq$2.62$\times$ for baseline encoders); (3) a single backbone outperforms strong tabular and sequence baselines on multi-task downstream evaluation. Clin-JEPA achieves mean AUROC 0.851 on ICareFM EEP and 0.883 on 8 binary risk tasks (+0.038 and +0.041 vs baseline average).

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2509.12742

Effective Gaussian Management for High-fidelity Object Reconstruction

作者:

Jiateng Liu↗Hao Gao↗Jiu-Cheng Xie↗Chi-Man Pun↗Jian Xiong↗Haolun Li↗Junxin Chen↗Feng Xu↗

This paper proposes an effective Gaussian management framework for high-fidelity scene reconstruction of both appearance and geometry. Unlike recent Gaussian Splatting (GS) pipelines that treat all primitives uniformly during optimization, our framework explicitly manages the attribute activation, representation and pruning of Gaussian. Specifically, our framework first introduces GauSep, a novel densification strategy that selectively activates Gaussian color or normal attributes to alleviate destructive gradient conflicts arising from dual supervision. We further propose GauRep, an adaptive Gaussian representation that dynamically adjusts spherical harmonics (SHs) orders and performs task-decoupled pruning to reduce redundancy at both the individual and global levels. To provide reliable geometric supervision for above mangement process, we additionally introduce CoRe, an regularized surface reconstruction module that distills robust normal fields from an SDF branch to the Gaussian representation through a confidence mechanism. Notably, the proposed Gaussian management is compatible with various reconstruction architectures and can be seamlessly integrated to improve performance while reducing size of the model. Extensive experiments demonstrate that our approach achieves superior or comparable performance in appearance and geometry reconstruction compared with state-of-the-art methods, while using significantly fewer parameters.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18709

LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment

作者:

Han Chen↗Ming Li↗Chenguang Wang↗Yijun Liang↗Dawei Zhou↗Hong jiao↗Tianyi Zhou↗

Item discrimination is a fundamental psychometric property of educational assessment, which measures whether an item meaningfully distinguishes students with higher proficiency from students with lower proficiency. While various existing works have explored whether large language models (LLMs) can estimate item difficulty, it remains unclear whether they can capture item discrimination. In this work, we evaluate 42 proprietary and open-weight LLMs in zero-shot settings using two complementary approaches: direct discrimination prediction, where models explicitly estimate an item's discrimination value from its content, and response-based Classical Test Theory (CTT) calibration, where LLM answers are treated as synthetic student responses to compute discrimination scores. Our results show that direct prediction yields weak alignment with human-calibrated discrimination: the best-performing model reaches only a Spearman correlation of 0.152. Response-based CTT calibration provides a stronger but still limited signal, with the all-persona synthetic respondent pool reaching a Spearman correlation of 0.241. These findings highlight item discrimination as an open challenge for LLM-based psychometric evaluation: current LLMs contain non-random discrimination-relevant signal, but they do not yet reliably capture how assessment items distinguish human students.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2601.18692

A Pragmatic VLA Foundation Model

作者:

Wei Wu↗Fan Lu↗Yunnan Wang↗Shuai Yang↗Shi Liu↗Fangjing Wang↗Qian Zhu↗He Sun↗Yong Wang↗Shuailei Ma↗Yiyu Ren↗Kejia Zhang↗…

Offering great potential in robotic manipulation, a capable Vision-Language-Action (VLA) foundation model is expected to faithfully generalize across tasks and platforms while ensuring cost efficiency (e.g., data and GPU hours required for adaptation). To this end, we develop LingBot-VLA with around 20,000 hours of real-world data from 9 popular dual-arm robot configurations. Through a systematic assessment on 3 robotic platforms, each completing 100 tasks with 130 post-training episodes per task, our model achieves clear superiority over competitors, showcasing its strong performance and broad generalizability. We have also built an efficient codebase, which delivers a throughput of 261 samples per second with an 8-GPU training setup, representing a 1.5~2.8$\times$ (depending on the relied VLM base model) speedup over existing VLA-oriented codebases. The above features ensure that our model is well-suited for real-world deployment. To advance the field of robot learning, we provide open access to the code, base model, and benchmark data, with a focus on enabling more challenging tasks and promoting sound evaluation standards.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.08525

DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving

作者:

Qimao Chen↗Fang Li↗Yuechen Luo↗Zehan Zhang↗Haiyang Sun↗Fangzhen Li↗Bing Wang↗Guang Chen↗Yang Ji↗Jiong Deng↗Hongwei Xie↗Hangjun Ye↗…

Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance, and augmented with counterfactual driving behaviors., (2) alongside a specialized Vision-Language Reward Model. To address the scarcity of failure cases in conventional datasets, we propose a counterfactual data annotation scheme to construct cases encompassing diverse driving styles and erroneous behaviors. Evaluations on our proposed benchmark reveal that even leading open-source and proprietary VLMs fail to excel across all tasks, highlighting significant room for improvement in existing models. Building on these findings, we subsequently tailor a specialized 1B reward model that outperforms larger VLMs on task-specific reward alignment. Finally, we validate our reward model's effectiveness by integrating it into RL finetuning and multi-modal trajectory scoring across multiple baselines, achieving performance comparable to rule-based reward calculations in both open-loop and closed-loop evaluation.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2605.21850

ACC: Compiling Agent Trajectories for Long-Context Training

作者:

Qisheng Su↗Zhen Fang↗Shiting Huang↗Yu Zeng↗Yiming Zhao↗Kou Shi↗Ziao Zhang↗Lin Chen↗Zehui Chen↗Lijun Wu↗Feng Zhao↗

Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce massive trajectories when solving problems, invoking tools and receiving environment observations across many turns. The evidence needed to answer the original question is thus scattered throughout these turns, requiring integration of distant context segments. Nevertheless, standard agent SFT masks tool responses and only trains turn-level tool selection, creating a supervision blind spot where these scattered signals go unused. We propose Agent Context Compilation (ACC), which converts trajectories from search, software engineering, and database querying agents into long-context QA pairs that combine the original question with tool responses and environment observations gathered across multiple turns, training the model to answer directly without tool use. This makes the dependencies between the question and the evidence explicit, enabling direct supervision of long-context reasoning over distant segments without additional annotation. ACC is a simple but effective approach that can be combined with any existing long-context extension or training method, providing scalable supervised fine-tuning data. We validate ACC on long-range dependency modeling tasks through MRCR and GraphWalks, challenging benchmarks requiring cross-turn coreference resolution and graph traversal over extended contexts. Training Qwen3-30B-A3B with ACC achieves 68.3 on MRCR (+18.1) and 77.5 on GraphWalks (+7.6), results comparable to Qwen3-235B-A22B, while preserving general capabilities on GPQA, MMLU-Pro, AIME, and IFEval. Further mechanism analysis reveals that the ACC-trained model exhibits task-adaptive attention restructuring and expert specialization.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11814

Sparsified Kolmogorov-Arnold Networks for Interpretable Quantum State Tomography

作者:

Xinge Wu↗Huaxin Wang↗Jiajun Liu↗Ruiqing He↗Jiandong Shang↗Hengliang Guo↗Qiang Chen↗

arXiv:2606.11814v1 Announce Type: cross Abstract: Machine-learning approaches to quantum state tomography can achieve high reconstruction fidelity, but the physical structure used by the trained model often remains implicit. Here we ask whether a sparsified Kolmogorov-Arnold Network (KAN) can be used not only as a regressor, but also as an inspectable reconstruction rule whose internal organization can be checked against known Pauli structure. We study a controlled three-qubit GHZ-family benchmark in which all 63 non-identity Pauli expectation values are used to reconstruct three GHZ-subspace variables: the population imbalance $z$, the real off-diagonal component $c$, and the imaginary off-diagonal component $s$. Under finite-shot sampling and depolarizing noise, external ablation identifies the extended 12-channel GHZ-relevant Pauli set from the 63 measurements, with exact top-12 recovery across the tested shot counts and depolarizing-noise strengths. These support patterns remain stable across multi-seed random-initialization and noise-level analyses, and collapse under random-label controls. The dominant pruned input-hidden-output pathways organize Z-type population observables and X/Y off-diagonal observables in a pattern consistent with the analytic GHZ Pauli grouping, and sparse formula recovery recovers the canonical signed Pauli relations. The contribution of the KAN is therefore pathway-level structural interpretability within a neural reconstruction model, rather than superior sparse regression. Together with negative controls, these probes provide a consistency chain for auditing learned reconstruction rules against known physical structure.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2602.12279

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

作者:

Leon Liangyu Chen↗Haoyu Ma↗Zhipeng Fan↗Ziqi Huang↗Animesh Sinha↗Xiaoliang Dai↗Jialiang Wang↗Zecheng He↗Jianwei Yang↗Chunyuan Li↗Junzhe Sun↗Chu Wang↗…

Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving complex spatial compositions, multiple interacting objects, or evolving instructions, require decomposing instructions, verifying intermediate results, and making iterative corrections. While test-time scaling (TTS) has demonstrated that allocating additional inference compute for iterative reasoning substantially improves language model performance, extending this paradigm to unified multimodal models remains an open challenge. We introduce UniT, a framework for multimodal chain-of-thought test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds. UniT combines agentic data synthesis, unified model training, and flexible test-time inference to elicit cognitive behaviors including verification, subgoal decomposition, and content memory. Our key findings are: (1) unified models trained on short reasoning trajectories generalize to longer inference chains at test time; (2) sequential chain-of-thought reasoning provides a more scalable and compute-efficient TTS strategy than parallel sampling; (3) training on generation and editing trajectories improves out-of-distribution visual reasoning. These results establish multimodal test-time scaling as an effective paradigm for advancing both generation and understanding in unified models.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16295

VisualClaw: A Real-Time, Personalized Agent for the Physical World

作者:

Haoqin Tu↗Jianwen Chen↗Zijun Wang↗Siwei Han↗Juncheng Wu↗Hardy Chen↗Haonian Ji↗Kaiwen Xiong↗Jiaqi Liu↗Peng Xia↗Jieru Mei↗Hongliang Fei↗…

Vision language models are serving as general-purpose interfaces for complex multimodal tasks. However, deployment still faces three gaps: VLMs typically incur high latency and cost when processing dense video frames and long prompts, the agent scaffold remains static after deployment, and standard video-QA benchmarks do not test whether agents can use visual evidence inside tool-using workspaces. We present VisualClaw, a self-evolving multimodal agent built around two principles. First, hybrid encoding reduces deployment cost by filtering less informative streaming frames with a cascaded gate and compressing the text skill bank through hot/cold top-k injection. Second, skill evolution lets the agent learn from failures: retrieved memories condition an evolver as direct concatenated context or as guided evidence, producing skill-bank updates that help future questions. Across 4 video-QA benchmarks with 2 VLMs, VisualClaw cuts per-question API cost by an average -98% versus full-frame upload and by -25.9% over the offline uniform 8 frame baseline, while boosting accuracy in most settings, e.g., an average +3.85% and a peak +15.80% on EgoSchema with Gemini 3 Flash. To address the gap, we curate VisualClawArena, a 200-scenario multimodal agentic benchmark built through a strict five-stage pipeline; models must use video evidence, documents, dynamic updates, and executable checks inside a workspace. On VisualClawArena, the same framework with computer-use agent backends improves macro accuracy by +2.9% for Codex (GPT-5.5) and +3.2% for Claude Code (Sonnet 4.6) over no-evolution baselines, with a -9.5% cost reduction compared to the uniform-sampled baseline. These properties make VisualClaw a natural fit for edge applications, where the cascade reduces a 1-hour streaming session from ~3,600 API uploads down to only 5-20 calls and the self-evolution makes it a perfect personalized assistant.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15007

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

作者:

NVIDIA↗Aaron Blakeman↗Aaron Thomas↗Aastha Jhunjhunwala↗Abhibha Gupta↗Abhinav Khattar↗Adam Rajfer↗Adi Renduchintala↗Adil Asif↗Aditya Vavre↗Adriana Flores Miranda↗Ahmad Bilal↗…

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2512.20043

Discovering Symmetry Groups with Flow Matching

作者:

Yuxuan Chen↗Jung Yeon Park↗Floor Eijkelboom↗Jianke Yang↗Jan-Willem van de Meent↗Lawson L. S. Wong↗Robin Walters↗

arXiv:2512.20043v3 Announce Type: replace Abstract: Symmetry is fundamental to understanding physical systems and can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data, yet discovering these symmetries automatically is challenging. We propose LieFlow, a novel framework that reframes symmetry discovery as a distribution learning problem on Lie groups. Instead of searching for the symmetry generators, our approach operates directly in group space, modeling a symmetry distribution over a large hypothesis group $G$. The support of the learned distribution reveals the underlying symmetry group $H \subseteq G$. Unlike previous works, LieFlow can discover both continuous and discrete symmetries within a unified framework, without assuming a fixed Lie algebra basis or a specific distribution over the group elements. Experiments on synthetic 2D and 3D point clouds, ModelNet10 and a real-world MI-Motion dataset show that LieFlow accurately discovers continuous and discrete subgroups, significantly outperforming a state-of-the-art baseline, LieGAN, in identifying discrete symmetries.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.12670

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

作者:

Xiangyi Li↗Yimin Liu↗Wenbo Chen↗Bingran You↗Zonglin Di↗Yifeng He↗Shenghan Zheng↗Kyoung Whan Choe↗Jiankai Sun↗Shuyi Wang↗Chujun Tao↗Binxu Li↗…

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2511.13271

Examining the Usage of Generative AI Models in Student Learning Activities for Software Programming

作者:

Rufeng Chen↗Shuaishuai Jiang↗Jiyun Shen↗AJung Moon↗Lili Wei↗

arXiv:2511.13271v2 Announce Type: replace-cross Abstract: The rise of Generative AI (GenAI) tools like ChatGPT has created new opportunities and challenges for computing education. Existing research has primarily focused on GenAI's ability to complete educational tasks and its impact on student performance, often overlooking its effects on knowledge gains. In this study, we investigate how GenAI assistance compares to conventional online resources in supporting knowledge gains across different proficiency levels. We conducted a controlled user experiment with 24 undergraduate students of two different levels of programming experience (beginner, intermediate) to examine how students interact with ChatGPT while solving programming tasks. We analyzed task performance, conceptual understanding, and interaction behaviors. Our findings reveal that generating complete solutions with GenAI significantly improves task performance, especially for beginners, but does not consistently result in knowledge gains. Importantly, usage strategies differ by experience: beginners tend to rely heavily on GenAI toward task completion often without knowledge gain in the process, while intermediates adopt more selective approaches. We find that both over-reliance and minimal use result in weaker knowledge gains overall. Based on our results, we call on students and educators to adopt GenAI as a learning rather than a problem solving tool. Our study highlights the urgent need for guidance when integrating GenAI into programming education to foster deeper understanding.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2508.02721

Blueprint First, Model Second: A Framework for Deterministic LLM Workflow

作者:

Libin Qiu↗Yuhang Ye↗Zhirong Gao↗Xide Zou↗Junfu Chen↗Ziming Gui↗Weizhi Huang↗Xiaobo Xue↗Wenkai Qiu↗Kun Zhao↗

arXiv:2508.02721v2 Announce Type: replace-cross Abstract: While powerful, the inherent non-determinism of large language model (LLM) agents limits their application in structured operational environments where procedural fidelity and predictable execution are strict requirements. This limitation stems from current architectures that conflate probabilistic, high-level planning with low-level action execution within a single generative process. To address this, we introduce the \textsc{Source Code Agent} framework, a new paradigm built on the ``Blueprint First, Model Second'' philosophy that decouples workflow logic from the generative model. An expert-defined operational procedure is first codified into a source code-based Execution Blueprint, which is then executed by a deterministic engine. The LLM is strategically invoked as a specialized tool to handle bounded, complex sub-tasks within the workflow, but never to decide the workflow's path. We evaluate on the TravelPlanner benchmark for constraint-aware travel planning. The \textsc{Source Code Agent} achieves a 35.56\% final pass rate, a 97.6\% improvement over the state-of-the-art ATLAS baseline (18.00\%) on the same Claude-Sonnet-4 backbone. Critically, it reduces constraint violations by 96.0\% (11 vs 275) while improving execution efficiency by 27.1\% (10.2$\pm$0.7 steps vs 14.0). Two production incident-diagnosis deployments and additional results on ScienceWorld and ALFWorld confirm that the architecture transfers beyond travel planning to procedurally well-defined, constraint-intensive workflows. Our work enables the verifiable and reliable deployment of autonomous agents in applications governed by strict procedural logic.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2602.14771

GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecture

作者:

Shih-Fang Chen↗Jun-Cheng Chen↗I-Hong Jhuo↗Yen-Yu Lin↗

The human visual system tracks objects by integrating current observations with previously observed information, adapting to target and scene changes, and reasoning about occlusion at fine granularity. In contrast, recent generic object trackers are often optimized for training targets, which limits robustness and generalization in unseen scenarios, and their occlusion reasoning remains coarse, lacking detailed modeling of occlusion patterns. To address these limitations in generalization and occlusion perception, we propose GOT-JEPA, a model-predictive pretraining framework that extends JEPA from predicting image features to predicting tracking models. Given identical historical information, a teacher predictor generates pseudo-tracking models from a clean current frame, and a student predictor learns to predict the same pseudo-tracking models from a corrupted version of the current frame. This design provides stable pseudo supervision and explicitly trains the predictor to produce reliable tracking models under occlusions, distractors, and other adverse observations, improving generalization to dynamic environments. Building on GOT-JEPA, we further propose OccuSolver to enhance occlusion perception for object tracking. OccuSolver adapts a point-centric point tracker for object-aware visibility estimation and detailed occlusion-pattern capture. Conditioned on object priors iteratively generated by the tracker, OccuSolver incrementally refines visibility states, strengthens occlusion handling, and produces higher-quality reference labels that progressively improve subsequent model predictions. Extensive evaluations on seven benchmarks show that our method effectively enhances tracker generalization and robustness.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14383

IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products

作者:

Haonan Qi↗Jin Cao↗Yongqi Zhang↗Xintong Wang↗Weidong Tang↗Bin Chen↗Chengfu Huo↗Haojun Pan↗Hengyu You↗Jing Li↗Yingde Wang↗Liang Ding↗…

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction – recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86–94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15–34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

阅读与讨论 → 访问原文 →

24.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2512.06718

Witnessing Spin-Orbital Entanglement using Resonant Inelastic X-Ray Scattering

作者:

Zecheng Shen↗Shuhan Ding↗Zijun Zhao↗Francesco A. Evangelista↗Yao Wang↗

arXiv:2512.06718v2 Announce Type: replace Abstract: Entanglement plays a central role in quantum technologies, yet its characterization and control in materials remain challenging. Recent developments in spectrum-based entanglement witnesses have enabled new strategies for quantifying many-body entanglement in macroscopic materials. Here, we develop a protocol for detecting spin-orbital entanglement using experiment-accessible resonant inelastic x-ray scattering (RIXS). Central to our approach is the construction of a Hermitian generator from experimentally measurable spectra, which allows us to compute the quantum Fisher information (QFI) available in spin–orbital systems. The resulting QFI provides upper bounds for $k$-producible states and thus serves as a robust witness of spin-orbital entanglement. To account for realistic experimental limitations, we further extend our framework to include relaxed QFI bounds applicable to measurements lacking full polarization resolution.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14259

Beyond a Single Explanation of the Adam–SGD Gap

作者:

Chenxiang Zhang↗Rustem Islamov↗Enea Monzio Compagnoni↗Jun Pang↗Aurelien Lucchi↗Antonio Orvieto↗

arXiv:2606.14259v1 Announce Type: new Abstract: Prior work has identified several factors that can contribute to the performance gap between Adam and SGD, spanning data aspects, architecture design, and optimization properties. Yet these explanations are often studied in isolation, leaving their relative importance unclear. In this work, we revisit these hypotheses through a controlled empirical study across vision, language, genomics, and graph tasks, spanning modern and classical architectures, and carefully designed training setups. Our results suggest that no single factor consistently explains the Adam–SGD gap. For instance, the Adam advantage can (1) persist under a uniform vocabulary distribution yet nearly disappear under a heavy-tailed one; (2) reverse in favor of SGD in softmax-attention models; and (3) become larger under soft architectural modifications, e.g., when ReLU is replaced by a GeLU nonlinearity. This suggests that the gap arises from nontrivial data and architecture interactions, rather than from a single common factor. Yet, we observe a pattern across our settings: a crossover batch size at which the relative advantage shifts from SGD to Adam as the batch size scales. These empirical results are captured by our theoretical gap model, which predicts this batch-size-dependent crossover. Our perspective helps reconcile several existing hypotheses while offering practical insights across domains.

阅读与讨论 → 访问原文 →