×

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

作者: Wu Liu ×
换一批
01.
arXiv (quant-ph) 2026-06-16

3D Ising criticality with Platonic lattice superconducting qubits

arXiv:2606.16854v1 Announce Type: new Abstract: The three-dimensional (3D) Ising model is a foundational model in statistical physics and critical phenomena, yet its analytical intractability has long impeded the precise determination of universal critical exponents. While high-precision estimates have been obtained through classical numerical methods and conformal bootstrap techniques, a direct quantum simulation of the 3D Ising criticality remains challenging, requiring nontrivial connectivity, sufficient system size, and high spectral resolution. In this work, assisted by the state-operator correspondence of conformal field theory, we perform a digital quantum simulation of the 3D Ising critical exponents using a multiply-connected 9-qubit superconducting quantum processor with a Platonic lattice geometry. Employing an extended variational quantum eigensolver equipped with a phase-based loss function, we variationally prepare the low-energy eigenstates of the transverse-field Ising model on a cubic Platonic lattice encoded in an 8-qubit register. The four lowest eigenenergies are extracted via Fourier-transform analysis and high-precision numerical fitting, agreeing with the exact diagonalization values up to +/- 0.001. The resulting scaling dimension Delta_epsilon = 1.5850 and critical exponent nu = 0.7067 match well with theory.

02.
arXiv (CS.AI) 2026-06-15

Communication Policy Evolution for Proactive LLM Agents

arXiv:2606.14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.

03.
arXiv (CS.CL) 2026-06-11

Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical judgment while patients increasingly use them for health advice. We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer. We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it. MedMisBench contains 10,932 medical question items and 48,889 misleading context-option pairs spanning medical reasoning, agentic capability, and patient-journey evaluation. Across 11 model configurations, mean accuracy falls from 71.1% on original questions to 38.0% under focused misleading context, with 51.5% attack success. The most damaging injections are formal, rule-like fabrications: authority-framed falsehoods reach 69.5% attack success and exception-poisoning claims reach 64.1%. A 14-member clinical panel from 7 countries identified serious potential harm in 38.2% of reviewed cases. MedMisBench exposes a structural blind spot in LLM evaluation in medical settings: existing benchmarks measure what models know, but not whether they preserve correct medical judgment under misleading context.

04.
arXiv (quant-ph) 2026-06-17

Fabless Quantum Chip Design and Commercial Production

arXiv:2606.17956v1 Announce Type: new Abstract: This paper proposes a fabless quantum-chip design and production architecture for superconducting quantum computing, centered on the SPICE-Q multiphysics simulation framework. The proposed ecosystem connects process-certified quantum PDKs, parameterized device cells, traceable model cards, SPICE-Q physical modeling languages, unified Q-EDA flows, foundry sign-off rules, cryogenic test feedback, and reusable quantum IP. In this model, design firms do not merely outsource fabrication; they prepare verified tape-outs under standardized process constraints and calibrated physical models. Its economic value lies in reducing repetitive device debugging, process exploration, and low-level layout effort, while its feasibility depends on PDK maturity, foundry yield, cryogenic test throughput, model-prediction accuracy, data-feedback mechanisms, and IP licensing boundaries. We argue that superconducting quantum chips can move from the current largely vertically integrated development model toward a fabless-foundry ecosystem only when hardware design is supported by standardized, verifiable, and reusable software and process interfaces. The required pillars are certified PDKs, PCell-based parameterized design, SPICE-Q cross-physics simulation, end-to-end Q-EDA automation, and a tradable quantum-IP market. By adapting lessons from the classical semiconductor industry to quantum hardware, this framework defines a path toward scalable, manufacturable, and commercially reusable superconducting quantum-chip design.

05.
arXiv (CS.AI) 2026-06-16

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

arXiv:2602.06486v2 Announce Type: replace Abstract: Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-as-a-judge approaches adapt to individual responses yet suffer from instability and bias. Human experts address this dilemma by combining domain-grounded principles with dynamic, claim-level assessment. Inspired by this process, we propose JADE, a two-layer evaluation framework. Layer 1 encodes expert knowledge as a predefined set of evaluation skills, providing stable evaluation criteria. Layer 2 performs report-specific, claim-level evaluation to flexibly assess diverse reasoning strategies, with evidence-dependency gating to invalidate conclusions built on refuted claims. Experiments on BizBench show that JADE improves evaluation stability and reveals critical agent failure modes missed by holistic LLM-based evaluators. We further demonstrate strong alignment with expert-authored rubrics and effective transfer to HealthBench and DR.BENCH, covering medical and 10-domain professional evaluation settings. Code and data are available at https://github.com/smiling-world/JADE.

06.
arXiv (quant-ph) 2026-06-19

Single-Step Phase-Engineered Pulse for Active Readout Cavity Reset in Superconducting Circuits

arXiv:2512.08393v2 Announce Type: replace Abstract: In a circuit QED architecture, we experimentally demonstrate a hardware-efficient and qubit-state-dependent Single-Step Phase-Engineered (SSPE) pulse scheme for actively depopulating a readout cavity. The protocol appends a reset segment with tailored amplitude and phase to a standard square readout pulse. Within the linear-response regime, the optimal reset amplitude scales proportionally with the readout amplitude, while the optimal reset phase remains invariant, significantly simplifying the experimental calibration procedure. Time-resolved measurements of the cavity photon number dynamics demonstrate that the SSPE scheme significantly outperforms the CLEAR protocol in terms of reset speed. Crucially, this approach enables arbitrarily fast, overshoot-free depletion of the cavity photon population, with the ultimate reset rate constrained by the finite analog bandwidth of the measurement chain. Furthermore, a comprehensive evaluation of the QND nature demonstrates that the SSPE scheme introduces no additional non-QND measurement errors. It exhibits non-QNDness comparable to both the free-decay and CLEAR protocols, with residual errors predominantly governed by state switching induced by qubit relaxation during the readout process. Thses results establish the SSPE scheme as a practical and scalable approach for achieving rapid and smooth cavity reset in superconducting quantum circuits.

07.
arXiv (CS.CV) 2026-06-18

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios. To address these challenges, we propose an instruction-driven agentic framework comprising three components. First, LandslideBench, a multimodal fine-grained dataset with seven subtype labels, high-resolution imagery, pixel-level masks, and high-quality textual descriptions, is constructed via multi-VLM cross-validation and interactive annotation. Then, LandslideVLM, a landslide-oriented VLM, is fine-tuned via LoRA on LandslideBench to enhance geological semantic understanding. Finally, LandslideAgent, a domain rule-enhanced agent taking LandslideVLM as its cognitive backbone, employs a dual-rule controller incorporating structured report metadata constraints and cross-validation identification constraints to regulate automated tool invocation. Experiments demonstrate that LandslideBench provides effective baselines across five mainstream models on fine-grained classification and semantic segmentation. LandslideVLM achieves accuracy improvements of 10.96%, 32.87%, and 15.91% on landslide discrimination, fine-grained classification, and semantic description quality, respectively. LandslideAgent further enables autonomous multi-source spatial data inference, realizing full-process intelligence for landslide identification and analysis.

08.
arXiv (CS.AI) 2026-06-19

StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation

arXiv:2606.20005v1 Announce Type: cross Abstract: Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training. However, existing approaches materialize both attention distributions before computing the KL reduction, incurring $O(N_QN_K)$ memory and IO costs that become prohibitive at long context lengths. We present StreamKL, the first fused GPU primitive for attention KL divergence that eliminates this quadratic materialization. StreamKL derives a novel online formulation for the coupled two-distribution KL reduction, enabling a single one-pass forward kernel that streams query-key tiles through on-chip SRAM. For the backward pass, StreamKL recomputes attention probabilities tile-by-tile, avoiding storage of quadratic intermediates. We further design and implement efficient GPU kernels with dedicated optimizations. Experiments show StreamKL delivers up to $43\times$ and $14\times$ speedups over baseline methods in the forward and backward passes, respectively. Most importantly, StreamKL reduces the extra HBM footprint of attention distillation from $O(N_QN_K)$ to $O(1)$, enabling long-context distillation on a single GPU.

09.
arXiv (CS.CV) 2026-06-17

NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results

This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

10.
arXiv (CS.AI) 2026-06-17

StepGuard: Guarding Web Navigation via Single-Step Calibration

arXiv:2606.17871v1 Announce Type: new Abstract: Web navigation requires agents to follow natural language goals, interact with web pages, and produce accurate answers. While recent advances leverage vision-language models and reinforcement learning, existing methods still suffer from single-step fragility due to reward misalignment and error propagation. To tackle the reward entanglement, we design Dynamic Dual-Policy Optimization (DDPO), which dynamically switches between a navigation-first mode for exploration and an answer-first mode for question-answering to mitigate reward conflict. To calibrate the single-step error, we propose Confidence-Guided Adaptive Navigation Reflection (CANR), a mechanism that estimates per-step confidence, triggers reflection only when necessary, and uses contrastive rewards to encourage self-correction to calibrate the single-step inaccuracy. With the above as the main components, we finally develop our StepGuard, a new framework of Guarding Web Navigation via Single-Step Calibration. Experiments demonstrate that our approach significantly improves navigation and answer accuracy, setting new state-of-the-art performance on standard web navigation benchmarks.

11.
arXiv (CS.CV) 2026-06-15

A Pragmatic VLA Foundation Model

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.

12.
arXiv (CS.CL) 2026-06-12

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

13.
arXiv (CS.AI) 2026-06-19

SIMBA: ABidirectional Retrieval Forward Simulation Framework for Modeling FY-4A GIIRS Hyperspectral Infrared Radiances Toward NWP Applications

arXiv:2606.19943v1 Announce Type: cross Abstract: Hyperspectral infrared observations are an important data source for numerical weather prediction (NWP) because they provide rich information on the vertical structure of atmospheric temperature and humidity. However, most existing deep learning methods mainly focus on one-way retrieval from radiances to atmospheric profiles, while the reverse radiance simulation process and the consistency between atmospheric state space and radiance observation space are insufficiently considered. In this study, we propose SIMBA, a unified bidirectional retrieval-forward simulation framework for FY-4A GIIRS hyperspectral infrared radiance modeling toward NWP applications. The framework jointly performs atmospheric profile retrieval and radiance reconstruction, introduces a cycle-consistency constraint to strengthen the coupling between the two processes, and employs a bidirectional Mamba state-space module to capture long-range dependencies along pressure levels. Using collocated FY-4A GIIRS observations and ERA5 reanalysis data, the proposed method is evaluated for temperature retrieval, specific humidity retrieval, long-wave radiance reconstruction, and medium-wave radiance reconstruction. Experimental results show that SIMBA outperforms several representative deep learning baselines across both retrieval and reconstruction tasks, while ablation experiments confirm the contribution of the bidirectional design and cycle-consistency mechanism. These results demonstrate that the proposed framework is effective for joint atmospheric profile retrieval and hyperspectral infrared radiance modeling, and suggest potential for future Jacobian-related analysis and NWP-oriented extensions.

14.
arXiv (quant-ph) 2026-06-12

Asymmetric quantum steering harvested near a Lorentz-violating BTZ black hole

arXiv:2606.12766v1 Announce Type: cross Abstract: We investigate the harvesting of quantum steering and its directional asymmetry between two Unruh-DeWitt detectors in a Lorentz-violating BTZ black hole spacetime. Since the detectors are located at different radial positions outside the black hole, they experience inequivalent local environments induced by gravitational redshift, causing Alice to undergo stronger effective thermal noise than Bob. Remarkably, we uncover a counterintuitive phenomenon in which the detector subjected to a higher effective temperature exhibits stronger steerability than the other one, revealing a nontrivial inversion of thermal intuition in curved spacetime. Furthermore, quantum steering survives only within a finite window of detector energy gaps and reaches its maximum within an optimal regime. We find that Lorentz violation suppresses steering most strongly near this optimal energy gap, indicating an enhanced sensitivity of maximal correlation extraction to symmetry breaking effects. Our results demonstrate that Lorentz violation acts as a geometric constraint on the quantum information capacity of spacetime, simultaneously restricting both the strength and the directionality of quantum correlations.

15.
arXiv (CS.CV) 2026-06-17

Enhancing Pathological VLMs with Cross-scale Reasoning

Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from global tissue architecture at low magnification to cellular morphology at higher magnification for accurate diagnosis. While existing pathological datasets for vision-language model (VLM) include various scales, they often lack an explicit cross-scale reasoning objective. This limitation prevents VLMs from capturing essential cross-scale representations and learning evidence-based reasoning. To bridge this gap, we introduce the first cross-scale training and evaluation paradigm that formulates pathology interpretation as multi-magnification reasoning. However, creating such a task reveals a critical challenge: multi-image visual question answering (VQA) is prone to text-only shortcuts, which allow models to guess answers using magnification-dependent artifacts rather than visual evidence. To address this, we propose a leakage-aware curation pipeline that combines adversarial text-only screening with constraint-guided question design. Using this pipeline, we construct Scale-VQA, a high-quality benchmark with 4,685 multiple-choice questions grounded in 2,537 pathology images across multiple magnification levels. Finally, we present ScaleReasoner-R1, a model trained via reinforcement learning to optimize performance on the cross-scale VQA task. ScaleReasoner-R1 achieves state-of-the-art performance on our cross-scale reasoning benchmark and generalizes to SOTA performance on established single-scale benchmarks. Findings suggest that even the limited cross-scale supervision can significantly improve pathological understanding. The code and demos will be open-sourced.

16.
arXiv (CS.CV) 2026-06-19

Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models

Evaluating video generation with clean, pixel-based reward models disconnects evaluation from the noisy diffusion process and incurs massive VAE decoding costs. In this paper, we challenge this paradigm by asking a fundamental question: Can a powerful video generator inherently discriminate preferences directly from noisy latents? To answer this, we introduce PRISM (Preference Representation in Intermediate States of Diffusion Models). PRISM employs a lightweight Query-based Aggregation head with a frozen video diffusion backbone to decode preference signals from noisy latents. Surprisingly, PRISM not only achieves SOTA preference accuracy but also unlocks strong noise-robustness, which enables early-stage Best-of-$N$ sampling. This allows for filtering suboptimal candidates at the very beginning of denoising, drastically reducing computation while boosting video quality. We also reveal a strong positive correlation between a backbone's generative performance and its inherent evaluative power, enabling self-improving video backbones.

17.
arXiv (CS.CL) 2026-06-11

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

18.
arXiv (CS.AI) 2026-06-16

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

arXiv:2606.01365v2 Announce Type: replace Abstract: Failure-aware observability diagnoses wasted computation in multi-agent LLM systems before final-answer evaluation can explain what went wrong. We propose a trace-based framework for a three-agent architecture – orchestrator, search agent, and execution agent – that converts structured events into online signals for loops, budget pressure, low information gain, and tool instability, then adds offline semantic grounding metrics and selective LLM-as-judge evaluation. On 165 GAIA validation traces under identical caps, 98 runs produce usable final answers and 67 fail or stop without one. Among warned failed runs, 58.1% of tokens are spent after the first warning on average, indicating substantial opportunity for intervention. A 10-task Level-2 pilot uses warnings to diversify search or require evidence, reducing post-warning token fraction from 0.638 in the baseline to 0.304. The results support a layered design: cheap online signals help the orchestrator redirect or halt redundant behavior, while deeper semantic checks identify whether completed answers are grounded enough to trust.

19.
arXiv (CS.AI) 2026-06-16

RollArt: Disaggregated Multi-Task Agentic RL Training at Scale

arXiv:2512.22560v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU-heavy environment execution, and bursty reward evaluation. Existing systems either colocate all stages on a single GPU cluster or decouple them only at a coarse granularity, overlooking hardware heterogeneity and incurring substantial synchronization overhead across stages. We present ROLLART, a system for multi-task agentic RL on disaggregated infrastructure. ROLLART maps each pipeline stage to best-fit hardware, routing prefill-heavy tasks to compute-optimized GPUs, decode-heavy tasks to bandwidth-optimized GPUs, and environments to CPU clusters. It decouples rollout at the trajectory level, allowing generation, environment interaction, and reward scoring to proceed independently, so that slow or failed environments never block the others. ROLLART offloads stateless reward computation to serverless infrastructure and overlaps rollout with training via staleness-bounded asynchronous weight synchronization. Our results demonstrate that ROLLART effectively improves training throughput and achieves 1.31–2.05 \(\times\) training time reduction compared to various RL systems. We also evaluated ROLLART by training a hundreds-of-billions-parameter MoE model for Qoder product on an Alibaba cluster with above 3,000 GPUs, demonstrating its stability and scalability.

20.
arXiv (quant-ph) 2026-06-16

Preparation of Fractional Quantum Hall States on Quantum Computers

arXiv:2606.16548v1 Announce Type: new Abstract: The realization of fractional quantum Hall (FQH) states, characterized by fractional charge and intrinsic topological order, on quantum computers represents a central challenge at the interface of condensed matter physics and quantum information science. Current methods are grouped into two types: methods based on (quasi-)adiabatic evolution of complex parent Hamiltonians to yield target states, and circuit-based approaches for direct state preparation, which are confined to effectively one-dimensional systems near the thin cylinder or torus limit. We introduce a complementary scheme relying on direct quantum circuit construction, which works for arbitrary geometries. Specifically, we present a method to precisely prepare the $\nu=1/3$ Laughlin state on the sphere geometry and demonstrate that it significantly reduces the required number of two-qubit gates and circuit depth, compared to variational quantum circuit approaches. In addition, we employ optimal control techniques to design control pulses for both superconducting and Rydberg atom platforms, identifying experimentally feasible protocols for state preparation. Our results provide an efficient and hardware-relevant pathway for realizing generic FQH states on both noisy intermediate-scale and fault-tolerant quantum devices.

21.
arXiv (CS.CV) 2026-06-16

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

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.

22.
arXiv (CS.AI) 2026-06-16

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

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.

23.
arXiv (CS.CL) 2026-06-15

OdysSim: Building Foundation Models for Human Behavior Simulation

Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven post-training pulls them toward a homogeneous, overly agreeable assistant register, creating a behavioral Sim2Real gap. We present OdysSim, the largest open systematic investigation of behavioral foundation models, i.e., models trained to simulate human behavior at scale. We propose SOUL, a taxonomy of five capability axes (CONV, SS, COG, ROLE, EVAL) that unifies 62 datasets and 23 benchmark tasks under one framework. Specifically, we curate the OdysSim corpus (21.4M interactions, 10B tokens, retrofitted with back-generated social contexts), construct the SOUL-Index benchmark, and develop an end-to-end training recipe combining midtraining, task-specific RL, and expert distillation. The resulting open 8B OSim model ranks first or tied-first on 8 of 23 tasks, outperforming any individual frontier model by this count, with the strongest gains on conversational and social tasks. Its outputs are also more human-like in length, formatting, and word choice, and it transfers zero-shot to out-of-distribution user simulation on $\tau$-bench, nearly matching real users on reaction alignment (93.2 vs. 93.5). We further show that LLM-as-judge RL induces reward-hacking patterns, and that our detectors can mitigate them during post-training. Together, our findings suggest that behavioral foundation models require rethinking the LLM training paradigm. We release all artifacts to support future research.

24.
arXiv (CS.CV) 2026-06-16

Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action

Foundation models have demonstrated impressive performance in enhancing healthcare efficiency across a wide range of medical applications. Nevertheless, their limited ability to perceive, understand, and interact with the physical world significantly constrains their effectiveness in real-world clinical workflows, where safety-critical decision-making and physical execution are tightly coupled. Recently, embodied artificial intelligence (AI) has emerged as a promising physical-interactive paradigm for intelligent healthcare, enabling agents to operate in complex medical environments. As research in this area rapidly expands, understanding how intelligent agents function as integrated, end-to-end systems in clinical environments becomes increasingly critical. However, existing surveys on medical embodied AI largely emphasize individual aspects or functional components, lacking a unified system-level organization of the field. To support and consolidate recent advances, we systematically survey the core components of medical embodied AI, with a particular emphasis on the coordinated integration of perception, decision-making, and action. We further review representative medical applications and relevant datasets, and we analyze the major challenges encountered in real-world clinical practice. Finally, we discuss key directions for future research in this rapidly evolving field. The associated project can be found at https://github.com/VMVLab/Medical_Embodied_AI_Paper_List.

25.
arXiv (CS.LG) 2026-06-19

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

arXiv:2606.04101v3 Announce Type: replace-cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load patterns. We present UltraEP, the first exact-load, real-time balancer for large-EP MoE training and serving prefill on rack-scale nodes (RSNs). Leveraging the extended scale-up connectivity among dozens of GPUs within RSNs, UltraEP rebalances every microbatch and layer on critical paths, which requires nontrivial co-design of plan solving and expert replication communication to minimize exposed overhead. To this end, UltraEP eagerly reacts to post-gating load with an efficient quota-driven planner, and executes the resulting irregular expert-state transfers with RSN-native persistent tile streaming and relay-based fan-out mitigation. We evaluate UltraEP in a multi-RSN deployment of up to 256 GPUs, using cutting-edge MoE models from 106B to 671B parameters. Averaged across training and serving, UltraEP achieves 94.3% of the force-balanced ideal throughput, delivering 1.49$\times$ improvement over no-balancing, while reducing the final inter-rank imbalance from 1.30$-$4.01 to 1.01$-$1.04.