wovepaper — the arXiv observatory

The paper presents AgentCompass, an open‑source infrastructure that standardizes and simplifies the evaluation of large‑language‑model based autonomous agents by separating benchma…

Publications (521)

Response probability distribution estimation of expensive computer simulators: A Bayesian active learning perspective using Gaussian process regression

Nonlinear quantum interferometry with Bose condensed atoms

Exploiting Physical Dynamics to Detect Actuator and Sensor Attacks in Mobile Robots

Learning to Retrieve from Agent Trajectories

Inference Computation Scaling for Feature Augmentation in Recommendation Systems

Locating the inner edge of neutron star crust using terrestrial nuclear laboratory data

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Non-negative Sparse and Collaborative Representation for Pattern Classification

SAVIOR: Towards Bug-Driven Hybrid Testing

Investigation of HIV-1 Gag binding with RNAs and Lipids using Atomic Force Microscopy

Lightweight Improved Residual Network for Efficient Inverse Tone Mapping

Learning Hyperplane Tree: A Piecewise Linear and Fully Interpretable Decision-making Framework

Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image

U-HNSW: An Efficient Graph-based Solution to ANNS Under Universal Lp Metrics

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

An updated efficient galaxy morphology classification model based on ConvNeXt encoding with UMAP dimensionality reduction

pyHB: an open-source automatic-differentiation-enhanced semi-analytical solver for nonlinear dynamics

Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference

Masked Latent Transformer with the Random Masking Ratio to Advance the Diagnosis of Dental Fluorosis

Privacy for All: Demystify Vulnerability Disparity of Differential Privacy against Membership Inference Attack

Equations of motion of test particles for solving the spin-dependent Boltzmann-Vlasov equation

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

Simulating spin dynamics with spin-dependent cross sections in heavy-ion collisions

A Taxation Perspective for Fair Re-ranking

Law Article-Enhanced Legal Case Matching: a Causal Learning Approach

Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis

Dynamical effects of spin-dependent interactions in low- and intermediate-energy heavy-ion reactions

A Dyadic Simulation Approach to Efficient Range-Summability

A Study of Implicit Ranking Unfairness in Large Language Models

Energy estimation of small-scale jets from the quiet-Sun region

New Vacuum Solar Telescope and Observations with High Resolution

Cryogenic Modeling of MOSFET Device Based on BSIM and EKV Models

SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval

Spectral indices for radio emission of 228 pulsars

Breaking the EOS-Gravity Degeneracy with Masses and Pulsating Frequencies of Neutron Stars

4D Feet: Registering Walking Foot Shapes Using Attention Enhanced Dynamic-Synchronized Graph Convolutional LSTM Network

SYSPART: Automated Temporal System Call Filtering for Binaries

Tailoring exciton dynamics by elastic strain-gradient in semiconductors

Neural Retrievers are Biased Towards LLM-Generated Content

FairSync: Ensuring Amortized Group Exposure in Distributed Recommendation Retrieval

Effects of isospin and momentum dependent interactions on liquid-gas phase transition in hot asymmetric nuclear matter

Extracting temperature of plasma through fusion reactions within a transport approach

Constraining the EOS of neutron-rich nuclear matter and properties of neutron stars with heavy-ion reactions

Spin transport in intermediate-energy heavy-ion collisions as a probe of in-medium spin-orbit interactions

TACL: Threshold-Adaptive Curriculum Learning Strategy for Enhancing Medical Text Understanding

P-MMF: Provider Max-min Fairness Re-ranking in Recommender System

Investigating the scaling of higher-order flows in relativistic heavy-ion collisions

Space- and Computationally-Efficient Set Reconciliation via Parity Bitmap Sketch (PBS)

Mechanical Wave Propagation within Nanogold Granular Crystals

Symmetry energy effects on the properties of hybrid stars

Simulating chiral anomalies with spin dynamics

Diode-pumped mode-locked femtosecond 2-um Tm:CaYAlO4 laser

Probing in-medium spin-orbit potential with intermediate-energy heavy-ion collisions

Peering into the Milky Way by FAST: III. Magnetic fields in the Galactic halo and farther spiral arms revealed by the Faraday effect of faint pulsars

Unusual Dielectric Relaxation in Lightly Doped n-Type Rhombohedral BaTi0.85Zr0.15O3:Ta Ferroelectric Ceramics

Angular momentum conservation and pion production in intermediate-energy heavy-ion collisions

Gradient-Induced Co-Saliency Detection

AGNs are not that cool: revisiting the intrinsic AGN far-infrared spectral energy distribution

Trigger3: Refining Query Correction via Adaptive Model Selector

Internet of Things Applications: Animal Monitoring with Unmanned Aerial Vehicle

Revisiting the isospin relaxation time in intermediate-energy heavy-ion collisions

LTP-MMF: Towards Long-term Provider Max-min Fairness Under Recommendation Feedback Loops

RECIPE: Rateless Erasure Codes Induced by Protocol-Based Encoding

Transport properties of asymmetric nuclear matter in the spinodal region

Reinforcement Re-ranking with 2D Grid-based Recommendation Panels

Privacy-preserving Channel Estimation in Cell-free Hybrid Massive MIMO Systems

Density slope of the nuclear symmetry energy from the neutron skin thickness of heavy nuclei

On Efficient Range-Summability of Ideally IID Random Variables in Two or Higher Dimensions

KuaiLive-M3: A Multi-Modal, Multi-Domain, and Multi-Feedback Dataset for Live Streaming Recommendation

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

3-dimensional QCD phase diagram with pion condensate in the NJL model

Pre-training of Context-aware Item Representation for Next Basket Recommendation

Rate-Aware Learned Speech Compression

Reducing detrimental electrostatic effects in Casimir-force measurements and Casimir-force-based microdevices

A Study of MatchPyramid Models on Ad-hoc Retrieval

Towards Completeness-Oriented Tool Retrieval for Large Language Models

GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Items

HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines

NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search

Trigger $^{3}$ : Refining Query Correction via Adaptive Model Selector

Comparing pion production in transport simulations of heavy-ion collisions at $270 A$ MeV under controlled conditions

Directly probing existence of $I^\pm$ -cluster structure in $^{20}$ Ne by relativistic heavy-ion collisions