MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Tool Use Reduces Depth-Induced Collapse in OOD Reasoning
Privacy-enhanced federated learning via asynchronous aggregation and local differential p…
A New Transformer-Based Approach for Audio-Based Kinship Verification and a New Uncontrol…
Rolling Day-Wise Mortality Prediction in Critically Ill Patients With AKI on CRRT Utilizi…
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
Steering Generative Robot Policies with Lexicographic Preferences
Thought without systematicity? Evaluating reasoning models on rule induction tasks
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from A…
LePlanner: An Iterative Amortized Controller For World Models
DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction
ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation
Calibrating Interpretability Instruments Before Trusting Their Verdicts
AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A C…
Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum …
MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks
Attention Is All You Need (to Avoid Spurious Oscillations)
mKernel: Fast Multi-GPU, Multi-Node Fused Kernels
OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise
Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Coll…
Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning
Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coor…
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Re…
NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass
SeqMaestro: From nucleotide sequences to biological hypotheses through interpretable mach…
Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language …
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
Kaininja: Extending Native 3D Generators to the Part Level
Building Legal Reward Models for Grounding and Abstention