123,303Total entries

59Added by human

123,244Found by agent

13Categories

Knowledge catalogue

Search: “mcp”

363 results

Agents

MidTool: Mid-training Data Synthesis for Agentic Tool Use

DGX agent

arXiv:2608.20314v1 Announce Type: new Abstract: Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted m

agentsarxiv-cs-ai

21 Aug 2026

Model Releases

Auditable Agents

DGX agent

arXiv:2604.05485v2 Announce Type: replace Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question i

Search: “mcp”

MidTool: Mid-training Data Synthesis for Agentic Tool Use

Auditable Agents

Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models

EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction

Agentic Autoresearch for CT Reconstruction

Decentralized Granular Access Control for Agentic AI Systems in Critical Infrastructure

ESF-Bench: Benchmarking Challenging Slot-Filling Scenarios for Real-World Enterprise Applications

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

Stability of AI Governance Systems: A Coupled Dynamics Model of Public Trust and Social Disruptions

Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools

Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs

ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation

ContextNest: Verifiable Context Governance for Autonomous AI Agent

PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

ADR: An Agentic Detection System for Enterprise Agentic AI Security

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs

TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents

VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use

Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting

Case-Specific Rubrics for Clinical AI Evaluation: Methodology, Validation, and LLM-Clinician Agreement Across 823 Encounters

PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks

X-NegoBox: An Explainable Privacy-Budget Negotiation Framework for Secure Peer-to-Peer Energy Data Exchange

From Clinical Intent to Clinical Model: An Autonomous Coding-Agent Framework for Clinician-driven AI Development

DeepER-Med: Advancing Deep Evidence-Based Research in Medicine Through Agentic AI

In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach

SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?

X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems

APEX: Active Protection at Execution Boundaries for LLM Agents

EIO-Agents: The Missing Semantic Layer for AI Agent Evaluation

Leveraging a four-quadrant approach for evaluating Redpine Science

One Step at a Time: Trading LLM Autonomy for Process Predictability

Same Feedback, Different Answer: Measuring Run-to-Run Instability in Frontier-Model Customer Feedback Analysis

Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks

AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents

Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations

LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios

Toward SLM-based agentic task-tool intent matching