AI Agents
Masumi Network Fuses Blockchain With AI for Agent Trust
Masumi Network combines Cardano blockchain with AI agents to solve trust, payment, and identity verification challenges in the emerging autonomous agent economy.
AI Agents
LLM Research
Think-Augmented Function Calling Boosts LLM Parameter Accuracy
New research introduces embedded reasoning to improve how LLMs handle function parameters, addressing a critical bottleneck in AI agent reliability for tool-using applications.
AI research
VibeTensor: AI Agents Now Generate Complete Deep Learning Systems
New research demonstrates AI agents can autonomously generate complete system software for deep learning, marking a significant step toward self-improving AI development pipelines.
AI Agents
eBay Cracks Down on AI Shopping Agents in Policy Shift
eBay updates terms of service to prohibit unauthorized AI agents from making purchases, signaling e-commerce platforms are drawing boundaries around autonomous AI systems.
AI Agents
New Framework Augments LLMs with Expert Knowledge for AI Agents
Researchers propose a software engineering framework for building AI agents that combines LLM capabilities with codified human expert domain knowledge for improved reliability.
AI Agents
IBM's AssetOpsBench Tests AI Agents in Real Industrial Scenarios
IBM Research releases AssetOpsBench, a benchmark testing AI agents on realistic industrial asset management tasks, revealing gaps between lab performance and real-world deployment challenges.
AI Agents
Goal Drift: Why AI Agents Lose Focus in Video Research
AI agents analyzing video content face a critical challenge: goal drift. As they process complex visual data, they lose sight of original objectives, requiring new architectural solutions.
AI Agents
Building Secure Sandboxes for AI Agents: A Technical Guide
Learn how to isolate AI agent code execution with secure sandbox environments. This guide covers containerization, permission models, and safety patterns for autonomous AI systems.
AI Agents
LangGraph Design Patterns: Building Smarter AI Agents
Master the architecture behind intelligent AI agents with LangGraph's graph-based approach to state management, conditional routing, and multi-agent orchestration.
AI Agents
Deep Agents: Solving Multi-Step AI Agent Failure Modes
AI agents often fail after several steps due to error compounding and context degradation. Deep Agents architecture introduces new mechanisms to maintain coherence across extended task execution.
LLM
Proactive Memory Extraction Advances LLM Agent Capabilities
New research proposes proactive memory extraction for LLM agents, moving beyond static summarization to enable more dynamic knowledge retention and recall in autonomous AI systems.
AI Agents
Context Engineering: The New Discipline Powering AI Agents
Beyond prompt engineering, context engineering is emerging as the critical discipline for building reliable AI agents—managing what information models see, when, and how.