Agents
The agentic stack, tracked daily: MCP and A2A protocols, LangChain/LangGraph, Claude Code, OpenAI Agents SDK, agent frameworks, benchmarks and orchestration patterns.
The agentic stack, tracked daily: MCP and A2A protocols, LangChain/LangGraph, Claude Code, OpenAI Agents SDK, agent frameworks, benchmarks and orchestration patterns.
Latest in Agents
30 stories
Multi-tenant LLM analytics with row-level security: How we built a secure agent on AWS
In this post, we show you how PAR built a production-ready multi-tenant LLM analytics system that enforces row-level security through a three-layer architecture…
Cloud CISO Perspectives: How Google Cloud Security uses AI internally
Welcome to the second Cloud CISO Perspectives for June 2026. Today, we’re discussing how we use AI to chart a path to autonomous software development lifecycle …
Debugging production agents with Amazon Bedrock AgentCore Observability
In this post, you learn how to debug production agent failures using built-in observability capabilities. We walk through common failure patterns, show how to a…
'%2F%3E%3Cg%20opacity%3D'0.16'%20stroke%3D'%23fff'%20stroke-width%3D'6'%20stroke-linecap%3D'round'%3E%3Cline%20x1%3D'292'%20y1%3D'42'%20x2%3D'370'%20y2%3D'42'%2F%3E%3Cline%20x1%3D'292'%20y1%3D'66'%20x2%3D'352'%20y2%3D'66'%2F%3E%3Cline%20x1%3D'292'%20y1%3D'90'%20x2%3D'372'%20y2%3D'90'%2F%3E%3C%2Fg%3E%3Cg%20fill%3D'%23fff'%20font-family%3D'-apple-system%2CBlinkMacSystemFont%2CSegoe%20UI%2CRoboto%2Csans-serif'%3E%3Ctext%20x%3D'30'%20y%3D'250'%20font-size%3D'30'%20font-weight%3D'700'%3EAI%20LABS%3C%2Ftext%3E%3Ctext%20x%3D'31'%20y%3D'280'%20font-size%3D'15'%20opacity%3D'0.82'%20font-weight%3D'500'%3Eblogs.nvidia.com%3C%2Ftext%3E%3C%2Fg%3E%3C%2Fsvg%3E)
Claude Meets Blackwell Ultra: Anthropic’s Models Now Run on NVIDIA GB300 in Azure
Anthropic’s Claude models in Microsoft Foundry — hosted on Microsoft Azure and running on NVIDIA GB300 Blackwell Ultra GPUs — are now generally available, givin…
Meta restricts use of Claude Code and Codex to keep rival AI out of its training data
Meta is restricting its engineers' use of Anthropic's Claude and OpenAI's Codex to prevent output from these AI tools from being incorporated into its own train…
Deloitte tells its own consultants: AI is coming for the billable hour
An internal Deloitte presentation projects that the consulting industry's classic hourly billing model will shrink to a thin sliver of the total market by 2035,…
Claude Code runs a GitHub repo's hidden malware without verification, giving attackers full control
Security researchers at Mozilla's 0DIN platform have shown how a single compromised GitHub repo can take over a developer's machine the moment an AI coding tool…
Intent-Governed Tool Authorization for AI Agents
AI agents increasingly act through external tools: they read private data, construct structured payloads, submit write requests, export records, and coordinate …
Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI
Occupancy prediction at voxel-level granularity is essential for safe robotic navigation and interaction in complex environments. Existing occupancy datasets, h…
Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce
Commercial NLP treats the shopping chatbot as a recommender or a conversion tool: its job is to match a user to a catalogue entry and close a sale. We argue tha…
BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding
Brain-Computer Interfaces (BCIs) and brain signal understanding are pivotal for clinical health and next-generation interactions. Despite this significance, its…
SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game
Evaluating LLM agents requires dynamic environments that go beyond static reasoning and zero-sum games. Real-world economic interaction is often open-ended and …
Training Observable Control Policies to Expose Agent State Through Actions
Physical or operational constraints often impose communications limitations on autonomous agents. Such limitations complicate monitoring or multiagent coordinat…
Only three AI models finished above starting capital in a 500-day startup survival test
Researchers at Princeton University built CEO-Bench, a test where AI agents have to run a fictional software company for 500 simulated days. Most current models…
Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners req…
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
Consistency distillation has significantly accelerated the inference of diffusion models. In this work, we reveal an intriguing asymmetry: while Logit-Normal sa…
Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent
Coding agents now interleave LLMs with retrieval over the working repository, and retrieval implementations vary widely across deployed harnesses. Inside a fixe…
Autonomous Subsea Cable Search and Tracking with Graph-Optimised Priors and Visual Tracking
Global communications rely on subsea cable infrastructure that remains vulnerable to damage from natural hazards and human activity. Autonomous underwater vehic…
Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image C…
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing
Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptible to error…
Finding the Time to Think: Learning Planning Budgets in Real-Time RL
Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely…
When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societies
LLM "agent societies" are studied via demonstrations of emergent consensus or polarization -- with no measurable control parameter, no theory of when each regim…
Grounded Scaling: Why Agentic AI Needs Deterministic Environments
Long-chain agent execution fails exponentially in environments designed for human tolerance: with per-step determinism $δ< 1$, $k$-step chain success degrades a…
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
Modern video diffusion models achieve higher generation quality through scaling, but this also increases inference cost. Although many acceleration methods have…
RLM-Cascade: Response-Level Speculative Decoding for Cost-Efficient LLM API Serving
We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architectur…
Self-Compacting Language Model Agents
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context w…
MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery
Long-term memory promises LLM agents that grow more capable across sessions, maintaining an accurate, evolving understanding of the user that interaction forms.…
Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed:…
Offline Multi-agent Continual Cooperation via Skill Partition and Reuse
Extracting skills from multi-agent offline dataset improves learning efficiency via sharing task-invariant coordination skills among tasks. In settings where ta…
Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning
Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framewor…