Frontier AI Watch

AI Agents

Agentic AI systems, coding agents and developer workflows, tool use, orchestration, multi-agent systems, safety evaluation, agent infrastructure, enterprise deployments, and durable workflows.

Agent systems, workflows, and safety

AI agents illustration
InfoQ AI, ML and Data EngineeringPublished

Reverse Engineer Anything Project Brings AI Agents to Binary Analysis

Reverse Engineer Anything (REA) is an open-source project with over 200K GitHub stars that connects coding agents such as Claude Code and Codex to reverse-engineering tools like Ghidra, Hopper, and IDA. The project lets developers inspect compiled binaries,…

AI agents illustration
InfoQ AI, ML and Data EngineeringPublished

Google EnvHarness Enables Self-Evolving Agents to Learn in Dynamics Environments

Google researchers open sourced EnvHarness, a framework that dynamically adapts agent-training environments to an agent's weaknesses without modifying the agent, environment, or evaluation system. According to the researchers, this approach can improve both…

AI agents illustration
InfoQ AI, ML and Data EngineeringPublished

AI in Production: Panellists Highlight Silent Failures, Harness Engineering, and Agent Governance

A recent InfoQ webinar examined operational challenges in deploying agentic systems. Key points included issues like semantic and embedding drift, which can lead to significant errors. Experts discussed the need for automated code reviews, continuous…

AI agents illustration
InfoQ AI, ML and Data EngineeringPublished

Grafana Applies SLOs and Error Budgets to AI Agent Behaviour

Grafana Labs is proposing a familiar reliability engineering approach for one of the less familiar problems in modern software: how to measure whether an AI agent is actually behaving well. By Craig Risi

AI agents illustration
InfoQ AI, ML and Data EngineeringPublished

Mini book: Evolutionary Architecture in Practice

Discover how to keep software evolvable as systems, technology, and teams shift. This edition explores agentic fitness functions for semantic drift, treating human comprehension as a core design metric, cross-cloud guardrails for regional autonomy, and…

AI agents illustration
InfoQ AI, ML and Data EngineeringPublished

Presentation: Exploding GPUs

Andrew Martin discusses why AI security is fundamentally tied to Kubernetes security. He shares insights into the evolving AI threat landscape, covering non-deterministic agent behavior, GPU supply chain vulnerabilities, shared compute risks, and practical…

AI agents illustration
InfoQ AI, ML and Data EngineeringPublished

AWS Introduces Strands Decider 2B and Strands Box for AI Agent Development

AWS has introduced two open-source projects for AI agent development: Strands Decider 2B, a small model designed to make decisions within agent workflows, and Strands Box, a sandbox for controlling agent execution. Both projects address different aspects of…

AI agents illustration
OpenAI NewsPublished

Benefit Street Partners answers questions faster with Codex

Anant Kumar builds tools to compare loan valuations and analyze credit agreements, using Codex for code review and faster follow-ups.