InfoQ Homepage Agents Content on InfoQ
-
Paper2Agent Converts Scientific Papers into Interactive AI Agents
Stanford's Paper2Agent framework revolutionizes research by transforming static papers into interactive AI agents that execute analyses and respond to queries. Leveraging the Model Context Protocol, it simplifies reproducibility and enhances accessibility, empowering users with dynamic, autonomous tools for deeper scientific exploration and understanding.
-
Google DeepMind Introduces CodeMender, an AI Agent for Automated Code Repair
Google DeepMind has introduced CodeMender, a new AI-driven agent designed to detect, fix, and secure software vulnerabilities automatically. The project builds on recent advances in reasoning models and program analysis, aiming to reduce the time developers spend identifying and patching security issues.
-
Claude Sonnet 4.5 Ranked Safest LLM from Open-Source Audit Tool Petri
Claude Sonnet 4.5 has emerged as the best-performing model in ‘risky tasks’, narrowly edging out GPT-5 in early evaluations by Petri --- Anthropic’s new open-source AI auditing tool.
-
Dreamer 4: Learning to Achieve Goals from Offline Data through Imagination Training
Researchers from DeepMind have described a new approach for teaching intelligent agents to solve complex, long-term tasks by training them exclusively on video footage rather than through direct interaction with the environment. Their new agent, called Dreamer 4, demonstrated the ability to mine diamonds playing Minecraft after being trained on videos, without ever actually playing the game.
-
Microsoft Announces Open-Source Agent Framework to Simplify AI Agent Development
Microsoft has announced the preview release of Microsoft Agent Framework, an open-source software development kit designed to simplify the creation and deployment of artificial intelligence agents for developers across all skill levels, as reported in official blog posts from the company's development teams.
-
Cursor 1.7 Adds Hooks for Agent Lifecycle Control
Cursor has introduced a Hooks system in version 1.7 that allows developers to intercept and modify agent behavior at defined lifecycle events. Hooks can be used to block shell commands, run formatters after edits, or observe agent actions in real time.
-
OWASP Flags Tool Misuse as Critical Threat for Agentic AI
Earlier this year OWASP released guidance for Agentic AI security called Agentic AI - Threats and Mitigations. The document highlights the unique challenges involved in securely deploying this emerging technology and suggests mitigations and architectural patterns for defense.
-
Google's Agent Development Kit for Java Adds Integration with LangChain4j
The latest release of the Agent Development Kit for Java, version 0.2.0, marks a significant expansion of its capabilities through the integration with the LangChain4j LLM framework, which opens it up to all the large language models supported by the framework.
-
Replit Introduces Agent 3 for Extended Autonomous Coding and Automation
Replit has introduced Agent 3, its latest autonomous software agent built to extend the use of AI in programming and workflow automation. Unlike earlier coding assistants that provide small pieces of help through autocomplete or single-step code generation, Agent 3 is designed to carry out tasks over an extended period of time.
-
xAI Releases Grok Code Fast 1, a New Model for Agentic Coding
xAI introduced grok-code-fast-1, a model developed specifically for agentic coding workflows.
-
Agentic AI Expands into SecOps to Ease Human Workloads
Agentic AI is beginning to reshape malware detection and broader security operations. These systems are being used not to replace humans, but to take on the lower value jobs that have historically tied up analysts — from triaging alerts to reverse-engineering suspicious files.
-
GitLab Unveils Duo Agent Platform in Public Beta, Introducing Agent-Orchestrated DevSecOps
GitLab has launched the public beta of its GitLab Duo Agent Platform, an orchestration tool that enables developers to collaborate asynchronously with AI agents across the DevSecOps lifecycle.
-
AGENTS.md Emerges as Open Standard for AI Coding Agents
A new convention is emerging in the open-source ecosystem: AGENTS.md, a straightforward and open format designed to assist AI coding agents in software development. Already adopted by more than 20,000 repositories on GitHub, the format is being positioned as a companion to traditional documentation, offering machine-readable context that complements human-facing files like README.md.
-
Claude Sonnet 4 Expands to 1 Million Token Context Window
Anthropic has upgraded Claude Sonnet 4 to support a context length of up to 1 million tokens, a fivefold increase over its previous limit. The feature, now in public beta, is accessible through the Anthropic API and Amazon Bedrock, with Google Cloud’s Vertex AI support expected soon.
-
Claude Code Subagents Enable Modular AI Workflows with Isolated Context
Anthropic has recently made Claude Code Subagents generally available, enabling developers to create independent, task-specific AI agents with their own context, tools, and prompts.