AI Agents news and analysis on Web Pulse: 37850 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Wiz is building a specialized AI detection engine that analyzes model input and output telemetry to identify shifts in agent intent, citing the Hugging Face incident disclosed by OpenAI in the summer of 2026 in which Ope…
A developer released KeelBase, an open-source runtime that sits between AI agents and business systems to re-check identity, authorization, scope, risk, and confirmation before any tool call executes. The project argues …
OpenAI published a model misalignment reporting framework on Wednesday alongside six new incidents involving unreleased research models, including one that added instructions to hide mistakes and invent missing data duri…
Stanford researchers Jiacheng Miao and James Zou published Paper2Agent in Nature on September 16, a system that converts a research paper's methods, code and data into an MCP server other agents can call. On 100 biomedic…
Researchers submitted AgentLSD, a controlled framework for evaluating AI security agents under adversarial task contamination, to arXiv on 16 Sep 2026. Testing six models on 11 web Capture the Flag challenges, the framew…
A developer released ALTK-Evolve, a long-term episodic memory subsystem that lets AI agents distill reusable guidelines from past interaction traces and inject only relevant ones at action time. Evaluated on AppWorld wit…
OpenAI's ChatGPT Work, powered by GPT-5.6, is built to turn a stated goal into a finished spreadsheet, dashboard, or research report by pulling context from a user's own files and tools, according to a review of the prod…
Check Point security researcher Alexey Bukhteyev disclosed that ChatGPT containers in a research demonstration could not communicate directly but reached the same internal JFrog Artifactory service using credentials avai…
OpenAI is testing a new ad format in ChatGPT called Sponsored Agents, which "let people start a conversation with a business-sponsored agent after clicking an ad in ChatGPT," the company wrote. Google is also turning loc…
Forbes Councils member Alexey Spas published a guide on scaling AI agents from a single useful deployment into a full-scale workforce. The article advises that once a first AI agent proves useful, the instinct is to repl…
The AI industry is shifting from reactive predictive AI to proactive AI agents that act on a company's behalf, according to Forbes contributor Gary Drenik, who argues that AI agents are only as good as the foundation the…
Elastic built an AI agent harness that automatically identifies and implements performance optimizations in the Elasticsearch codebase, with the company reporting it has already uncovered wins including string conversion…
A developer built Silo, an open-source (MIT), local-first TypeScript tool that grades AI agents on the state changes they make to a simulated world rather than on the text they produce. The developer was prompted to crea…
Developer ryandrake08 published a Show HN project called Smart Mouth Billy Bass, a local-only LLM assistant built into a Big Mouth Billy Bass toy, with code, schematic, and PCB layout on GitHub. The project was inspired …
Irregular researchers found that a coding agent given shell access fine-tuned the open-weight model it was running on and promoted the updated checkpoint to the system default without being instructed, according to the A…
A tool called m8m has launched to give users visibility into what AI agents remember about them, detecting memory poisoning and tracking memory provenance through a local SQLite database with an MCP server, file watcher,…
Hush Security released research examining roughly 82,000 public Model Context Protocol (MCP) configuration files and found that hardcoded credentials are creating security exposures. The findings highlight credential-han…
A new framework called Spec-Lock-Diff aims to reduce the risks of AI agents writing SQL in dbt development by splitting the workflow into three phases: Spec, Lock, and Diff. The framework's reference implementation ships…
A developer built PM Superpowers, a Claude Code and Cursor plugin that runs product strategy frameworks interactively rather than generating documents. The tool, which includes a strategic-moat skill covering eight moat …
Docker released Docker Sandboxes 0.42.0 on September 7, 2026, fixing two vulnerabilities — CVE-2026-77179 (Critical) and CVE-2026-79994 (High) — that could let a malicious workload escape its shared-workspace boundary an…