AI Agents news and analysis on Web Pulse: 36324 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
OpenAI introduced a structured triage and review framework for tracking, investigating, and publicly disclosing model misalignment across training, evaluation, testing, and deployment, sorting flagged incidents into "Rea…
An operator of a five-agent AI organization reported that all 10 of its own "verified success" verdicts failed independent recomputation, with claims marked externally verified while showing zero tokens consumed against …
A new evaluation framework called PACT is proposed to test whether enterprise-grade LLM agents comply with rules specified in their system context when deployed in sensitive domains such as hiring, healthcare, and financ…
Ripple expanded its XRPL developer kit to support Stripe and Tempo's Machine Payments Protocol, enabling AI agents to pay for data, computing, and other services on the XRP Ledger, the company said in a recent update. Th…
Amazon Web Services launched a new "getting started experience" for its console aimed at "builders who are working at the pace of AI," Senior Solutions Architect Micah Walter announced in a Wednesday post, after the comp…
A developer measuring AI crawler traffic on a small WordPress site found that Meta accounted for 52.3% of all AI crawler requests over 30 days, more than every other vendor combined, yet none of its requests came from a …
A developer's pair-programming notes conclude that AI coding assistants are useful for generating optimization hypotheses and tracing failures but unreliable as judges of whether their own proposals work, after several c…
Uber CEO Dara Khosrowshahi unveiled a driver and courier roadmap on September 17th that adds AI guidance tools, new paid task types, and expanded compensation and protections for eligible delayed trips. The package inclu…
Prompt injection remains an unfixed structural weakness in AI agents because large language models cannot distinguish developer instructions from text they read, and indirect prompt injection — hidden in webpages, emails…
A developer built Rig, an open-source orchestration harness that sits between coding agents rather than acting as another chat-based code generator. Rig uses a parent CLI to convert intent into scoped work, dispatches it…
A developer published a beginner's guide to configuring permission rules in Claude Code, showing how allow/ask/deny gates in .claude/settings.json can block risky agent actions such as force-pushing a branch or running a…
A September 15, 2026 arXiv paper demonstrates that poisoned benchmarks can induce self-modifying AI coding agents to write vulnerable code on clean, held-out tasks, with Hyperagents powered by Sonnet 4.5 self-evolving in…
Anthropic said in a Thursday blog post that Claude now leads 26% of its AI research and development work, up from below 1% in March, with more than 90% of work at or above the "AI collaborates" level. Anthropic reported …
Dataminr announced Dataminr Advanced for Corporate Security, an agentic AI product that uses Agentic Corroboration, Agentic Context, and Near-Term Predictive Intelligence to help corporate security teams predict and veri…
A systematic mapping of 14,767 arXiv papers introducing or updating LLM evaluation resources between January 2022 and August 2026 finds growing emphasis on action, interaction, and professional applications, with LLM-bas…
A new arXiv study (2609.19244v1) analyzed Web search across four conversational platforms — ChatGPT, Claude, Grok, and DeepSeek — combining real-world user interactions with controlled API experiments. The study found th…
A position paper posted to arXiv (2609.19203v1) argues that compound agentic AI systems need a Foundation Model Operating System (FMOS), a system layer that virtualizes foundation model interactions the way virtual machi…
Researchers introduced MAGS, a unified multi-agent framework that generates executable programs with formal safety guarantees by using Dafny as a verification-aware intermediate representation, according to an arXiv pape…
A new arXiv paper (2609.19387v1) introduces AutoTuring, a benchmark that gives the same AI agent the same 15-dimensional accelerator design space twice — once as named architectural knobs with simulator counters and once…
A paper on arXiv (2609.19519v1) proposes a three-part hierarchical architecture for long-horizon language-model agents — time-scale-indexed levels, a clocked tick as the unit of autonomous action, and cascaded intelligen…