AI Agents news and analysis on Web Pulse: 36357 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
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…
A new arXiv paper (2609.19526v1) introduces Recursive Self Improvement via Fast Tree-search (SIFT), a sample-efficient framework that lets coding agents recursively modify their own implementations under strict budget co…
A new arXiv paper (2609.19524v1) proposes a unified evaluation framework for trustworthy AI that assesses large language models, agentic systems, and multimodal models across eight trustworthiness dimensions: capability,…
A new arXiv paper (2609.19538v1) proposes a hierarchical hybrid large language model (LLM) and multi-agent reinforcement learning (MARL) architecture for low-altitude wireless networks (LAWNs) supporting heterogeneous un…
Researchers constructed UC-Bench, a human-annotated benchmark for detecting user-side implicit conflicts in Human-LLM dialogue, and found existing LLMs struggle with the task, especially when conflicts stem from implicit…
A frontend-backend architecture that lets full-duplex speech-to-speech models delegate tool calls to a text-based backend LLM achieved 92-97% tool-call recall and 81.2% accuracy in rejecting irrelevant calls in a single-…
A new arXiv paper (2609.19425v1) reports that tool-augmented LLM agents hallucinate calls to tools that do not exist, and that no existing tool-selection or gating defense can reject them because a fabricated call is by …
A cooperative framework called UnifiedPlayers, comprising a Planning Player, an Execution Player, and an Evaluation Player, outperformed the strongest prior baseline by at least 3.5% on mathematical reasoning and 3.9% on…