AI Agents news and analysis on Web Pulse: 11936 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
NVIDIA's new Vera CPU targets agentic throughput, addressing orchestration overhead in multi-step AI workflows. A 5B-parameter latent diffusion model generates multiplayer Rocket League matches at 20 FPS, while Rowboat o…
Researchers tested whether replacing CLI arguments with a single --json payload improves AI agent performance, building a synthetic CLI called podctl for complex multi-service deployments. The study found that while JSON…
MongoDB staff AI developer advocate Apoorva Joshi outlines four principles for building safe, compliant AI agents, citing incidents where Replit and Cursor agents deleted production databases due to governance failures. …
Australian dock workers are demanding a 28-hour work week with no loss of pay as port logistics giant DP World expands its use of AI and automation. The Maritime Union of Australia warns that the technology threatens up …
Readme2demo, an AI agent that reads a repository's README and runs it inside a hardened Docker sandbox to generate verified tutorials and demo videos, has been released. The tool replays every step in a fresh container b…
A developer has published a guide for building an Agentic OS, a lightweight automation layer that enables AI to autonomously inspect repositories, assign tasks, verify outputs, and enforce budgets. The system separates A…
A study of about 1,080 job postings at OpenAI and Anthropic reveals the two AI labs are diverging in their approaches to agentic AI, which poses a security risk as AI agents' behavior can drift over time, evading standar…
Researchers introduced PatchOptic, an optic-inspired interface for shared-state LLM workflows that enforces contracts between local updates and global validity through projected reads and verified structured patches. Eva…
Researchers introduced Prompt-to-Paper, a multi-agent AI system that generates verifiable bioinformatics manuscripts by grounding claims in 60-100 cited papers, executing real computational experiments, and scoring quali…
Researchers introduced CSTutorBench, a benchmark to evaluate small language models as tutors for block-based programming in VEX VR robotics. Testing 11 models revealed that instruction-tuning approach predicts tutoring q…
Researchers demonstrate that moving memory retrieval inside the agent loop reduces latency from hundreds of milliseconds to ~100 microseconds, eliminating redundant actions and improving recall. In tests across GPT-5-cla…
A synthesis of 27 papers (2023-2026) spanning 19 benchmarks reveals six recurring failure clusters in large language model agents, including tool-use errors, planning failures, and safety issues, with failures compoundin…
Researchers introduced NapMem, a framework that transforms long-term user memory into a structured action space for conversational agents, enabling active navigation across memory granularities. Trained with reinforcemen…
Researchers introduced Onnes, a physics-grounded multi-agent LLM simulator for cryogenic fault diagnosis in quantum computing infrastructure. In controlled evaluations, a zero-shot LLM panel matched a supervised ML class…
Researchers introduced StateFuse, a conflict-aware replicated memory contract for multi-agent systems that preserves contradictory observations instead of collapsing them. In evaluations, StateFuse enabled safer abstenti…
Researchers introduced Light-Omni, a multimodal agent framework for reflexive video understanding that uses dual contextual states to avoid costly iterative reasoning. It achieved a 2.4% accuracy gain over M3-Agent with …
Researchers tested how persona prompts affect large language model agents in an iterated Split or Steal game, finding that mutual cooperation dominated in roughly 74% of rounds across 160 sessions. Model choice significa…
Researchers introduced FirstResearch, a framework that generates auditable research questions for LLM scientific discovery agents by producing a structured Research Question Certificate. In evaluations, FirstResearch out…
Researchers introduced ArtisanCAD, an industrial-level CAD agent that uses expert-grounded knowledge distillation to convert ambiguous text prompts into executable CAD programs. The system leverages a CAD intermediate re…
Researchers introduced AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution for training LLM-based autonomous agents. The platform generates high-fidel…