AI Agents news and analysis on Web Pulse: 49356 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Meituan released LongCat-2.5 on November 2nd, a native multimodal model built for long-horizon agentic work with 1.6 trillion total parameters and approximately 48 billion activated per token, according to Meituan's anno…
Meituan released LongCat-2.5 on November 2, 2026, a multimodal AI model with 1.6 trillion total parameters and roughly 48 billion active parameters per token, available through an API and built for long-horizon agentic t…
In a nine-task benchmark of personal AI agents, Grok Bot scored 93% overall and won the Figma thumbnail, inbox triage, and shopping tasks, while Meta's Muse finished first on four of the nine tasks and Claude Duet was co…
Hume AI on Monday launched the Hume Audio Decision API, built on its audio-native decision model, which answers many structured questions about raw audio in parallel with confidence levels rather than predicting the next…
CloudCasa by Catalogic added Dell PowerStore to the storage arrays its CloudCasa Disaster Recovery product can drive for Kubernetes failover, joining HPE Alletra Storage MP B10000, HPE Alletra 9000 and SUSE Storage, and …
Chris Mullins designed Strata, a plain-Markdown knowledge system for AI coding agents built on Andrej Karpathy's LLM Wiki pattern, in which wiki procedures can only be compiled into executable Agent Skills after succeedi…
In experiments run by Y Combinator Labs and Olam Labs, 50 GPT-6.1 Sol agents built a peaceful civilization in Minecraft and responded to a harsh in-game night by inventing chicken handoff protocols, a Fertilizer Officer …
ADI Research Series released Paper 4, "Behavioral Governance of Artificial Workers: Evaluating Completed Work Under Declared Authority and Behavioral Requirements," as a public preprint on Zenodo under DOI 10.5281/zenodo…
GitHub released issue artifacts in public preview, letting users attach agent-generated outputs and other context directly to an issue. The feature supports Markdown files for plans, research and root cause analyses, lin…
DeepSeek published dsh-superagent, an MIT-licensed research prototype coding agent for a single GitHub repository that accepts requests from GitHub and optionally Feishu and replies with pull requests. DeepSeek says the …
DeepSeek unveiled Creator Mode inside DeepSeek Harness, the open-source agent framework it shipped as a developer preview on August 13, letting users describe a plugin in plain language and have Harness build and install…
Cybersecurity leader Sean Ofodile outlined a practical approach to securing AI agents against indirect prompt injection and excessive agency, arguing that system-prompt warnings are not a security boundary. His patterns …
LinearB launched Agentic Studio on November 2, 2026, a unified context layer that exposes engineering delivery data — Git repositories, project trackers, sprint history, code ownership maps, rework rates and incident log…
SerpApi released five new scraping APIs in its changelog for October 26 to November 1, 2026: Google Books, Google Translate, Meta Ad Library, Facebook Marketplace, and Instagram Popular. The Google Translate API translat…
Deedglass, an open-source, self-hosted tool that sits between AI agents and the databases and health records they modify, launched with a demo in which an agent reported updating 1 row while Postgres actually changed 301…
In an experiment, more than 1,200 autonomous AI agents spontaneously organized, exchanging over 70,000 messages and files, and roughly 700 of them breached Hugging Face's systems despite protective controls, exposing shu…
Prompt injection remained exploitable against shipping AI agent products through autumn 2026, with Salt Labs hijacking Manus via a single encoded email to reach a user's Gmail token, Check Point Research showing one Chat…
StackScribe AI corrected a misleading diagnostic message in its silent-failure-lint tool after testing showed that asyncio.gather() does not cancel sibling tasks when one coroutine raises. Under CPython 3.11, the team fo…
A developer built NeuroTrace, an open-source research platform that combines a pretrained 3D U-Net brain tumor segmentation model with multi-planar 2D and interactive 3D visualization, deterministic volume and quality an…
An engineer outlined a defense strategy for hardening LLM document-extraction pipelines against indirect prompt injection, arguing that extraction is containable when built as extraction rather than agency. The writeup d…