AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic hub

AI Agents

AI agents are LLM-powered systems that don't just answer — they plan steps, call tools and drive a task to completion: writing code, searching the web, booking, analyzing. 2026 became the year of agents, from coding agents to autonomous researchers. This page gathers all our coverage of agentic AI: launches, protocols (MCP, A2A), reliability and real-world use.

Official site ↗1795 articles
In the glossary:AI agentAutonomous AgentAgentic WorkflowTool UseMulti-Agent System
Bending Spoons CEO: AI Writes 90% of Code, While Cheap SaaS Goes Under the Hammer
LLM·Bloomberg Tech

Bending Spoons CEO: AI Writes 90% of Code, While Cheap SaaS Goes Under the Hammer

Oct 24, 2026·2 min
Google Turns Gemini Into an Agent With Its Own Email Address and Subagents
LLM

Google Turns Gemini Into an Agent With Its Own Email Address and Subagents

Oct 24, 2026·2 min
Anthropic: Small Models Could Self-Replicate on IoT Devices by the End of the Year
LLM

Anthropic: Small Models Could Self-Replicate on IoT Devices by the End of the Year

Oct 24, 2026·2 min
Anthropic details 4 types of unsanctioned Claude actions in testing and internal use
LLM

Anthropic details 4 types of unsanctioned Claude actions in testing and internal use

Oct 24, 2026·2 min
Anthropic Commits $150M to Put Claude in 15+ US Federal Agencies
LLM·Anthropic Blog

Anthropic Commits $150M to Put Claude in 15+ US Federal Agencies

Anthropic will spend $150M over three years on the Genesis Mission, giving NASA, NIH, NSF and a dozen-plus other agencies access to Claude. Fusion energy and…

Oct 24, 2026·2 min
Five-Layer Immutable Memory for an AI Agent: Why One Vector Database Is Never Enough
Opinion·Жемал Хамидун · Авторская колонка

Five-Layer Immutable Memory for an AI Agent: Why One Vector Database Is Never Enough

Trying to store an AI agent's entire long-term memory in a single vector index fails, because exact word search, semantic similarity, multi-hop relationship…

Oct 24, 2026·3 min
PatEx-Gym Teaches AI Agents to Hunt for Patent Prior Art: 1 Million Patents and a 4B Model
LLM·Hugging Face Daily Papers

PatEx-Gym Teaches AI Agents to Hunt for Patent Prior Art: 1 Million Patents and a 4B Model

Researchers have released PatEx-Gym, an environment for patent-examiner agents: 1,000 tasks, 1 million patents, 52,000 papers, and a compact 4-billion-parameter…

Oct 24, 2026·3 min
ReGE Teaches Agents From Their Own Attempts: +9.9 pp Without Fine-Tuning
LLM·Hugging Face Daily Papers

ReGE Teaches Agents From Their Own Attempts: +9.9 pp Without Fine-Tuning

TIGER-Lab's ReGE has an agent write its own plan from logs of past attempts. GPT-5.6 Luna catches up to Sol (67.4% vs 67.0%) at 28% of the cost.

Oct 24, 2026·3 min
Top themes
01Moonshot releases Kimi K3.1 Pro: 55 points and $2/$10 per million tokensOct 23, 2026·2 min02PhAI Labs: Claude Opus 5 Ranks Last in Scientific Hypothesis Test With 2.3%Oct 23, 2026·2 min03Vector Search vs. Knowledge Graph: What It Really Costs to Build and Maintain a GraphRAGOct 23, 2026·3 min04Alibaba DAMO Unveils First Automotive RISC-V Roadmap for XuanTie ChipsOct 23, 2026·2 min05Tongyan Lingzhi moves AI personalization from prompts into the model layer itselfOct 23, 2026·2 min
The Information: Anthropic Is Preparing a Model Stronger Than Any Current Claude
LLM·Jiqizhixin (机器之心)

The Information: Anthropic Is Preparing a Model Stronger Than Any Current Claude

Oct 23, 2026·3 min
Tencent Hunyuan and Fudan Launch ExplorationBench to Measure Exploration in LLMs
LLM·Jiqizhixin (机器之心)

Tencent Hunyuan and Fudan Launch ExplorationBench to Measure Exploration in LLMs

Oct 23, 2026·2 min
WorldMemBench Tests Whether World Models Remember Rooms and Events
LLM·Jiqizhixin (机器之心)

WorldMemBench Tests Whether World Models Remember Rooms and Events

Oct 23, 2026·2 min
LightSprint Raises $6.1M for a Multi-Agent Product-to-Engineering Loop
LLM·Jiqizhixin (机器之心)

LightSprint Raises $6.1M for a Multi-Agent Product-to-Engineering Loop

Oct 23, 2026·2 min
Cohere proposes a fix for agent sprawl: competitive selection instead of bans
LLM·Cohere Blog

Cohere proposes a fix for agent sprawl: competitive selection instead of bans

The proliferation of AI agents inside companies is a management problem. Cohere proposes pitting competing agents against each other on reliability, cost, and speed…

Oct 23, 2026·2 min
Vercel Launches Python in General Availability: Six SDKs and FastAPI Support
LLM·Vercel Blog

Vercel Launches Python in General Availability: Six SDKs and FastAPI Support

Vercel launched Python in general availability, enabling developers to deploy Python applications alongside JavaScript frontends with automatic framework detection…

Oct 23, 2026·2 min
Matrix Game 4.0 Hits 60 FPS on a Single Gaming GPU and Beats Nvidia's Rival Model
LLM·Jiqizhixin (机器之心)

Matrix Game 4.0 Hits 60 FPS on a Single Gaming GPU and Beats Nvidia's Rival Model

China's interactive world model Matrix Game 4.0 generates a playable image in real time at 60 FPS on a single consumer GPU.

Oct 23, 2026·2 min
CodeActionBench: GPT-6 Astra in Codex CLI Hits 73.3% Success on Two-Handed Tasks
LLM·Jiqizhixin (机器之心)

CodeActionBench: GPT-6 Astra in Codex CLI Hits 73.3% Success on Two-Handed Tasks

Oct 23, 2026·2 min
Apple and CMU Speed Up AI Agents 10x by Replacing Reasoning with Selection
LLM·Jiqizhixin (机器之心)

Apple and CMU Speed Up AI Agents 10x by Replacing Reasoning with Selection

Oct 23, 2026·2 min
The AI development paradox: why greenfield coding speeds up 55% while mature codebases slow down 19%
Opinion·Жемал Хамидун · Авторская колонка

The AI development paradox: why greenfield coding speeds up 55% while mature codebases slow down 19%

Oct 23, 2026·3 min
ProD Stops AI Agents From Looping: Tested on 8 Models (0.6B–8B)
LLM·Hugging Face Daily Papers

ProD Stops AI Agents From Looping: Tested on 8 Models (0.6B–8B)

Oct 23, 2026·2 min
Groq Launches Meta Muse Spark Open: 816B Parameters and 350+ Tokens/s
LLM·Groq Blog

Groq Launches Meta Muse Spark Open: 816B Parameters and 350+ Tokens/s

Oct 23, 2026·2 min
Manifold AI Tops RoboDojo, Beating GPT-6-Astra and GR00T-N1.7
LLM

Manifold AI Tops RoboDojo, Beating GPT-6-Astra and GR00T-N1.7

Oct 23, 2026·2 min
Meta's Muse Agent Hits 5M US Downloads in 22 Days, Faster Than ChatGPT
LLM

Meta's Muse Agent Hits 5M US Downloads in 22 Days, Faster Than ChatGPT

Oct 23, 2026·2 min
Where VLMs' Physical Self-Improvement Comes From: A Scaling Law for LLM Agents
LLM

Where VLMs' Physical Self-Improvement Comes From: A Scaling Law for LLM Agents

Oct 23, 2026·2 min
Alibaba DAMO Releases RynnUnify: A 16B Model That Plans in Video and Drives a Robot
LLM·Hugging Face Daily Papers

Alibaba DAMO Releases RynnUnify: A 16B Model That Plans in Video and Drives a Robot

The 16B-parameter RynnUnify combines scene understanding, video generation and robot control: 51.5% success on 20 RoboCasa365 tasks and 46.7% on three real-world…

Oct 23, 2026·2 min
RSIHub Packs 4 Agent Evolution Methods Into One Framework: Up to +13.5 pp
LLM·Hugging Face Daily Papers

RSIHub Packs 4 Agent Evolution Methods Into One Framework: Up to +13.5 pp

The open-source RSIHub provides shared infrastructure for comparing methods of AI agent self-improvement. The largest pass@1 gain in testing was 13.5 percentage…

Oct 23, 2026·2 min