This week in Evals

FrontierPhysics: Evaluating Agents for End-to-End Physics ResearchNov 4 · ▲ 43
Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM LayersNov 4
ServerBench: How can your coding agents design specialized LLM serving systems?Nov 4

This week

Get the morning digest

The top stories in the fields you follow, at 08:00 your time.

Latest in AI and developer tools

Today's trail

updated 11m ago

Last hour Today

Pulse · lohud.com

lohud.com · Nov 5

Claimlane raises €5.6 million to scale AI agents for aftersales product resolution

Pulse

Top picks this weekarXiv

arXiv

Nov 4

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

AI End-to-end physics research benchmark for AI agents.

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

GitHub

Dec 21

home-assistant/home-assistant.io

:blue_book: Home Assistant User documentation

golang/go

The Go programming language

microg/GmsCore

Free implementation of Play Services

obsproject/obs-studio

OBS Studio - Free and open source software for live streaming and screen recording

Today's trail

Most active this week

neural operators · physics informed neuralneural operators56 this week
agents · toolagents55 this week
indirect prompt injection · prompt injectionagents45 this week
gpu memory · gpusInference & serving43 this week
coding agents · coding agentagentsNew40 this week
recursive self improvement · airecursive self improvement38 this week
agent collaboration · multi agentrecursive self improvement35 this week
judges · llm judgesFrontier LLMs32 this week
pose estimation · camera poseMultimodal32 this week
reasoning models · reasoning tasksFrontier LLMs32 this week

Rising topics

Rising tools

Soup+1295% downloads · 17.2k/wk+1295.0%
better-auth+111% downloads · 1.6M/wk+111.4%
openclaude+176% downloads · 5.8k/wk+176.1%
TanStack AI+93% downloads · 1.8M/wk+92.9%
context-mode+49% downloads · 40.9k/wk+48.6%
notion-mcp-server+97% downloads · 387.2k/wk+97.3%
Scalar+89% downloads · 1M/wk+88.7%
nx-console+55% downloads · 128.7k/wk+55.2%

All tools

This week in Evals

This week

Get the morning digest

Today's trail

Claimlane raises €5.6 million to scale AI agents for aftersales product resolution

Confluent Expands Real-Time Data Access for AI Agents and Applications

Navitas Sinks 15% as AI Chip Stocks Slide After Midterms

Pulse

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

moonshotai/Kimi-K3.1-Pro

KKKKhazix/agent-autoloop

Astra can read and write weights to improve Qwen

OpenAIs GPT-6 Cyber can both break into systems and propose how to fix them

Top picks

home-assistant/home-assistant.io

golang/go

microg/GmsCore

obsproject/obs-studio

Today's trail

This week in Evals

Claimlane raises €5.6 million to scale AI agents for aftersales product resolution

Confluent Expands Real-Time Data Access for AI Agents and Applications

Navitas Sinks 15% as AI Chip Stocks Slide After Midterms

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

moonshotai/Kimi-K3.1-Pro

KKKKhazix/agent-autoloop

Astra can read and write weights to improve Qwen

OpenAIs GPT-6 Cyber can both break into systems and propose how to fix them

Most active this week

Rising tools

home-assistant/home-assistant.io

golang/go

microg/GmsCore

obsproject/obs-studio