Live feed

research.nvidia.com · 2026-09-24 · Ranked: agentic match · community signal · fresh 0.97 · score 2.75 · Context

SWE-Serve: Benchmarking Agentic Engineering for Production Inference Serving

arxiv.org · 2026-09-24 · Ranked: agent + evaluation match · research watch · fresh 0.92 · score 2.50

SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories

Large language model based coding agents have made substantial progress on repository-level software engineering tasks. Existing repository benchmarks, however, usually start from a human-identified issue and evaluate... Context & related coverage →

cloud.google.com · 2026-09-24 · Ranked: agentic match · cloud platform update · fresh 0.86 · score 2.18

Power your agents: Gemini 3.8 Live with Live Avatar is now generally available

Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enterprise . First pre... Context & related coverage →

anthropic.com · 2026-09-24 · Ranked: agent match · research watch · fresh 0.86 · score 2.05

Project Swap: What happens when agents trade for us?

To see what works and what breaks when agents are sent into a market, we made a miniature market of Claudes. Context & related coverage →

arxiv.org · 2026-09-24 · Ranked: evaluation match · research watch · fresh 0.90 · score 2.03

From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model

Visual software often needs a decision over supplied alternatives rather than a generated explanation. We present PixelJev, a native-image decision interface that maps an image, a task instruction, and a runtime candi... Context & related coverage →

langchain.com · 2026-09-24 · Ranked: agent match · practitioner analysis · fresh 0.92 · score 1.95

New in LangSmith Engine: red teaming and automated testing

LangSmith Engine now includes Red Teaming to proactively detect agent issues and automated agent testing. Learn more about the Engine v2 release. Context & related coverage →

github.blog · 2026-09-24 · Ranked: agent match · practitioner analysis · fresh 0.93 · score 1.86

AI-powered fuzzing with the GitHub Security Lab Taskflow Agent

In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework. The post AI-powered fuzzing with the GitHub Security Lab Taskflow Agent appeared first on... Context & related coverage →

infoq.com · 2026-09-24 · Ranked: practitioner analysis · fresh 0.90 · score 1.80

InfoQ Launches High-Performing Teams Certification Program

InfoQ has opened enrollment for a new five-week certification program covering engineering team design, delivery flow, AI-enabled work, and metrics, facilitated by InfoQ editor and podcast co-host Olimpiu Pop. By Arte... Context & related coverage →

deepmind.google · 2026-09-24 · Ranked: frontier lab · fresh 0.87 · score 1.80 · Context

Introducing Gemini 3.8 Live with Live Avatar

AI: Reset to Zero · 2026-09-24 · Ranked: community signal · fresh 0.92 · score 1.80 · Context

‘Bigger than a Breadbox’ in AI. Capex, Gemini & DeepSeek. ARD #170

infoq.com · 2026-09-24 · Ranked: practitioner analysis · fresh 0.89 · score 1.79

Un-Mused: How a Single Debug Setting Bypassed macOS Security in Meta’s AI Client

Security researcher Patrick Wardle revealed an unpatched zero-day vulnerability in Meta's Muse desktop client for macOS. This flaw lets unprivileged software manipulate the assistant's extensive permissions, compromis... Context & related coverage →

langchain.com · 2026-09-24 · Ranked: agent match · practitioner analysis · fresh 0.90 · score 1.76

Managed Deep Agents delivers a better user experience for agents in production

Managed Deep Agents is the simplest way to build, deploy, and run agents in production. The 0.8 release adds support for user-owned credentials, user-level memory, HTTP channels, file transfer in Slack and a pre-built... Context & related coverage →