Agents

LinkedIn detailed a Kubernetes-based multi-agent AI code review platform that completes 79,000+ reviews weekly, with a 63.9% developer acceptance rate.

A new empirical study finds 248,641 AI-authored GitHub pull requests have already received an AI-generated review, with distinct patterns by agent pairing.

A new empirical study finds coding agents overwhelmingly read and write their own instruction files, rarely touch classical documentation, and almost never use docs to recover from failures.

Cloudflare opens a private beta of WriteGuard, a policy and audit layer that classifies and can block risky write actions AI agents take through MCP servers.

AMD's open-source local AI agent framework for Ryzen AI NPUs gains a terminal-native agent hub, cross-surface confirmation gates, and MCP security fixes.

A George Mason University study finds a software task's difficulty for AI coding agents can be predicted from patch and repository structure before the agent ever runs.

A Google study finds AI agents that first write a semi-formal specification before generating tests catch 9.8 percentage points more real bugs than agents that generate tests directly.

A study spanning seven AI models and five coding-agent harnesses finds they fail identically when a required repository fact is unavailable, and fabricate rather than stop.

A new study finds AI-written bug-fix patches are far larger and more complex than developers' own fixes even when tests pass, and proposes a lightweight adapter called RECAP to trim the bloat.

DeepSeek released its Harness agent runtime as MIT-licensed open source and rolled out DeepSeek-V4-Pro with native OpenAI Responses API support.

Six companies agreed on a shared packaging format for AI agent skills and MCP servers; Anthropic, which created the underlying protocols, is not part of the effort.

Bank of America has enhanced EricaAssist, the AI agent used by more than 18,000 customer service representatives, with generative AI that delivers guidance in under three seconds.