Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-09-16 · source-backed
A ReAct agent scored 77.4% mean accuracy but succeeded on all 5 runs for only 53.0% of tasks, a 24.4-point consistency gap. IBM's Consistency Analyzer replays each decision step with k=5 controlled resampling to find flip-prone decisions without full task replays or ground truth, then converts those into guidelines injected at inference. Result: pass^5 to 69.0%, mean@5 to 81.0%, gap halved to 12.0pp, and +13.0pp transfer to similar tasks. Code is at AgentToolkit/altk-evolve with the report at arXiv 2609.08832.
Each link below shares sources, entities, or timing with this story.
Three memory strategies across eight models from 30B to 745B on AppWorld's 585 multi-step tasks. Curated retrieval gave gpt-oss-120b +16.1 percentage points on goal completion for 5% more tokens. DeepSeek-V3.2 needed the full guideline set for +9.5pp at a 78% token cost. GLM-5...
Google's A2UI (13K stars) is an open standard letting agents send declarative JSON component descriptions that clients render using native widgets — React, Flutter, SwiftUI. The security model is smart: agents can only request pre-approved components from a client catalog, pre...
chrome-devtools-mcp isn't another community MCP server with 200 stars and a README that doesn't match the code. It's Google's Chrome DevTools team shipping an official MCP server that gives any coding agent (Claude Code, Gemini CLI, Codex, Cursor) full access to Chrome DevTool...
Numbers first, because they're the whole argument. On AppWorld's 168 tasks with DeepSeek-V3.2: ALTK-Evolve hit 89.3% goal completion at 263K tokens per task. ACE hit 80.4% at 634K (IBM Research on HF). Nine points better, 41% of the tokens. On the weaker gpt-oss-120b: 56.0% at...
Founding signatories include AWS, Anthropic, Google, OpenAI, NVIDIA, Microsoft and GitHub, IBM, Red Hat, Cisco, JPMorganChase, Citi, the Rust Foundation, Zscaler, and Sonatype, with OpenSSF, CNCF, and OpenInfra participating. The open letter drew 455 points on HN. (Akrites / L...
Google Labs launched a Stitch 2.0 update on March 18 that does something nobody else has done: it creates a structured, portable, agent-readable handoff format between design tools and coding agents. The feature is called DESIGN.md — a markdown file that encodes design system...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.