Indeed an exceptionally beautiful paper.
Two key decoupling insights from the paper on skill evolution for AI Agents:
1. Separate raw execution traces, accumulated knowledge base, and skill evolution during the skill iteration lifecycle.
2. Decouple the skill‑discovery phase from the skill‑execution phase.
Besides, two critical properties deserve close attention for agent self‑evolution: the complementarity between skill evolution and LLM scaling, as well as the transferability of evolved skills.
Google's team just dropped a 9-page PDF on Harness Engineering - one formula replaced prompt engineering:
the twist: same Claude Sonnet, same benchmark - change only the harness
the formula: Agent = Model + Harness
here's the playbook in 6 steps:
step 1 → add guides - AGENTS.md, rule files, constraint docs - each line is a past agent failure turned into a permanent fix
step 2 → add sensors - linters, tests, validation scripts the agent runs on its own output before a human sees it
step 3 → build the agentic loop - plan, execute, verify, fix - bounded retries, budget caps, escalation when stuck
step 4 → externalize memory - the model forgets every session. the harness remembers state, decisions, and artifacts across all of them
step 5 → enforce permissions - which tools, how many writes, what needs approval. the model doesn't enforce safety. the harness does
step 6 → wire observability - track every tool call, cost, retry. trip wires fire when behavior drifts
the result: your agent stops being a demo and starts being infrastructure - every failure makes the system permanently better, not just the next conversation
this 9-page PDF is what comes after prompt engineering and context engineering
bookmark and build the full system from the article below ↓
Introducing Interactive Generative UI Artifacts!
Sometimes markdown, images, and Mermaid diagrams aren't enough for the agent to fully express an idea. Antigravity can now create rich, interactive artifacts. Explore everything from dynamic data visualizations to 3D explanatory simulations, rendered seamlessly inline and in your artifacts panel.
The AI-Native SDLC keeps human judgement central to the process and considers the governance and regulation requirements of large enterprise organizations.
The loop keeps running. Human judgement stays above it.
https://t.co/u42d0684gH
🚢 Marin 535B-A23B started training this week! As usual, the whole process is open.
Voyage plan: pretraining (80%) + midtraining (20%) on 18.75T tokens on 11 x GB200 NVL72 for ~3 months (2.7e24 FLOPs). Post-training will follow.
Before kicking off the run, we trained a 4-rung scaling ladder from 1.6B-A61M (48B tokens) to 27.7B-A1.2B (926B tokens) to debug issues, and to make a forecast of our hero run. This is by far our biggest run, so definitely expecting the unexpected.
Teams are using the open-source Codex harness to bring agents into the tools they already use, from internal apps to operations dashboards.
Their applications control the interface, context, tools, and approvals while the harness handles the agent loop.
https://t.co/shi2vwqxh4