XYZAILab launches 35B and 397B DeepSearch agents built in an AI4AI loop
机器之心 · wechat · 2026-07-25
What XYZAILab released
- XYZAILab launched two DeepSearchAgent systems: XYZ-Aquila-mini (35B) and XYZ-Aquila-pro (397B).
- The lab says both models set new state-of-the-art results on several DeepSearch benchmarks.
The core idea: AI4AI
- The project is framed as AI4AI: using AI to help build, debug, and improve AI systems themselves.
- The team says it ran a two-month effort with 10+ researchers, about 1,000 GPU-equivalent cards, and more than 300 agent workers.
- The workflow follows a human-governed loop: humans set goals, rules, budgets, and evaluation criteria; agents generate tasks, run experiments, propose fixes, and record evidence.
What changed in the system
- The system integrates task construction, training, runtime optimization, and evaluation into one closed loop.
- It introduces mechanisms such as append-only audit logs, visible state reconstruction, state-faithful SFT, and independent evaluators/gates.
- AI also proposed new engineering ideas from failure traces, including proactive context summarization and a persistent “research notebook” concept.
Results and implications
- XYZ-Aquila-mini reportedly leads on seven public benchmarks including BrowseComp, BrowseComp-ZH, DeepSearchQA, GAIA, LiveBrowseComp, Humanity’s Last Exam, and WideSearch.
- XYZ-Aquila-pro hits top public scores on some benchmarks and matches Kimi-K2.6 on DeepSearchQA.
- The lab positions DeepSearch as a first public proof that AI can drive an AI R&D loop, but only under explicit rules and independent verification.
More from coding & agent
- Anthropic makes agent memory file-based, exportable, auditable, and reversible — VraserX · 2026-07-25
- “Typing code was never the job,” argues a post on Claude and $500K engineers — gdechichi · 2026-07-25
- Etched says inference means owning the full stack, not just writing kernels — AccBalanced · 2026-07-25
- Open-source TokenShield adds turn-scoped hashes to stop CrewAI retry loops — bulleykebaal · 2026-07-25
- Abacus AI routes its xHigh agent mode to Opus 5 and GPT 5.6 — bindureddy · 2026-07-25
- Andrew Ng open-sources OpenWorker, a local-first desktop agent that can deliver finished work — 量子位 · 2026-07-25