Survey Maps 119 Personal-Agent Systems Across Six Levels of Loop Closure
liuziwei7 · x · 2026-11-09
Ziwei Liu shares a survey titled "Always-On Personal Intelligence: A Roadmap Towards Continuing, Self-Evolving Loops," a joint effort from NTU, UC Berkeley, Princeton, Stanford, NUS, KAUST, Dartmouth, UNC Chapel Hill and Northwestern.
- Defines an always-on assistant as Sensing, Memory and Action linked by six channels.
- Reviews each module and places 119 systems on six levels of loop closure.
- Flags two channels as notably underdeveloped (text truncated at that point).
- Context: frontier labs have shipped personal agents such as Muse, dots, Claude Duet, Grok Bot and Gemini Daily Brief, while wearables like Omi and Bee capture conversations all day; robots are following the same path, with frontier models becoming their high-level brain.
Related event: Nine Universities Release Survey on Always-On Personal AI Agents(2 posts)→
More from AGI Musings
- A week toward the singularity: Anthropic speeds up 2x, Claude does 3-day lab work in 90 minutes — rand_longevity · 2026-11-09
- Anthropic's amended S-1 warns of imminent 'dramatically accelerated' AI-driven R&D progress — TheZvi · 2026-11-09
- METR: Anthropic's AI R&D is accelerating at ~2x, recursive self-improvement possibly under a year away — Don't Worry About the Vase (Zvi) · 2026-11-09
- Perplexity CEO touts model-neutrality as crypto's 'credible neutrality' idea reaches AI — dnlkwk · 2026-11-09
- InstaDeep CEO: Anthropic's unreleased Models 3 and 4 sit halfway to AI2027's Agent-2 — connoraxiotes · 2026-11-09
- Nature review: AI has transformed maths — and may outgrow human insight — LucaAmb · 2026-11-09