Appendix — References
Overview#
This appendix curates a small set of papers and projects across foundational areas that repeatedly show up in AGI-adjacent system design: world modeling, memory, reasoning & planning, embodiment, autonomy, and safety & alignment.
How to use this appendix#
The appendix surveys research areas often associated with AGI-scale capability. These are not presented as requirements, predictions, or a roadmap.
They are included to ground claims made in the core sections about autonomy, feedback, and system reliability in existing technical work.
The core paper intentionally avoids architectural prescriptions; the appendix exists to map the surrounding landscape for readers who want to explore it.
Chapters#
| Chapter | Scope | Route |
|---|---|---|
| World models | Predictive representations, latent dynamics, model-based control. | Open |
| Memory | Retrieval, persistence, and memory as an agent-system interface. | Open |
| Reasoning & planning | Decomposition, tool use, search over thoughts/programs, planning loops. | Open |
| Embodiment | Vision-language-action policies, imitation, and robotics benchmarks. | Open |
| Autonomy | Agents in web/software environments, exploration, orchestration, guardrails. | Open |
| Safety & alignment | Preference learning, evaluation, interpretability, monitoring. | Open |