Stanford & Northeastern unveil Retriever, a time-aware programming framework for long-horizon robots
yining_hong · x · 2026-10-30
Linfeng Zhao's team at Stanford and Northeastern introduce Retriever, a programming framework for asynchronous, closed-loop robot manipulation systems, asking what interface should connect increasingly capable coding agents to the physical world.
Key ideas:
- Robot agents run in physical time with multiple feedback loops, but lack a good programming abstraction;
- Retriever adds a time-aware building block called "Flow", analogous to a PyTorch layer or a Ray Actor;
- Users wire Flows together and specify when each runs and what inputs it reads; the framework handles asynchronous execution.
More from coding & agent
- Repo-native tooling: a sandboxed agent workflow using Git as a dead drop — OutrageousAbies5835 · 2026-10-30
- Anthropic engineer shows agent engineering shifting from prompts to self-improving systems — goyalshaliniuk · 2026-10-30
- The agent harness isn't for the agent — it's for us — seanmcdonaldxyz · 2026-10-30
- YC F26's Composal sends agent swarms to test your product like real users — ycombinator · 2026-10-30
- KreaMossMix ComfyUI workflow chains MOSS-Image and Krea 2 for four image variants per prompt — Plane-Implement1044 · 2026-10-30
- Dev builds fail-closed MCP tool that refuses to PASS unverified US businesses — cstill_dev · 2026-10-30