NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and decide. Physical interaction, however, remains the domain of action policies, which provide dense, low-latency control. We present NavGPT-3, a harness that connects the two models, with an OS-like runtime built above it: reasoning, acting, and monitoring run as threads with their own context, tools, and permissions, while the runtime schedules them and decides which thread controls the robot's motion, so that the robot can react to sudden real-world ev...
| Authors | Gengze Zhou, Yicong Hong, Jiazhao Zhang et al. |
|---|---|
| Primary category | cs.RO |
| Published | 7 October 2026 |
| Last updated at source | 12 October 2026 |
Popularity, last 3 days
0 now (-5 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 16 Oct 2026 Description: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and → Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and
- 16 Oct 2026 Topics added cs.RO, cs.AI, cs.CL, cs.CV, cs.LG removed hf-daily-papers, agentic reinforcement learning, reasoning, action policies, navgpt-3, os-like runtime, thread switching, interruption, navgpt vla
Changes detected by Silytics between refreshes of the source.
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.