Tag
论文提出轨迹接地指令翻译器(TGIT),在冻结的空中VLN导航器前端将简短的用户意图指令翻译为可执行命令,解决训练指令与部署指令之间的"指令差距",将真实人类指令上的成功率从11.33%提升至32.51%。
Introduces AdaCoM, an external LLM-based context manager for frozen agents, using reinforcement learning to improve long-horizon task performance by preserving task constraints and pruning stale content, with experiments on web search and deep research benchmarks.