SenseNova-RoboRSI 用 RSI 循环改进智能体框架，RoboDojo 平均分达 56.83
A stronger robot doesn't always require a stronger foundation model.
SenseTime 的 SenseNova 团队提出 SenseNova-RoboRSI，在不更新 GPT-6 Astra 模型权重的情况下，通过递归自我改进（RSI）循环演化智能体框架，在 RoboDojo 上取得 56.83 平均分和 50.83% 任务成功率，对比已公布的 28.97 基线提升 27.86 分。该方法还报告了 LIBERO-PRO 94.50% 和 RoboCasa 64.60 的结果，并探索了多点末端执行器（EEF）预测以及规划与反馈子智能体，让主智能体拆解任务、执行动作并根据反馈调整后续动作。团队表示 RoboRSI 即将开源，完整技术报告也在准备中。
查看原帖🤖 𝗘𝘃𝗲𝗿𝘆 𝗿𝗼𝗯𝗼𝘁 𝘁𝗮𝘀𝗸 𝗳𝗮𝗶𝗹𝘂𝗿𝗲 𝗰𝗮𝗻 𝗯𝗲𝗰𝗼𝗺𝗲 𝗮 𝗹𝗲𝘀𝘀𝗼𝗻 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗻𝗲𝘅𝘁 𝗶𝘁𝗲𝗿𝗮𝘁𝗶𝗼𝗻. 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮-𝗥𝗼𝗯𝗼𝗥𝗦𝗜 uses 𝗥𝗦𝗜 to evolve 𝗮𝗴𝗲𝗻𝘁 𝗵𝗮𝗿𝗻𝗲𝘀𝘀𝗲𝘀 through physical task feedback, without updating model parameters. ▶ 𝗥𝗼𝗯𝗼𝗗𝗼𝗷𝗼: 56.83 avg. score, 50.83% success rate, +𝟮𝟳.𝟴𝟲…
展开完整原文
🤖 𝗘𝘃𝗲𝗿𝘆 𝗿𝗼𝗯𝗼𝘁 𝘁𝗮𝘀𝗸 𝗳𝗮𝗶𝗹𝘂𝗿𝗲 𝗰𝗮𝗻 𝗯𝗲𝗰𝗼𝗺𝗲 𝗮 𝗹𝗲𝘀𝘀𝗼𝗻 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗻𝗲𝘅𝘁 𝗶𝘁𝗲𝗿𝗮𝘁𝗶𝗼𝗻. 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮-𝗥𝗼𝗯𝗼𝗥𝗦𝗜 uses 𝗥𝗦𝗜 to evolve 𝗮𝗴𝗲𝗻𝘁 𝗵𝗮𝗿𝗻𝗲𝘀𝘀𝗲𝘀 through physical task feedback, without updating model parameters. ▶ 𝗥𝗼𝗯𝗼𝗗𝗼𝗷𝗼: 56.83 avg. score, 50.83% success rate, +𝟮𝟳.𝟴𝟲 𝗽𝗼𝗶𝗻𝘁𝘀 𝘃𝘀. 𝘁𝗵𝗲 𝗚𝗣𝗧-𝟲 𝗔𝘀𝘁𝗿𝗮 𝗯𝗮𝘀𝗲𝗹𝗶𝗻𝗲 (𝟮𝟴.𝟵𝟳) ▶ 𝗥𝗦𝗜 𝗹𝗼𝗼𝗽: Execute → Diagnose → Improve → Validate → Inherit ▶ 𝗘𝘅𝗽𝗹𝗼𝗿𝗲𝗱 𝗮𝗻𝗱 𝘃𝗮𝗹𝗶𝗱𝗮𝘁𝗲𝗱: Multi-point EEF prediction and Planning + Feedback Subagents This achievement reflects the collective efforts of our joint team. RoboRSI will be 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲𝗱 𝘀𝗼𝗼𝗻 at https://t.co/iTVQ1YDFcn. A comprehensive 𝘁𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝗿𝗲𝗽𝗼𝗿𝘁 detailing our methods and findings is also on the way. Stay tuned!
正文
当前显示原文，中文全文译文尚未就绪。
A stronger robot doesn't always require a stronger foundation model. Sometimes, it just needs a better way to act.
Recent research from SenseNova team offers an interesting example of how agent system design can improve embodied AI performance.
With GPT-6 Astra's model weights unchanged, SenseNova-RoboRSI reports a RoboDojo average score of 56.83, compared with a published baseline of 28.97, alongside a 50.83% task success rate.
It also reports strong results on LIBERO-PRO (94.50%) and RoboCasa (64.60).
One strategy explored by SenseNova-RoboRSI is multi-point end-effector (EEF) prediction. Rather than predicting and executing one target at a time, it generates short sequences of action targets in a single step, helping improve motion continuity while reducing repeated model calls.
Combined with Planning and Feedback Subagents, the Main Agent can break down tasks, execute actions, monitor progress, and adjust subsequent actions based on feedback.
More importantly, SenseNova-RoboRSI brings these strategies into a recursive self-improvement (RSI) loop, where execution results help guide improvements to future agent harness configurations.
Improving the harness may become just as important as improving the model itself.