Long-horizon robot execution requires a clear distinction between a model's proposal, a controller's termination, and verified task completion. We present RegenHarness, an evidence-gated robot-agent harness connecting task planning to heterogeneous robot skills. Its execution architecture couples a model loop for conte...
Kai-Lin Wang, Hao-Xiang Jie, Yao-Yuan Yan et al.· 1 citation
Memory-augmented agents typically integrate procedural knowledge by injecting retrieved skills directly into text prompts. This approach dangerously equates readable text with reliable execution. To bridge this gap, we introduce From Memory to Guide, a novel paradigm that transitions procedural memory from passive text...
Tan Zhi-Xuan, Peng-Jie Gu, Zhao-Song Li et al.· 0 citations
While large language models have achieved remarkable success in isolated code generation, authentic software engineering requires sustained reasoning, complex state management, and continuous cross-domain abstraction. However, current evaluations of skill evolution in autonomous agents suffer from a critical identifiab...
Tan Zhi-Xuan, Peng-Jie Gu, Zhao-Song Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.