The proposed exploration-augmented key-observation gating first determines whether the current RL episode is judgment-worthy based on its similarity to a generated success trajectory, and proposes VLM success reward via Exploration-Augmented Key-Observation Gating (VLMeg) to well harness VLM for embodied reward design.
Xin Liu, Yu-Tong Jiang, Jia-Yue Su et al.· 0 citations
Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior. For long-horizon tasks, each rollout is costly, and a limited interaction budget may yield few examples of effective behavior. Sparse, delayed feedback also makes it difficu...
Li-Rong Che, Yu-Zhe Yang, Pei Lin et al.· 5 citations· ⚡1
This work introduces HarnessVLN, a zero-shot, training-free framework that unifies instruction-following and object-goal navigation through a shared Agent Harness and demonstrates its applicability to both navigation tasks in real-world environments.
Yang Chen, Li-Rong Che, Zhen-Yu Huang et al.· 6 citations· ⚡2
CoBench is introduced, a construct-level benchmark for evaluating multi-agent embodied coordination in executable household tasks and shows that coordination ability is highly construct-specific: strong overall performance does not imply balanced competence across different coordination types.
Yang Chen, Ye-Xin Xie, Li-Rong Che 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.
