Training prompts in online reinforcement learning (RL) differ substantially in how informative they are for the current policy: some are already saturated while others are too difficult to yield reliable learning signals, yet both receive equal rollout budget under standard training. We propose an exploration-guided pr...
Yuan-Hao Yue, Qianli Ma, Cheng-Yu Wang et al.· 0 citations
A two-stage self-evolutionary knowledge distillation framework that equips small MLLMs with robust and adaptive tool-use behaviors and introduces weighted semantic objectives and iteratively expand competence through error-driven optimization, hybrid experience replay, and group-relative policy refinement with multi-di...
Lei Shen, Cheng-Yu Wang, Yuanjie Lyu et al.· Proceedings of the 32nd ACM...· 0 citations
Autonomous multi-modal agents are increasingly important in real-world applications due to their ability to reason about complex environments and orchestrate tool use. However, deploying multi-modal large language models (MLLMs) for tool use is often constrained by computational cost and inference latency, creating a p...
Lei Shen, Chengyu Wang, Yuanjie Lyu et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
