Agentic Reinforcement Learning (RL) trains LLM agents through multi-turn interactions with external tool environments. Its multi-turn nature exposes two system-level bottlenecks unaddressed by existing agentic RL frameworks. First, end-to-end training throughput is constrained by the slowest trajectories to complete, y...
Ming-Jun Zhang, Yu-Cheng Li, Meng-Hao Zhang et al.· 0 citations
To the best of this audit, this is the first automated system to synthesize this trace-tree model family, generate well-founded inversion proofs, and emit self-contained Lean 4 certificates.
Jia-Ming Zhao, Bing Wu, Tong-Bin Yang et al.· 0 citations
The results support a compact, Fisher-conditioned privileged subspace for short-budget OPSD, with strict gains in 11 of the 12 model-checkpoint combinations and an exact tie at 4B step 25.
Yun-Meng Chen, Kun Wang, Pei-Han Li et al.· 1 citation
An externally anchored leading-order effective field linking empirical dynamics, an interpretable mechanism and neural computation is identified linking empirical dynamics, an interpretable mechanism and neural computation in closed-loop human-AI systems.
Min-Lin Wu, Xu Fang, Yi-Cheng Zhang et al.· 0 citations
A unified execution model that maintains a work item's persistent identity and versioned authoritative state across calls is introduced that is associated with higher end-to-end pass rates across fresh sessions in this benchmark, at a measurable time cost.
Zhen-Hang Nie, Gui Zheng, Xudong Sun 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.
