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
Coding-agent approval interfaces bind a human decision to a command or tool call, while developer tools execute the transitive workflow that invocation activates. Package installation can run lifecycle hooks and write files; an MCP call can exercise network authority. We call the resulting record-coverage failure appro...
Jin-Qian Zhang, Hao-Jun Xia, Shu-Jiang Wu et al.· 0 citations
Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later model inputs, providers meter it again. An admitted malicious or compromised tool can thereby convert untrusted data into recurring victim-billed processing without victim c...
Jin-Qian Zhang, Hao-Jun Xia, Shu-Jiang Wu et al.· 0 citations
High-throughput experimentation and self-driving laboratories are drastically accelerating materials discovery, yet automated interpretation of X-ray powder diffraction (XRPD) data remains a critical rate-limiting step. Conventional search-match workflows rely heavily on expert manual intervention, while pure data-driv...
Hongqing V. Wang, Ming-Wei Chen, Hong Luo et al.· 0 citations
An object-centric 3D representation alignment framework built upon $\pi_0$, using SAM3D as a frozen 3D teacher to provide target-object 3D priors during training, which enables the policy to internalize target-object 3D information while preserving the original RGB-language-to-action inference pipeline without requirin...
Zong-He Liu, Shan Jie, Xiao-Quan Sun et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
