4 papers
Reinforcement Learning with Robust Rubric Rewards
Ya-Qi Yu, Hao Wang, Fangyu Hong +15
While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi…
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
Yusong Lin, Xinyuan Liang, Haiyang Wang +8
Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate o…
CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion
Yusong Lin, Haiyang Wang, Shuzhe Wu +4
Agentic coding requires agents to effectively interact with runtime environments, e.g., command line interfaces (CLI), so as to complete tasks like resolving dependency issues, fix…
FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
Qixing Zhou, Jiacheng Zhang, Haiyang Wang +9
Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presenc…