This work presents CoworkEnv, a capability-guided framework for synthesizing executable training environments for AI coworkers, and compares RL training dynamics across configurations that vary reward processing and credit assignment.
Zhong-Wei Xie, Yi-Ming Du, Jiaxin Bai et al.· 0 citations
Although large language models (LLMs) encode language in highly distributed spaces, they remain vulnerable to focal disruptions---a phenomenon strikingly similar to how localized brain damage causes clinical aphasia in humans. To investigate this theoretical tension, we ask whether LLMs possess a functional structure a...
Mu-Xuan He, Wang Bill Zhu, Yue-Ying Chen et al.· 0 citations
Repeated event forecasting requires extracting predictive signals from noisy evidence and evaluating their value across successive decisions. We introduce JockeyBench, a benchmark and evaluation protocol that studies this problem through historical Japanese horse racing. The protocol combines time-gated evidence, price...
Zhong-Wei Xie, Xing-Su Li, Jing Yu et al.· 0 citations
Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces a failure mode we call co-cheating: the proposer and solver increasingly agree on shared errors, so internal reward improves without a matc...
Mei-Jia Chen, Hao Li, Zheng Lu et al.· arXiv.org· 3 citations
Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a single language and depend on manually curated tasks. We introduce Zero2Repo, a benchmark in which an agent receives a product requirements document, an interface...
Pei Yang, Tian-Yu Shi, Yu-Hang Yao et al.· 0 citations
Empirically, UOPD is evaluated across a broad range of agentic tasks, including ALFWorld, WebShop, and Search, demonstrating its superior performance over OPD methods and their variants.
Wen-Bo Zhang, Peng-Cheng Xu, Wei-Zhi Du et al.· 3 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.