الباحثون

Bryan Kian Hsiang Low

المنشورات 2

نسخة أولية وصول مفتوح

MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution

Zhiwei Shang, Yu Huo, Mingrong Gong وآخرون · 2026

An agent harness is the code that organizes context, maintains state, and coordinates tool calls for a language model. We study how to improve the harness under a limited evaluation budget while keeping model weights fixed. Our method, MESH-Harness, organizes each harness into functional modules with explicit role-spec …

نسخة أولية وصول مفتوح

RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation

Jingtan Wang, Sirajul Salekin, Young mok Jung وآخرون · 2026

Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at the environment level or prioritize local reward-based signals, without explicitly considering rela …

المؤلفون المشاركون

Zhiwei Shang Yu Huo Mingrong Gong An Yan Zikun Qu Junhao Dong Chenglin Wu Zhongxiang Dai Jingtan Wang Sirajul Salekin Young mok Jung Javier Movellan