9 papers · 1 filter
State2State: Environment-Derived Mid-Training for LLM Agents
Xuanyu Lei, Yiqi Zhu, Chenliang Li +6
Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Thoug…
Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
Mingyang Li, Yurou Liu, Jieping Ye +3
In this report, we present LOGOS (Language Of Generative Objects in Science), a scientific generative language model that unifies heterogeneous tasks across the natural sciences wi…
EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management
Rongzhi Zhu, Xiang Huang, Yuchuan Wu +8
Emotional intelligence (EI) in Large Language Models (LLMs) is often evaluated through static understanding tasks or single-response dialogue generation. However, emotion managemen…
SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization
Qi Zhang, Zhaopeng Feng, Xiaonan Shi +8
Agent skills, which consist of reusable strategies that guide agent reasoning and action, have shown strong potential for improving model capability at inference time. However, cur…
STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments
Junyang Wang, Haiyang Xu, Xi Zhang +4
Mobile GUI agents excel at immediate reactive control but frequently fail in realistic, long-horizon tasks that require memory. This failure stems from a fundamental conflict betwe…
Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation
Kaiyuan Liu, Ziyuan Zhuang, Yang Bai +3
On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is a…