Learning from Human Demonstrations Enables Adaptive GUI Agents
Pre-submission to ARR. Corresponding author. Adaptive GUI agents learning from human demonstrations.
yuepeng-fu
•
•
1 分钟阅读时长
Test-Time Exploration in Unknown Environments
Submitted to KDD 2026. Corresponding author. Test-time exploration in unknown environments.
wentong-chen
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
Submitted to KDD 2026. Corresponding author. Diagnosing step-level process quality in tool-using agents.
shengda-fan
AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
ArXiv 2026. First author. Open-source 4B agent model achieving SOTA on GAIA & HLE, surpassing GPT-5 and Claude-4.5-Sonnet.
ToLeaP: Rethinking Development of Tool Learning with Large Language Models
Submitted to ACL 2026. First author. Unified evaluation platform for tool-learning agents.
Reflective Reinforcement Tool Learning
Submitted to ACL 2026. Reflective reinforcement learning for tool learning.
Diversity-aware Training for Test-time Scaling
Submitted to ACL 2026. Corresponding author. Diversity-aware training for test-time scaling.
bohan-lyu
AtomMem: Learnable Dynamic Agentic Memory with Atomic Memory Operation
Submitted to ACL 2026. Corresponding author. Learnable dynamic agentic memory with atomic operations.
yupeng-huo
MiniCPM4: Ultra-Efficient LLMs on End Devices
ArXiv 2025. Team contribution (led MCP agent capabilities). 8,300+ GitHub Stars.
minicpm-team
Collaborative Evolving Strategy for Automatic Data-Centric Development
ArXiv 2024. Co-first author. Collaborative evolving strategy for data-centric development. 11,400+ GitHub Stars.
xu-yang