9 papers
Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity
Doyoung Kim, Zhiwei Ren, Jie Hao +11
We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents' function-calling capabilities under realistic API complexity. Unlike prior work that a…
Robust, Observable, and Evolvable Agentic Systems Engineering: A Principled Framework Validated via the Fairy GUI Agent
Jiazheng Sun, Ruimeng Yang, Xu Han +5
The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these defic…
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
Xingcheng Zhou, Xuyuan Han, Feng Yang +3
We present OpenDriveVLA, a Vision Language Action model designed for end-to-end autonomous driving, built upon open-source large language models. OpenDriveVLA generates spatially g…
Driving with Regulation: Trustworthy and Interpretable Decision-Making for Autonomous Driving with Retrieval-Augmented Reasoning
Tianhui Cai, Yifan Liu, Zewei Zhou +6
Understanding and adhering to traffic regulations is essential for autonomous vehicles to ensure safety and trustworthiness. However, traffic regulations are complex, context-depen…
MiniCPM4: Ultra-Efficient LLMs on End Devices
MiniCPM Team, Chaojun Xiao, Yuxuan Li +80
This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in…
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Yunhe Yan, Shihe Wang, Jiajun Du +12
(M)LLM-powered computer use agents (CUA) are emerging as a transformative technique to automate human-computer interaction. However, existing CUA benchmarks predominantly target GU…