8 papers
Evo-Bench: Can Language Models Improve Agent Harness?
Lisheng Huang, Chen Yang, Hao Zhou +6
Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolu…
Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model
Nanbeige Lab, :, Chen Yang +23
We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-agent, and complex tool-use ta…
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
Hao Zhou, Tiru Wu, Yan Jiang +3
Multi-modal multi-agent systems (MM-MAS) have gained increasing attention for their capacity to enable complex reasoning and coordination across diverse modalities. As these system…
CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning
Qi Song, Honglin Li, Yingchen Yu +6
Recent releases such as o3 highlight human-like "thinking with images" reasoning that combines tool use with stepwise verification, yet most open-source approaches still rely on te…
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Xiaoyu Tian, Haotian Wang, Shuaiting Chen +12
Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing meth…
CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations
Huan-ang Gao, Zikang Zhang, Tianwei Luo +9
Large Language Model (LLM) agents, while proficient in the digital realm, face a significant gap in physical-world deployment due to the challenge of forming and maintaining a robu…