Papers2

#code interpreter

AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

Zhaochen Su, Jincheng Gao et al.Feb 26arXiv

AgentVista is a new test (benchmark) that checks whether AI agents can solve tough, real-life picture-based problems by using multiple tools over many steps.

#AgentVista#multimodal agents#visual grounding

MAXS: Meta-Adaptive Exploration with LLM Agents

Intermediate

Jian Zhang, Zhiyuan Wang et al.Jan 14arXiv

MAXS is a new way for AI agents to think a few steps ahead while using tools like search and code, so they make smarter choices.

#LLM agents#tool-augmented reasoning#lookahead