Coding Agents with Multimodal Browsing are Generalist Problem Solvers

TL;DR

OpenHands-Versa is a versatile AI agent utilizing a minimal set of general tools like code editing, web search, and multimodal browsing, achieving high performance across diverse benchmarks and surpassing specialized agents.

Contribution

This work introduces OpenHands-Versa, a generalist agent with a limited toolkit that outperforms specialized agents on multiple challenging benchmarks.

Findings

OpenHands-Versa outperforms previous best results on three benchmarks.

A minimal set of general tools can achieve high task performance.

Existing multi-agent systems lack generalization beyond their specific domains.

Abstract

Modern human labor is characterized by specialization; we train for years and develop particular tools that allow us to perform well across a variety of tasks. In addition, AI agents have been specialized for domains such as software engineering, web navigation, and workflow automation. However, this results in agents that are good for one thing but fail to generalize beyond their intended scope. One reason for this is that agent developers provide a highly specialized set of tools or make architectural decisions optimized for a specific use case or benchmark. In this work, we ask the question: what is the minimal set of general tools that can be used to achieve high performance across a diverse set of tasks? Our answer is OpenHands-Versa, a generalist agent built with a modest number of general tools: code editing and execution, web search, as well as multimodal web browsing and file access. Importantly, OpenHands-Versa demonstrates superior or competitive performance over leading specialized agents across three diverse and challenging benchmarks: SWE-Bench Multimodal, GAIA, and The Agent Company, outperforming the best-performing previously published results with absolute improvements in success rate of 9.1, 1.3, and 9.1 points respectively. Further, we show how existing state-of-the-art multi-agent systems fail to generalize beyond their target domains. These results demonstrate the feasibility of developing a generalist agent to solve diverse tasks and establish OpenHands-Versa as a strong baseline for future research.