The OpenHands Software Agent SDK provides a composable architecture for production software agents featuring native sandboxed execution, multi-LLM routing, and built-in security analysis.
Coding agents with multimodal browsing are generalist problem solvers
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
A11YRepair uses divide-and-conquer clustering and WCAG knowledge to repair multi-fault accessibility violations in web projects, showing better results than baselines on a new 60-project benchmark with some patches merged upstream.
DIA uses autonomous coding agents with shared memory to automate data tasks and matches or exceeds prior best results on seven SQL benchmarks across dialects and categories.
Adding visual dependency-graph images to a text-based coding agent cuts token consumption by up to 26% while keeping issue-resolution accuracy roughly unchanged.
Control-theoretic guardrails enable proactive correction of risky LLM agent actions in latent space, preventing catastrophes like collisions or bankruptcy while preserving task performance in simulated environments.
CVEvolve is a zero-code LLM agent harness that autonomously discovers algorithms for scientific image tasks including registration, peak detection, and segmentation, reporting improvements over baselines via iterative search and holdout evaluation.
citing papers explorer
-
The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
The OpenHands Software Agent SDK provides a composable architecture for production software agents featuring native sandboxed execution, multi-LLM routing, and built-in security analysis.
-
A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair
A11YRepair uses divide-and-conquer clustering and WCAG knowledge to repair multi-fault accessibility violations in web projects, showing better results than baselines on a new 60-project benchmark with some patches merged upstream.
-
Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents
DIA uses autonomous coding agents with shared memory to automate data tasks and matches or exceeds prior best results on seven SQL benchmarks across dialects and categories.
-
LLM Agents Can See Code Repositories
Adding visual dependency-graph images to a text-based coding agent cuts token consumption by up to 26% while keeping issue-resolution accuracy roughly unchanged.
-
From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails
Control-theoretic guardrails enable proactive correction of risky LLM agent actions in latent space, preventing catastrophes like collisions or bankruptcy while preserving task performance in simulated environments.
-
CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing
CVEvolve is a zero-code LLM agent harness that autonomously discovers algorithms for scientific image tasks including registration, peak detection, and segmentation, reporting improvements over baselines via iterative search and holdout evaluation.