Terminal User Interfaces (TUIs) combine the stateful, screen-oriented behaviour of GUIs with terminal deployment and are now common in developer tools. Yet they lack a dedicated testing methodology.
arXiv:2608. 03743v1 Announce Type: cross Abstract: Terminal User Interfaces (TUIs) combine the stateful, screen-oriented behaviour of GUIs with terminal deployment and are now common in developer tools.
arXiv:2609.22000v1 Announce Type: new Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Re...
WebUIProof is a new execution‑oriented benchmark for WebUI code generation that supplies structured specifications and dense, executable interaction tests across general WebUIs and 3D interactive simulations. It employs a UI‑agent harness that runs tests in a headless browser using a plan–act–observe loop to locate DOM elements, perform actions, observe changes, and verify assertions. Evaluations on eight commercial LLMs reveal frequent interaction‑based failures, especially on 3D interfaces, and demonstrate that training compact models with RL rewards from these tests improves functional completion and reduces build failures.
arXiv:2606. 09426v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools.
arXiv:2604. 13072v2 Announce Type: replace-cross Abstract: OpenClaw-style personal assistants extend LLM agents from isolated tool use to open-ended, stateful, and personalized software environments.
arXiv:2606. 28480v1 Announce Type: cross Abstract: As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader range of general computer-use tasks beyond coding.
arXiv:2604. 06742v2 Announce Type: replace-cross Abstract: The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift towards intent-driven software development, where autonomous agents are expected to design and deliver complete, runnable software systems from scratch.
CUA-Universe is a scalable environment-to-data pipeline that transforms real desktop software into hybrid GUI+CLI environments, enabling agents to coordinate visual inspection with command-line operations. It includes App-Forge for reproducible VMs and CLI surfaces, Task-Weave for generating diverse hybrid tasks, and Path-Steer for efficient rollouts and trajectory harvesting. Training on this data improves agent success and efficiency across multiple benchmarks, demonstrating the value of hybrid interaction.
The paper introduces SWE-Flux, a repository‑level benchmark designed to test large language models’ ability to reason about runtime behavior. It contains 480 execution‑grounded instances from 12 real Python repositories, with gold answers automatically harvested from instrumented test executions. Evaluation of five LLMs shows the task remains difficult, with the best model achieving only 37% accuracy, and the benchmark can generate challenging variants through input perturbation.
GUI-CC is a benchmark designed to assess the contextual consistency of GUI world models when used as agent environments, rather than just one‑step next‑screen predictors. It includes two tracks: an offline reference‑action track that rolls models along real mobile GUI trajectories, and an online agent‑loop track where fixed probing agents interact with model‑generated UIs. The benchmark evaluates transition fidelity, plausibility, contextual consistency, and task progress across 500 offline trajectory tasks and 200 online tasks spanning 30 mobile apps.
arXiv:2609.06229v1 Announce Type: cross Abstract: Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical...
arXiv:2606. 24551v1 Announce Type: new Abstract: Computer-use agents can execute software tasks through either graphical interfaces or programmatic command interfaces, but existing evaluations confound interaction modality with differences in tasks, initial states, verifiers, and permitted actions.