Autonomous Software Testing
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Governance Controls for AI-Generated Test Artifacts in Autonomous Software Testing
Announce Type: new Abstract: Artificial Intelligence (AI) and Large Language Models (LLMs) are increasingly used in autonomous software testing; however, AI-generated test artifacts often suffer from hallucinations, compliance violations, security risks, and limited explainability. To enhance the reliability, transparency, and trustworthiness of AI-generated testing artifacts, this research introduces the concept of Governance-Aware Autonomous Testing Framework (GATF). The framework extends...
Driverless taxis: Uber plans to test autonomous robotaxis in Munich
In San Francisco and Beijing they are already a familiar sight; soon driverless taxis could also be ferrying passengers around Munich. Uber plans to roll out autonomous robotaxis there, but it is still waiting for the green light from regulators. The decision was announced in Taipei, but it actually concerns a completely different city: in Munich, Uber plans to deploy autonomous robotaxis together with the AI company Autobrains.
FASE: Fast Adaptive Semantic Entropy for Code Quality
arXiv:2606.09800v1 Announce Type: new Abstract: Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle. However, system reliability remains hindered by LLM hallucinations and error propagation across interacting agents. While semantic entropy provides a principled way to quantify uncertainty without ground-truth answers, current methods often rely on costly LLM-driven equivalence checks.
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
arXiv:2606.05391v1 Announce Type: new Abstract: Autonomous software agents hold promise to increase developer productivity but make mistakes and exhibit novel failure modes, making human oversight central to successful human-agent collaboration. Existing research on agent oversight is largely conceptual; normative frameworks exist, but how users actually oversee agents is less known. In this paper, we bridge this gap by providing early empirical anchors for the theoretical discourse on agent...
A Causal Probabilistic Framework for Perception-Informed Closed-Loop Simulation of Autonomous Driving
Announce Type: new Abstract: Software-in-the-loop (SIL) simulation is a cornerstone for the validation of modern automotive safety functions. However, many current frameworks utilize ideal sensing, which bypasses the functional insufficiencies of perception algorithms, leading to over-optimistic safety assessments. This paper proposes a perception-informed SIL testing methodology that bridges the gap between ground-truth simulation and real-world perception behavior.
Humanoid robots work nonstop in package test
Figure AI says three of its humanoid robots crossed more than 24 hours of continuous autonomous operation after a test that was supposed to last only eight hours kept running.The California-based robotics startup says its Helix-02 artificial intelligence-powered robots sorted small packages around the clock without human control. The robots became part of a livestream that viewers followed closely. They even picked up names along the way: Bob, Frank and Gary.Once people started calling them...
Cab-less electric trucks hit Ohio roads
A freight truck with no driver, no cab and no one sitting behind the wheel is starting to sound more familiar. In fact, this summer, that is exactly what is happening on local roads in Marysville, Ohio.EASE Logistics, an Ohio-based logistics company, is partnering with autonomous truck technology company Einride to deploy two cab-less electric trucks between EASE warehouse locations. The two companies recently announced the proof-of-concept service.The trucks will operate on EASE property...
Agentic Generation and Evolution of Knowledge Models
Announce Type: new Abstract: Complex software systems such as autonomous vehicles, robotics increasingly interact with dynamic physical, cyber, and social environments. Reasoning about their behavior, maintaining them under continuous change, and evolving them safely require trustworthy knowledge about the system, its assumptions, and its operating context. Knowledge models (KMs) provide a practical basis for such reasoning, but they may themselves become incomplete, inconsistent, or...
Agentic Generation and Evolution of Knowledge Models
arXiv:2606.03662v2 Announce Type: replace Abstract: Complex software systems such as autonomous vehicles, robotics increasingly interact with dynamic physical, cyber, and social environments. Reasoning about their behavior, maintaining them under continuous change, and evolving them safely require trustworthy knowledge about the system, its assumptions, and its operating context. Knowledge models (KMs) provide a practical basis for such reasoning, but they may themselves become incomplete,...
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
arXiv:2512.18552v3 Announce Type: replace Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g., pass-to-pass and fail-to-pass tests) heavily depend on human knowledge or curation, posing a fundamental barrier to superintelligence. In this paper, we present Self-play SWE-RL (SSR), a first step toward training...