y0news
#formal-verification4 articles
4 articles
AIBullisharXiv – CS AI · 4h ago4
🧠

Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments

Researchers propose a new framework for foundation world models that enables autonomous agents to learn, verify, and adapt reliably in dynamic environments. The approach combines reinforcement learning with formal verification and adaptive abstraction to create agents that can synthesize verifiable programs and maintain correctness while adapting to novel conditions.

AIBullisharXiv – CS AI · 4h ago3
🧠

Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification

Researchers developed a neurosymbolic verification framework to audit logical consistency in AI-generated radiology reports, addressing issues where vision-language models produce diagnostic conclusions unsupported by their findings. The system uses formal verification methods to identify hallucinations and missing logical conclusions in medical AI outputs, improving diagnostic accuracy.

AIBullisharXiv – CS AI · 4h ago4
🧠

SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems

Researchers propose SafeGen-LLM, a new approach to enhance safety in robotic task planning by combining supervised fine-tuning with policy optimization guided by formal verification. The system demonstrates superior safety generalization across multiple domains compared to existing classical planners, reinforcement learning methods, and base large language models.

AIBullisharXiv – CS AI · 4h ago5
🧠

Provably Safe Generative Sampling with Constricting Barrier Functions

Researchers have developed a safety filtering framework that ensures AI generative models like diffusion models produce outputs that satisfy hard constraints without requiring model retraining. The approach uses Control Barrier Functions to create a 'constricting safety tube' that progressively tightens constraints during the generation process, achieving 100% constraint satisfaction across image generation, trajectory sampling, and robotic manipulation tasks.