safety-verification

Tag

Cards List
#safety-verification

BernBRS: Certified Backward Reachability for Deep Bernstein Neural Networks

arXiv cs.LG ↗ · 4d ago Cached

The paper introduces BernBRS, a scalable framework for certified backward reachability analysis of DeepBernNets, computing certified inner and outer approximations of the Backward Reachable Set via activation-pattern-based refinement of the input space cover, demonstrated on Half-Cheetah and TinyBERT-derived models.

0 favorites 0 likes
#safety-verification

Learning Regions of Attraction for Transverse Feedback Linearization under Controller Singularities

arXiv cs.AI ↗ · 4d ago Cached

This paper learns the constrained region of attraction for transverse feedback linearization under controller singularities by decomposing the Zubov value function into an analytic quadratic cost-to-go and a learned safety value function via fitted value iteration, achieving substantially better coverage than quadratic and PINN baselines on unicycle and quadrotor path-following tasks.

0 favorites 0 likes
#safety-verification

SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety

arXiv cs.CL ↗ · 2026-09-30 Cached

SCOUT introduces a two-stage agentic safety verifier that combines reasoning-intensive rubric generation with tool-intensive evidence gathering to detect unsafe behaviors in computer-use agents, improving unsafe detection on AutoElicit-Bench and reducing unsafe execution rates from 30.2% to 17.2% via test-time reflection.

0 favorites 0 likes
#safety-verification

PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents

Hugging Face Daily Papers ↗ · 2026-08-20 Cached

PolicyGuide compiles domain policies into workflow graphs and uses a proactive verifier to guide LLM agents through multi-step procedures, improving policy compliance across various benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback