…Jona te Lintelo , , , , Abstract MASCing is a framework that enables flexible reconfiguration of Mixture-of-Experts model behavior for safety objectives through steering matrices and routing gate modifications without requiring retraining. AI…
…Debugging (2026) Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety (2026) Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework (2026) CritBench: A…
…in Embodied AI (2026) The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents (2026) EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents (2026) PRISM: : Planning and Reasoning with…
…graded rubric and inherits that evaluator's exposure. View arXiv page View PDF Project page Add to collection Community https://lixin.ai/ListOPD Get this paper in your agent: hf papers read…
…Furthermore, we curate representative datasets, benchmarks, and evaluation metrics, offering a structured comparison across task families and identifying open challenges in synchronization , spatial reasoning , controllability , and safety . By consolidating this rapidly expanding…
…Daoxuan Zhang , , , Abstract Embodied Search and Rescue task and benchmark are introduced to evaluate multimodal large language model-driven UAV agents in realistic search and rescue scenarios with dynamic environmental conditions. AI…
…Benchmarking LLM Agents on Real-World Hardware Bug Repair Tasks (2026) ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces (2026) Spec Kit Agents: Context-Grounded Agentic Workflows (2026…
…AI-generated summary End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficient inference. Existing paradigms typically fall short: autoregressive…
…Accepted to ICML 2026 Workshop Scalable Learning and Optimization for Efficient Multimodal AI Agents (SCALE) This is an automated message from the Librarian Bot . I found the following papers similar to this…
…AI-generated summary Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effective and diverse attacks in red-teaming is important…