Entities · Models
Claude Haiku 4.5
16 articles tagged with this entity.
-
Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents
-
Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents
-
Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare
-
MCP Server Architecture Patterns for LLM-Integrated Applications
-
Peer-Preservation in Frontier Models
-
HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools
-
CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies
-
From `May' to `Is': Certainty Distortion in Language Model Rewriting
-
Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs
-
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
-
FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks
-
Training Deliberative Monitors for Black-Box Scheming Detection
-
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
-
Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework
-
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
-
Jailbreaking Vision-Language Models Through the Visual Modality