Entities · Models
Claude Sonnet 4.6
47 articles tagged with this entity.
-
The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI
-
Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents
-
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
-
Seduced by the Narrative: Assessing Rule Adherence in Semi-Open Textual Sandboxes
-
EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation
-
LLMs as Teaching Assistants for Mathematics Exam Grading: Reliability, and Practical Usability
-
Citation Discipline in Spec-Driven Development: A Cross-Model Empirical Study of Output Determinism and Automated Hallucination Detection in LLM-Generated Code
-
Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering
-
What's new in Claude Sonnet 5
-
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
-
IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations
-
Hierarchical Experimentalist Agents
-
Instruction Bleed: Cross-Module Interference in Prompt-Composed Agentic Systems
-
When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs
-
REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection
-
Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies
-
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
-
Unintended Effects of Geographic Conditioning in Large Language Models
-
Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems
-
PrologMCP: A Standardized Prolog Tool Interface for LLM Agents
-
HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools
-
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
-
Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis
-
$\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems
-
Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models
-
Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories
-
Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR
-
Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy
-
When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents
-
Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming
-
Scaffold, Not Vocabulary? A Controlled, Two-Tier, Pre-Registered Study of a Popperian Code-Generation Skill
-
Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models
-
Interfaze: The Future of AI is built on Task-Specific Small Models
-
ATLAS: Agentic Test-time Learning-to-Allocate Scaling
-
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
-
From Outliers to Errors: Auditing Pali-to-English LLM Translations with Multi-Reference Adjudication
-
Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas
-
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
-
The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
-
Training Deliberative Monitors for Black-Box Scheming Detection
-
Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension
-
Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
-
PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation
-
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
-
UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Tasks
-
Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation
-
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction