✍️ Prompt Engineering - cwensel · Scour

Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents

🕵️AI Agents Academic

Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces

🔗LLM Workflows Academic

CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model

🧠LLMs Academic

PRISM: Recovering Instruction Sets from Language Model Activations

🧠LLMs Academic

Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems

🔗LLM Workflows Academic

IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking

🔗LLM Workflows Academic

Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

🧠LLMs Academic

arxiv.org··Hacker News

CRANE: Knowledge Editing for Reasoning MLLMs

🔗LLM Workflows Academic

Operationalizing Linguistic Methods through Prompt-Engineering Skills: An Automatic Chinese Web Neologism Detection Pipeline

🧠LLMs Academic

Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents

🕵️AI Agents Academic

Tight Sample Complexity of Transformers

🔗LLM Workflows Academic

TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization

🔗LLM Workflows Academic

Toward Agentic Governance: What Shapes LLM-Agent Intervention in Public Forums?

🔗LLM Workflows Academic

Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention

🔗LLM Workflows Academic

DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning

🔗LLM Workflows Academic

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

🧠LLMs Academic

UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding

🧠LLMs Academic

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

🕵️AI Agents Academic

Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models

🧠LLMs Academic

GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks

🧠LLMs Academic

Log in to enable infinite scrolling