Tag: LLM agents
Browse our exclusive articles!
Many-Tier Instruction Hierarchy for Advanced LLM Agents
Explore Many-Tier Instruction Hierarchy (ManyIH) to improve how LLM agents handle conflicting instructions with scalable privilege levels.
LLM Agents Enhance Diagnostic Reasoning with Scaffolding
Discover how LLM-based agents using structuring and problematizing scaffolds boost diagnostic reasoning in vocational learning scenarios.
SEA-Eval: Benchmark for Evaluating Self-Evolving AI Agents
Discover SEA-Eval, a benchmark designed to evaluate self-evolving AI agents beyond episodic tasks, focusing on long-term performance and reliability.
Deep Researcher Agent: 24/7 AI Experimentation Framework
Discover the Deep Researcher Agent, an autonomous AI framework enabling 24/7 deep learning experiments with zero-cost monitoring and enhanced efficiency.
STEP-HRL: Efficient Hierarchical RL for LLM Agents
Discover STEP-HRL, a hierarchical reinforcement learning framework that boosts LLM agents' efficiency with step-level transitions and reduced token use.