Tag: autonomous agents
Browse our exclusive articles!
AgentHazard: Benchmark for Detecting Harmful Agent Behavior
AgentHazard benchmark evaluates harmful behavior in computer-use agents, highlighting safety risks and the need for improved safeguards in AI models.
Experiential Reflective Learning Boosts LLM Agent Adaptability
Discover how Experiential Reflective Learning enhances self-improving LLM agents by enabling rapid adaptation and improved task success rates.
6GAgentGym: Autonomous Learning for 6G Network Management
Discover 6GAgentGym, a framework enabling autonomous agents to manage 6G networks using tool use, data synthesis, and closed-loop learning.
Multi-Agent Collaboration for Automated Research: Empirical Study
Explore how multi-agent systems improve automated research efficiency and effectiveness through empirical analysis of coordination frameworks.
APEX-EM: Advanced Online Learning for Autonomous Agents
Discover APEX-EM, a non-parametric online learning framework boosting autonomous agents' performance with structured procedural experience replay.