Tag: autonomous agents
Browse our exclusive articles!
Turing Test on Screen: Benchmarking Mobile GUI Agent Humanization
Explore the Turing Test on Screen benchmark for enhancing mobile GUI agents' human-like behavior to improve detection and interaction in digital environmen...
CORA: Risk-Controlled Agents for Safe Mobile GUI Automation
Discover CORA, a framework ensuring safe, risk-controlled autonomous mobile GUI automation with formal guarantees and real-world benchmark validation.
Constraint-Aware Memory Boosts Language-Based Drug Discovery
Discover how Constraint-Aware Corrective Memory (CACM) improves language-based drug discovery with precise diagnostics and 36% higher success rates.
TraceSafe: Assessing LLM Guardrails in Multi-Step Tool Use
Explore TraceSafe-Bench, the first benchmark evaluating LLM guardrails' effectiveness in multi-step tool-calling trajectories for enhanced AI safety.
AgentCity: Governance Model for Autonomous AI Economies
Discover AgentCity's Separation of Power model enabling transparent, accountable governance for autonomous AI agent economies via smart contracts.