Tag: LLM agents
Browse our exclusive articles!
WebXSkill: Enhancing Autonomous Web Agents with Executable Skills
Discover WebXSkill, a framework that boosts autonomous web agents' efficiency by bridging the grounding gap with executable skills and natural language gui...
Mobile GUI Agents: Testing Real-World Threat Resilience
Explore how mobile GUI agents perform under real-world threats with new testing frameworks revealing significant performance drops.
Autonomous LLM Research Loop in Computational Physics
Explore how autonomous LLM agents read, reproduce, critique, and extend computational physics research for groundbreaking scientific automation.
How Effectively Do Agents Follow Task Plans?
Explore how programming agents comply with task plans, the impact on performance, and strategies to improve plan adherence for better results.
Dual-Trace Encoding Boosts Cross-Session Recall in LLM Agents
Discover how dual-trace encoding enhances cross-session memory recall in LLM agents, improving temporal reasoning and knowledge tracking by 20%.