Agent Seer: Synthesizing Scenarios from Specification Understanding
Joint Optimization of Tool Creation and Use for Large Language Model Agents
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
Autogenesis A Self-Evolving Agent Protocol
Externalization in LLM Agents A Unified Review of Memory Skills Protocols and Harness Engineering
ReAct Synergizing Reasoning and Acting in Language Models
Automating Database-Native Function Code Synthesis with LLMs
Act Wisely Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models