2 papers
cs.LG2026
Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems
Tan Zhu, Tong Yao, Kananart Kuwaranancharoen +4
Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights. Extending this par…
cs.CL2026
From Symbolic to Natural-Language Relations: Rethinking Knowledge Graph Construction in the Era of Large Language Models
Kanyao Han, Yushang Lai
Knowledge graphs (KGs) have commonly been constructed using predefined symbolic relation schemas, typically implemented as categorical relation labels. This design has notable shor…