2 papers
cs.MA2026
Living-Harness Is an Interactive-Agent Evolver
Yuetian Du, Yucheng Wang, He Xu +9
Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedba…
cs.IR2026
An LLM-powered Agentic Recommendation System for Connected TV Content Discovery
Lei Shi, Di Wang, Harry Tran +23
Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such as trending topic…