Shuai Liu

Schema-Conditioned Memory Evidence Ranking for Underspecified Tool Calls: A Controlled Study on Mem2ActBench

Large language model (LLM) agents often need historical conversations to recover argument values omitted from current tool requests. This study introduces SCAR–Pair, a two-stage ranker for memory retrieval after tool selection. It separates schema-expanded candidate generation from parameter-level scoring and integrate...