Qingjie Liu

A3Bench: an audience-aligned multilingual benchmark for video audience insights understanding

Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents

Experiments on WebShop, ALFWorld, and visual Sokoban show consistent improvements across language and vision-language models, while diagnostic ablations support the effectiveness of Bellman fixed-point value estimation and show that step-level credit should be incorporated selectively rather than uniformly into the final advantage.

LivingRAG: Augmenting Graph RAG with Experience

LivingRAG adds a writable experience store to a graph-based retrieval backbone, enabling verified experiences to be reused during inference in two ways, and analyzes online QA streams and finds reusable signals from shared entities, graph neighborhoods, and question templates.