← Search

Peijie Liu

2 accepted papers

2025

AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems

NeurIPS 2025spotlight

The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs’ advanced reasoning and role-playing capabilities to enable autonomous, adaptive decision-making. Unlike traditional recommendation approa…

Cited by 0SourcecodeScholar
2025

Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models

ICML 2025poster

Chain-of-Thought (CoT) technique has proven effective in improving the performance of large language models (LLMs) on complex reasoning tasks. However, the performance gains are inconsistent across different tasks, and the underlying mechanism remains a long-standing research question. In this work,…