PaSa: An LLM Agent for Comprehensive Academic Paper Search

1 code implementation • 17 Jan 2025 • Yichen He, Guanhua Huang, Peiyuan Feng, Yuan Lin, Yuchen Zhang, Hang Li, Weinan E

Notably, PaSa-7B surpasses the best Google-based baseline, Google with GPT-4o, by 37. 78% in recall@20 and 39. 90% in recall@50.

AGILE: A Novel Reinforcement Learning Framework of LLM Agents

1 code implementation • 23 May 2024 • Peiyuan Feng, Yichen He, Guanhua Huang, Yuan Lin, Hanchong Zhang, Yuchen Zhang, Hang Li

Our ablation study highlights the indispensability of memory, tools, consultation, reflection, and reinforcement learning in achieving the agent's strong performance.

Question Answering reinforcement-learning +2