8 papers
AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning
Peilin Wu, Xinlu Zhang, Kun Wan +4
Rubric-based reward shaping provides interpretable and editable reward signals for fine-tuning LLMs via reinforcement learning (RL), but existing adaptive rubric methods typically…
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
Peilin Wu, Mian Zhang, Kun Wan +4
Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behavi…
Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers
Kaiyu He, Zhang Mian, Peilin Wu +2
While Large Language Models (LLMs) excel at factual retrieval, they often struggle with the "curse of two-hop reasoning" in compositional tasks. Recent research suggests that param…
Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
Peilin Wu, Mian Zhang, Xinlu Zhang +2
Agentic Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by enabling dynamic, multi-step reasoning and information retrieval. However, these system…
GEAR: A General Evaluation Framework for Abductive Reasoning
Kaiyu He, Peilin Wu, Mian Zhang +4
Since the advent of large language models (LLMs), research has focused on instruction following and deductive reasoning. A central question remains: can these models discover new k…
LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
Shuo Yan, Ruochen Li, Ziming Luo +11
Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery. However, their capability in the fundamental yet crucial task of reprodu…