3 papers
cs.CL2026
Mitigating Exploration Bias in RL for Multi-Instruction Following
Mian Zhang, Yueqin Yin, Kaiyu He +4
RL has emerged as a powerful paradigm for enhancing the instruction following capabilities of LLMs. While existing training recipes achieve substantial gains, we find that they suf…
cs.CL2025
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…
cs.CL2025
Do Retrieval-Augmented Language Models Adapt to Varying User Needs?
Peilin Wu, Xinlu Zhang, Wenhao Yu +3
Recent advancements in Retrieval-Augmented Language Models (RALMs) have demonstrated their efficacy in knowledge-intensive tasks. However, existing evaluation benchmarks often assu…