Year: 2026
Type: conference-paper
Abstract: Retrieval-augmented generation (RAG) effectively extends the knowledge boundaries of large language models (LLMs) for complex tasks, yet current paradigms typically optimize for an interleaving of reasoning and retrieval, where models fail to critically evaluate retrieved information against the target question.Most existing methods rely on sparse outcomebased rewards, failing to provide explicit supervision for the internal reasoning process or to diagnose information inadequacy.To address this, we propose Eval-RAR, an Evaluationdriven Retrieval-Augmented Reasoning framework.Eval-RAR introduces a "Search-then-Evaluate" paradigm where the model performs explicit self-evaluation after each search step, generating a rationale to either identify sufficient evidence or specify missing information to guide subsequent queries.To optimize this process, we employ reinforcement learning with a fine-grained evaluation reward, providing intermediate feedback that encourages the model to track core entities and maintain logical consistency.Experiments on seven single-hop and multi-hop QA benchmarks demonstrate that Eval-RAR outperforms existing methods.
Authors: Heng Yu, Rui Li, Qi Liu, Wenjun Feng, Junfeng Kang, Yi Zhan
Institution: University of Science and Technology of China
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166899400