Retrieval-Augmented Generation (RAG) systems face challenges with complex, multi-hop questions, and iterative agentic frameworks such as Search-R1 (Jin et al., 2025) have been proposed to address these complexities. However, such approaches can introduce inefficiencies, including repetitive retrieval of previously processed information and challenges in contextualizing retrieved results effectively within the current generation prompt. Such issues can lead to unnecessary retrieval turns, suboptimal reasoning, inaccurate answers, and increased token consumption. In this paper, we investigate test-time modifications to Search-R1’s open-source Qwen2.5-7B pipeline to mitigate these identified shortcomings. Specifically, we explore the integration of two components and their combination: a contextualization module to better integrate relevant information from retrieved documents into reasoning, and a de-duplication module that replaces previously retrieved documents with the next most relevant ones. We evaluate our approaches using the HotpotQA (Yang et al., 2018) and the Natural Questions (Kwiatkowski et al., 2019) datasets, reporting the exact match (EM) score, an LLM-as-a-Judge assessment of answer correctness, and the average number of turns. Our best-performing variant (contextualization) achieves a 5.6% increase in EM score and reduces the average number of turns by 10.5% compared to the Search-R1 baseline. While contextualization itself introduces additional LLM calls, our results demonstrate improved answer accuracy and reduced retrieval load.

Persona agents, which are LLM agents conditioned to act according to an assigned persona, enable contextually rich and user-aligned interactions across domains like education and healthcare.However, evaluating how faithfully these agents adhere to their personas remains a significant challenge, particularly in free-form settings that demand consistency across diverse, persona-relevant environments.We introduce PersonaGym, the first dynamic evaluation framework for persona agents, and PersonaScore, a human-aligned automatic metric grounded in decision theory that enables comprehensive large-scale evaluation. Our evaluation of 10 leading LLMs across 200 personas and 10,000 questions reveals significant advancement opportunities.For example, GPT-4.1 had the exact same PersonaScore as LLaMA-3-8b despite being a more recent and advanced closed-source model. Importantly, increased model size and complexity do not necessarily enhance persona agent capabilities, underscoring the need for algorithmic and architectural innovation toward faithful, performant persona agents.

This paper studies the use of style embeddings to enhance author profiling for the goal of personalization of Large Language Models (LLMs). Using a style-based Retrieval-Augmented Generation (RAG) approach, we meticulously study the efficacy of style embeddings in capturing distinctive authorial nuances. The proposed method leverages this acquired knowledge to enhance the personalization capabilities of LLMs. In the assessment of this approach, we have employed the LaMP benchmark, specifically tailored for evaluating language models across diverse dimensions of personalization. The empirical observations from our investigation reveal that, in comparison to term matching or context matching, style proves to be marginally superior in the development of personalized LLMs.