arXiv:2605.24266v1 Announce Type: new 
Abstract: Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended queries by combining retrieval, reasoning, and generation. Yet most frameworks rely on rigid workflows with one-shot scoping and long autonomous runs, offering little room for course correction if user intent shifts mid-process. We present SteER, a framework for Steerable deEp Research that introduces interpretable, mid-process control into long-horizon research workflows. At each decision point, SteER uses a cost-benefit formulation to determine whether to pause for user input or to proceed autonomously. It combines diversity-aware planning with utility signals that reward alignment, novelty, and coverage, and maintains a live persona model that evolves throughout the session. SteER outperforms state-of-the-art open-source and proprietary baselines by up to 22.80\% on alignment, leads on quality metrics such as breadth and balance, and is preferred by human readers in 85\%+ of pairwise alignment judgments. We also introduce a persona-query benchmark and data-generation pipeline. To our knowledge, this is the first work to advance deep research with an interactive, interpretable control paradigm, paving the way for controllable, user-aligned agents in long-form tasks.

أدت التطورات الأخيرة في نماذج اللغة الكبيرة (LLMs) إلى تطوير SteER، وهو إطار مصمم للبحث العميق القابل للتوجيه، والذي يعزز تفاعل المستخدم أثناء سير العمل البحثي طويل الأمد من خلال السماح بالتحكم واتخاذ القرارات أثناء العملية.

Los avances recientes en modelos de lenguaje de gran tamaño (LLMs) han llevado al desarrollo de SteER, un marco diseñado para la investigación profunda orientable, que mejora la interacción del usuario durante los flujos de investigación a largo plazo al permitir el control y la toma de decisiones en medio del proceso.

Des avancées récentes dans les modèles de langage de grande taille (LLMs) ont conduit au développement de SteER, un cadre conçu pour la recherche approfondie orientable, qui améliore l'interaction utilisateur lors des flux de recherche à long terme en permettant un contrôle et une prise de décision en cours de processus.

Recent advancements in large language models (LLMs) have led to the development of SteER, a framework designed for steerable deep research, which enhances user interaction during long-term research workflows by allowing mid-process control and decision-making.