Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding

• URL: http://arxiv.org/abs/2608.05876v1
• Date: Thu, 06 Aug 2026 10:58:17 GMT
• Title: Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding
• Abstract summary: G-STEER learns a clarification policy from graph-scaffolded trajectories spanning diverse factor dependencies and evidence conditions.<n>Experiments show that G-STEER achieves the strongest overall weighted target coverage and the highest downstream report personalization across both evaluated DRAs.
• Score: 9.25068659105141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: User requests serve as research specifications for deep research agents, shaping what evidence to seek and how to synthesize it. In personalized deep research, these specifications must additionally reflect user goals, constraints, preferences, and evaluation criteria. User context can be incorporated either within the deep research pipeline or into the research specification provided as its input. We focus on the latter, refining the user request into a personalized research specification before passing it to an unchanged deep research agent. This requires resolving three coupled decisions: which framing factors are relevant, whether the available user context sufficiently supports them, and whether to retrieve user memory, ask the user, or stop and refine the query. For training, G-STEER organizes framing factors as elicitation targets in an Intent Elicitation Graph that captures their dependencies. It learns a clarification policy from graph-scaffolded trajectories spanning diverse factor dependencies and evidence conditions. The policy produces a refined query while balancing target coverage against the costs of evidence acquisition. Experiments show that G-STEER achieves the strongest overall weighted target coverage and the highest downstream report personalization across both evaluated DRAs, while asking roughly one third as many user questions as a strong clarification baseline.

Related papers

• DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents [17.420077157633852]
  Reinforcement learning with rubric-based rewards improves deep research agents by optimizing them against checkable criteria that translate report quality into reward signals.<n>Most existing studies ask an LLM to generate rubrics for a given query, but when the model fails to infer the underlying information needs, the generated rubrics may be incomplete and reduce RL efficiency.<n>To obtain more reliable query--rubric supervision, we introduce DeepRubric, a data construction framework that reverses this process.
  arXiv  Detail & Related papers  (2026-06-15T17:52:27Z)
• Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery [36.57361069825463]
  We introduce Personalized Deep Research (PDR), a framework that integrates dynamic user context into the core retrieval-reasoning loop.<n>PDR unifies user profile modeling with iterative query development, dual-stage (private/public) retrieval, and context-aware synthesis.<n>This allows the system to autonomously align research sub-goals with user intent and optimize the stopping criteria for evidence collection.
  arXiv  Detail & Related papers  (2026-05-11T13:14:54Z)
• Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering [39.08300602619814]
  Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context.<n>We propose PR2, a reinforcement learning framework that integrates reasoning and retrieval from personal context for personalization.
  arXiv  Detail & Related papers  (2026-02-22T19:43:43Z)
• SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback [68.60326181052658]
  We propose an agentic pipeline that automatically generates high quality, difficulty-controlled deep search question-answer pairs.<n>Our pipeline, SAGE, consists of a data generator which proposes QA pairs and a search agent which attempts to solve the generated question.<n>Our intrinsic evaluation shows SAGE generates questions that require diverse reasoning strategies, while significantly increases the correctness and difficulty of the generated data.
  arXiv  Detail & Related papers  (2026-01-26T06:37:56Z)
• Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards [60.0970117192627]
  Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents.<n>Existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of agents' reasoning process.<n>We propose textbfCitation-aware RL Rewards (CaRR), a fine-grained reward framework for deep search agents.
  arXiv  Detail & Related papers  (2026-01-09T18:57:53Z)
• Query Decomposition for RAG: Balancing Exploration-Exploitation [83.79639293409802]
  RAG systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggregating them to generate an answer.<n>We formulate query decomposition and document retrieval in an exploitation-exploration setting, where retrieving one document at a time builds a belief about the utility of a given sub-queries.<n>Our main finding is that estimating document relevance using rank information and human judgments yields a 35% gain in document-level precision, 15% increase in alpha-nDCG, and better performance on the downstream task of long-form generation.
  arXiv  Detail & Related papers  (2025-10-21T13:37:11Z)
• Towards Personalized Deep Research: Benchmarks and Evaluations [56.581105664044436]
  We introduce Personalized Deep Research Bench, the first benchmark for evaluating personalization in Deep Research Agents (DRAs)<n>It pairs 50 diverse research tasks with 25 authentic user profiles that combine structured persona attributes with dynamic real-world contexts, yielding 250 realistic user-task queries.<n>Our experiments on a range of systems highlight current capabilities and limitations in handling personalized deep research.
  arXiv  Detail & Related papers  (2025-09-29T17:39:17Z)
• Characterizing Deep Research: A Benchmark and Formal Definition [24.523394260858822]
  We propose a formal characterization of the deep research (DR) task and introduce a benchmark to evaluate the performance of DR systems.<n>We argue that the core defining feature of deep research is not the production of lengthy report-style outputs, but rather the high fan-out over concepts required during the search process.
  arXiv  Detail & Related papers  (2025-08-06T08:09:28Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness [56.42192735214931]
  retrievers are expected to not only rely on the semantic relevance between the documents and the queries but also recognize the nuanced intents or perspectives behind a user query. In this work, we study whether retrievers can recognize and respond to different perspectives of the queries. We show that current retrievers have limited awareness of subtly different perspectives in queries and can also be biased toward certain perspectives.
  arXiv  Detail & Related papers  (2024-05-04T17:10:00Z)
• High Quality Related Search Query Suggestions using Deep Reinforcement Learning [0.15229257192293202]
  "High Quality Related Search Query Suggestions" task aims at recommending search queries which are real, accurate, diverse, relevant and engaging. We train a Deep Reinforcement Learning model to predict the query a user would enter next. The reward signal is composed of long-term session-based user feedback, syntactic relatedness and estimated naturalness of generated query.
  arXiv  Detail & Related papers  (2021-08-10T05:22:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.