Deep Research Pretraining via Predictive Navigation

• URL: http://arxiv.org/abs/2608.00432v1
• Date: Sat, 01 Aug 2026 04:17:14 GMT
• Title: Deep Research Pretraining via Predictive Navigation
• Abstract summary: Deep Research Pretraining is an offline framework that derives predictive navigation supervision from naturally occurring evidence structures.<n>It teaches models what to search for, which documents to inspect, and how to synthesize evidence.
• Score: 14.408072671638779
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep research agents are often trained on expensive, environment-grounded tool-use trajectories that require repeated retrieval, document inspection, and report evaluation. We introduce Deep Research Pretraining (DRP), an offline framework that derives predictive navigation supervision from naturally occurring evidence structures. Given a citation-bearing or hyperlinked passage, DRP constructs a proxy research objective, recovers linked evidence and graph-related alternatives, and converts them into search-open-write trajectories. This teaches models what to search for, which documents to inspect, and how to synthesize evidence, without a live retrieval environment or executed policy rollout. We instantiate DRP on scholarly citation graphs (DRP-Paper) and Wikipedia hyperlinks (DRP-Web), continually pretrain separate Qwen3-14B-Base models on 1B tokens, and fine-tune them on controlled fractions of 13K agent trajectories. Across five independently sampled subsets at each low-data budget, both variants consistently outperform matched no-DRP models on DeepResearch Bench. With one quarter of the SFT data, DRP-Web even surpasses a fixed no-DRP full-data checkpoint, with gains transferring to ResearchQA, WebWalkerQA, and SimpleQA. Starting from matched low-data SFT checkpoints, the DRP-Web advantage also persists through subsequent agentic RL. Source-matched and evidence-mismatch controls indicate that these improvements arise from evidence-conditioned navigation rather than domain exposure or agent-format imitation. DRP thus provides a promising complementary approach to trajectory-based agent training.

Related papers

• PathRouter: Aligning Rewards with Retrieval Quality in Agentic Graph Retrieval-Augmented Generation [41.730631759393525]
  Agentic GraphRAG trains language-model agents to iteratively retrieve and reason over graph-structured evidence.<n>We present Path, a path-aware training framework for agentic GraphRAG.
  arXiv  Detail & Related papers  (2026-06-15T08:48:04Z)
• VeriTrace: Evolving Mental Models for Deep Research Agents [43.43659414477917]
  Deep research agents face vast, interdependent, and pervasively uncertain information.<n>Existing systems explore what evolving intermediate representations should look like, but leave their evolution to the implicit reasoning.<n>We argue that an agent's mental model should instead evolve through explicit feedback that continuously aligns task understanding with reality.
  arXiv  Detail & Related papers  (2026-05-25T17:46:57Z)
• MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning [74.07254720088926]
  We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering.<n>We propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO.<n>Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%.
  arXiv  Detail & Related papers  (2026-04-15T07:39:08Z)
• Process Reward Agents for Steering Knowledge-Intensive Reasoning [18.184546182516225]
  We introduce Process Reward Agents (PRA), a test-time method for providing domain-grounded, online, step-wise rewards to a frozen policy.<n>PRA consistently outperforms strong baselines, achieving 80.8% accuracy on MedQA with Qwen3-4B.<n> PRA generalizes to unseen frozen policy models ranging from 0.5B to 8B parameters, improving their accuracy by up to 25.7% without any policy model updates.
  arXiv  Detail & Related papers  (2026-04-10T16:45:44Z)
• AgentIR: Reasoning-Aware Retrieval for Deep Research Agents [76.29382561831105]
  Deep Research agents generate explicit natural language reasoning before each search call.<n> Reasoning-Aware Retrieval embeds the agent's reasoning trace alongside its query.<n>DR- Synth generates Deep Research retriever training data from standard QA datasets.<n>AgentIR-4B achieves 68% accuracy with the open-weight agent Tongyi-DeepResearch.
  arXiv  Detail & Related papers  (2026-03-04T18:47:26Z)
• TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG [71.06073770344732]
  Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval.<n>We present TreePS-RAG, an online, tree-based RL framework for agentic RAG that enables step-wise credit assignment while retaining outcome-only rewards.
  arXiv  Detail & Related papers  (2026-01-11T14:07:30Z)
• Step-DeepResearch Technical Report [90.50586290399683]
  We introduce Step-DeepResearch, a cost-effective, end-to-end agent.<n>We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing.<n>To bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios.
  arXiv  Detail & Related papers  (2025-12-23T16:32:27Z)
• WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research [73.58638285105971]
  This paper tackles textbfopen-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports.<n>We introduce textbfWebWeaver, a novel dual-agent framework that emulates the human research process.<n>Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym.
  arXiv  Detail & Related papers  (2025-09-16T17:57:21Z)
• DPTDR: Deep Prompt Tuning for Dense Passage Retrieval [53.217524851268216]
  Deep prompt tuning (DPT) has gained great success in most natural language processing(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning(FT) still dominates. We propose two model-agnostic and task-agnostic strategies for DPT-based retrievers, namely retrieval-oriented intermediate pretraining and unified negative mining.
  arXiv  Detail & Related papers  (2022-08-24T12:55:00Z)

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.