FlashResearch: Real-time Agent Orchestration for Efficient Deep Research

• URL: http://arxiv.org/abs/2510.05145v1
• Date: Thu, 02 Oct 2025 00:15:39 GMT
• Title: FlashResearch: Real-time Agent Orchestration for Efficient Deep Research
• Abstract summary: FlashResearch is a novel framework for efficient deep research.<n>It transforms sequential processing into parallel, runtime orchestration.<n>It can deliver up to a 5x speedup while maintaining comparable quality.
• Score: 62.03819662340356
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep research agents, which synthesize information across diverse sources, are significantly constrained by their sequential reasoning processes. This architectural bottleneck results in high latency, poor runtime adaptability, and inefficient resource allocation, making them impractical for interactive applications. To overcome this, we introduce FlashResearch, a novel framework for efficient deep research that transforms sequential processing into parallel, runtime orchestration by dynamically decomposing complex queries into tree-structured sub-tasks. Our core contributions are threefold: (1) an adaptive planner that dynamically allocates computational resources by determining research breadth and depth based on query complexity; (2) a real-time orchestration layer that monitors research progress and prunes redundant paths to reallocate resources and optimize efficiency; and (3) a multi-dimensional parallelization framework that enables concurrency across both research breadth and depth. Experiments show that FlashResearch consistently improves final report quality within fixed time budgets, and can deliver up to a 5x speedup while maintaining comparable quality.

Related papers

• Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques [45.003333444832656]
  Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models.<n> realizing this efficiency requires specialized inference mechanisms, such as diffusion-aware caching and reuse.<n>We introduce a unified latency decomposition framework for dLLMs to disentangle these factors and analyze their impact on inference speed in real deployments.
  arXiv  Detail & Related papers  (2026-07-14T14:48:06Z)
• DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning [58.09293442211248]
  Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks.<n>This report presents DuMate-DeepResearch, a multi-agent DR framework built on the Qianfan Agent Foundry.
  arXiv  Detail & Related papers  (2026-06-05T14:10:48Z)
• Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis [64.2820121997882]
  We introduce HierFlow, a training-free, test-time hierarchical search architecture that automates agentic workflow design.<n> HierFlow maximizes efficiency through an intelligent gating module that selectively triggers execution-level searches based on contextual necessity.<n> Comprehensive testing across question answering, mathematical reasoning, and code generation benchmarks confirms that HierFlow consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-05-20T01:56:11Z)
• Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design [39.31356016375221]
  Marco DeepResearch is a deep research agent optimized with a verification-centric framework design at three levels.<n>We introduce verification mechanisms to graph-based and agent-based QA synthesis to control question difficulty.<n>We design a verification-driven synthesis trajectory method that injects explicit verification patterns into training trajectories.<n>We use Marco DeepResearch itself as a verifier at inference time and effectively improve performance on challenging questions.
  arXiv  Detail & Related papers  (2026-03-30T12:42:02Z)
• REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents [40.38002661542917]
  REDSearcher is a unified framework that codesigns complex task synthesis, midtraining, and posttraining for scalable searchagent optimization.<n>We introduce toolaugmented queries to encourage proactive tool use rather than passive recall.<n>During midtraining, we strengthen core atomic capabilities knowledge, planning, and function calling.<n>We build a local simulated environment that enables rapid, lowcost algorithmic iteration for reinforcement learning experiments.
  arXiv  Detail & Related papers  (2026-02-15T17:04:46Z)
• Deep Researcher with Sequential Plan Reflection and Candidates Crossover (Deep Researcher Reflect Evolve) [0.0]
  This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics.<n>Our system utilizes two key innovations: Sequential Research Plan Refinement via Reflection and a Candidates Crossover algorithm.<n>Our architecture achieved an overall score of 46.21, demonstrating superior performance by surpassing leading deep research agents.
  arXiv  Detail & Related papers  (2026-01-28T18:45:39Z)
• SpatCode: Rotary-based Unified Encoding Framework for Efficient Spatiotemporal Vector Retrieval [24.77802224063016]
  We present a unified vector retrieval framework that integrates temporal, spatial, and semantic similarity.<n>Our framework substantially outperforms the baselines in both retrieval accuracy and efficiency.<n>These results highlight the effectiveness of the proposed approach for scalabletemporal information retrieval in intelligent systems.
  arXiv  Detail & Related papers  (2026-01-14T14:53:06Z)
• A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent (Static-DRA) [0.0]
  This paper introduces the Static Deep Research Agent (Static-DRA), a novel solution built upon a hierarchical Tree-based static workflow.<n>The core contribution is the integration of two user-tunable parameters, Depth and Breadth, which provide granular control over the research intensity.<n>The agent's architecture, comprising Supervisor, Independent, and Worker agents, facilitates effective multi-hop information retrieval.
  arXiv  Detail & Related papers  (2025-12-03T15:37:13Z)
• ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking [59.65564262588308]
  Parallel thinking expands exploration breadth, complementing the deep exploration of information-seeking (IS) agents.<n>We propose ParallelMuse, a two-stage paradigm designed for deep IS agents.<n> Experiments across multiple open-source agents and benchmarks demonstrate up to 62% performance improvement.
  arXiv  Detail & Related papers  (2025-10-28T17:51:50Z)
• Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey [92.71325249013535]
  Deliberative tree search is a cornerstone of Large Language Model (LLM) research.<n>This paper introduces a unified framework that deconstructs search algorithms into three core components.
  arXiv  Detail & Related papers  (2025-10-11T03:29:18Z)
• Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution [48.7788770680643]
  Flash-Searcher is a novel parallel agent reasoning framework.<n>It decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths.<n>It achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks.
  arXiv  Detail & Related papers  (2025-09-29T17:39:30Z)
• 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)
• WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents [72.28593628378991]
  WebResearcher is an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process.<n>WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.
  arXiv  Detail & Related papers  (2025-09-16T17:57:17Z)
• Deep Researcher with Test-Time Diffusion [32.375428487905104]
  Test-Time Diffusion Deep Researcher conceptualizes research report generation as a diffusion process.<n>Draft-centric design makes the report writing process more timely and coherent.<n>We demonstrate that our TTD-DR achieves state-of-the-art results on a wide array of benchmarks.
  arXiv  Detail & Related papers  (2025-07-21T21:23:21Z)
• SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis [94.33978856270268]
  Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios.<n>Existing approaches face critical limitations that lack high-quality training trajectories and suffer from distributional mismatches.<n>This paper introduces SimpleDeepSearcher, a framework that bridges the gap through strategic data engineering rather than complex training paradigms.
  arXiv  Detail & Related papers  (2025-05-22T16:05:02Z)
• Recurrent Auto-Encoders for Enhanced Deep Reinforcement Learning in Wilderness Search and Rescue Planning [0.294944680995069]
  Wilderness search and rescue operations are often carried out over vast landscapes.<n>The problem is not one of complete coverage, but one of maximizing the information gathered in the limited time available.<n>We propose that a combination of a recurrent autoencoder and deep reinforcement learning is a more efficient solution to the search problem.
  arXiv  Detail & Related papers  (2025-02-26T17:54:47Z)

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.